David Menotti

Sarthak Pati, Ujjwal Baid, Brandon Edwards et al.

Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data. This is currently addressed by centrally sharing ample, and importantly diverse, data from multiple sites. However, such centralization is challenging to scale (or even not feasible) due to various limitations. Federated ML (FL) provides an alternative to train accurate and generalizable ML models, by only sharing numerical model updates. Here we present findings from the largest FL study to-date, involving data from 71 healthcare institutions across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, utilizing the largest dataset of such patients ever used in the literature (25,256 MRI scans from 6,314 patients). We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent. We anticipate our study to: 1) enable more studies in healthcare informed by large and diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further quantitative analyses for glioblastoma via performance optimization of our consensus model for eventual public release, and 3) demonstrate the effectiveness of FL at such scale and task complexity as a paradigm shift for multi-site collaborations, alleviating the need for data sharing.

Valfride Nascimento, Rayson Laroca, Jorge de A. Lambert et al.

The License Plate Recognition (LPR) field has made impressive advances in the last decade due to novel deep learning approaches combined with the increased availability of training data. However, it still has some open issues, especially when the data come from low-resolution (LR) and low-quality images/videos, as in surveillance systems. This work focuses on license plate (LP) reconstruction in LR and low-quality images. We present a Single-Image Super-Resolution (SISR) approach that extends the attention/transformer module concept by exploiting the capabilities of PixelShuffle layers and that has an improved loss function based on LPR predictions. For training the proposed architecture, we use synthetic images generated by applying heavy Gaussian noise in terms of Structural Similarity Index Measure (SSIM) to the original high-resolution (HR) images. In our experiments, the proposed method outperformed the baselines both quantitatively and qualitatively. The datasets we created for this work are publicly available to the research community at https://github.com/valfride/lpr-rsr/

Marcelo dos Santos, Rayson Laroca, Rafael O. Ribeiro et al.

Diffusion models have proven effective for various applications such as images, audio and graph generation. Other important applications are image super-resolution and the solution of inverse problems. More recently, some works have used stochastic differential equations (SDEs) to generalize diffusion models to continuous time. In this work, we introduce SDEs to generate super-resolution face images. To the best of our knowledge, this is the first time SDEs have been used for such an application. The proposed method provides an improved peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and consistency than the existing super-resolution methods based on diffusion models. In particular, we also assess the potential application of this method for the face recognition task. A generic facial feature extractor is used to compare the super-resolution images with the ground truth and superior results were obtained compared with other methods. Our code is publicly available at https://github.com/marcelowds/sr-sde

Valfride Nascimento, Rayson Laroca, Rafael O. Ribeiro et al.

Despite significant advancements in License Plate Recognition (LPR) through deep learning, most improvements rely on high-resolution images with clear characters. This scenario does not reflect real-world conditions where traffic surveillance often captures low-resolution and blurry images. Under these conditions, characters tend to blend with the background or neighboring characters, making accurate LPR challenging. To address this issue, we introduce a novel loss function, Layout and Character Oriented Focal Loss (LCOFL), which considers factors such as resolution, texture, and structural details, as well as the performance of the LPR task itself. We enhance character feature learning using deformable convolutions and shared weights in an attention module and employ a GAN-based training approach with an Optical Character Recognition (OCR) model as the discriminator to guide the super-resolution process. Our experimental results show significant improvements in character reconstruction quality, outperforming two state-of-the-art methods in both quantitative and qualitative measures. Our code is publicly available at https://github.com/valfride/lpsr-lacd

Marcelo dos Santos, Rayson Laroca, Rafael O. Ribeiro et al.

Super-resolution algorithms often struggle with images from surveillance environments due to adverse conditions such as unknown degradation, variations in pose, irregular illumination, and occlusions. However, acquiring multiple images, even of low quality, is possible with surveillance cameras. In this work, we develop an algorithm based on diffusion models that utilize a low-resolution image combined with features extracted from multiple low-quality images to generate a super-resolved image while minimizing distortions in the individual's identity. Unlike other algorithms, our approach recovers facial features without explicitly providing attribute information or without the need to calculate a gradient of a function during the reconstruction process. To the best of our knowledge, this is the first time multi-features combined with low-resolution images are used as conditioners to generate more reliable super-resolution images using stochastic differential equations. The FFHQ dataset was employed for training, resulting in state-of-the-art performance in facial recognition and verification metrics when evaluated on the CelebA and Quis-Campi datasets. Our code is publicly available at https://github.com/marcelowds/fasr

Valter Estevam, Rayson Laroca, Helio Pedrini et al.

The success of Zero-shot Action Recognition (ZSAR) methods is intrinsically related to the nature of semantic side information used to transfer knowledge, although this aspect has not been primarily investigated in the literature. This work introduces a new ZSAR method based on the relationships of actions-objects and actions-descriptive sentences. We demonstrate that representing all object classes using descriptive sentences generates an accurate object-action affinity estimation when a paraphrase estimation method is used as an embedder. We also show how to estimate probabilities over the set of action classes based only on a set of sentences without hard human labeling. In our method, the probabilities from these two global classifiers (i.e., which use features computed over the entire video) are combined, producing an efficient transfer knowledge model for action classification. Our results are state-of-the-art in the Kinetics-400 dataset and are competitive on UCF-101 under the ZSAR evaluation. Our code is available at https://github.com/valterlej/objsentzsar

Pietro Melzi, Ruben Tolosana, Ruben Vera-Rodriguez et al.

Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail. This paper offers an overview of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at WACV 2024. This is the first international challenge aiming to explore the use of synthetic data in face recognition to address existing limitations in the technology. Specifically, the FRCSyn Challenge targets concerns related to data privacy issues, demographic biases, generalization to unseen scenarios, and performance limitations in challenging scenarios, including significant age disparities between enrollment and testing, pose variations, and occlusions. The results achieved in the FRCSyn Challenge, together with the proposed benchmark, contribute significantly to the application of synthetic data to improve face recognition technology.

Pedro C. Neto, Fadi Boutros, Joao Ribeiro Pinto et al.

This work summarizes the IJCB Occluded Face Recognition Competition 2022 (IJCB-OCFR-2022) embraced by the 2022 International Joint Conference on Biometrics (IJCB 2022). OCFR-2022 attracted a total of 3 participating teams, from academia. Eventually, six valid submissions were submitted and then evaluated by the organizers. The competition was held to address the challenge of face recognition in the presence of severe face occlusions. The participants were free to use any training data and the testing data was built by the organisers by synthetically occluding parts of the face images using a well-known dataset. The submitted solutions presented innovations and performed very competitively with the considered baseline. A major output of this competition is a challenging, realistic, and diverse, and publicly available occluded face recognition benchmark with well defined evaluation protocols.

Rayson Laroca, Marcelo Santos, Valter Estevam et al.

Public datasets have played a key role in advancing the state of the art in License Plate Recognition (LPR). Although dataset bias has been recognized as a severe problem in the computer vision community, it has been largely overlooked in the LPR literature. LPR models are usually trained and evaluated separately on each dataset. In this scenario, they have often proven robust in the dataset they were trained in but showed limited performance in unseen ones. Therefore, this work investigates the dataset bias problem in the LPR context. We performed experiments on eight datasets, four collected in Brazil and four in mainland China, and observed that each dataset has a unique, identifiable "signature" since a lightweight classification model predicts the source dataset of a license plate (LP) image with more than 95% accuracy. In our discussion, we draw attention to the fact that most LPR models are probably exploiting such signatures to improve the results achieved in each dataset at the cost of losing generalization capability. These results emphasize the importance of evaluating LPR models in cross-dataset setups, as they provide a better indication of generalization (hence real-world performance) than within-dataset ones.

Rayson Laroca, Valter Estevam, Alceu S. Britto et al.

This work draws attention to the large fraction of near-duplicates in the training and test sets of datasets widely adopted in License Plate Recognition (LPR) research. These duplicates refer to images that, although different, show the same license plate. Our experiments, conducted on the two most popular datasets in the field, show a substantial decrease in recognition rate when six well-known models are trained and tested under fair splits, that is, in the absence of duplicates in the training and test sets. Moreover, in one of the datasets, the ranking of models changed considerably when they were trained and tested under duplicate-free splits. These findings suggest that such duplicates have significantly biased the evaluation and development of deep learning-based models for LPR. The list of near-duplicates we have found and proposals for fair splits are publicly available for further research at https://raysonlaroca.github.io/supp/lpr-train-on-test/

Rayson Laroca, Luiz A. Zanlorensi, Valter Estevam et al.

License Plate Recognition (LPR) plays a critical role in various applications, such as toll collection, parking management, and traffic law enforcement. Although LPR has witnessed significant advancements through the development of deep learning, there has been a noticeable lack of studies exploring the potential improvements in results by fusing the outputs from multiple recognition models. This research aims to fill this gap by investigating the combination of up to 12 different models using straightforward approaches, such as selecting the most confident prediction or employing majority vote-based strategies. Our experiments encompass a wide range of datasets, revealing substantial benefits of fusion approaches in both intra- and cross-dataset setups. Essentially, fusing multiple models reduces considerably the likelihood of obtaining subpar performance on a particular dataset/scenario. We also found that combining models based on their speed is an appealing approach. Specifically, for applications where the recognition task can tolerate some additional time, though not excessively, an effective strategy is to combine 4-6 models. These models may not be the most accurate individually, but their fusion strikes an optimal balance between speed and accuracy.

Diego Rafael Lucio, Luiz A. Zanlorensi, Yandre Maldonado e Gomes da Costa et al.

Accurate extraction of the Region of Interest is critical for successful ocular region-based biometrics. In this direction, we propose a new context-based segmentation approach, entitled Ocular Region Context Network (ORCNet), introducing a specific loss function, i.e., he Punish Context Loss (PC-Loss). The PC-Loss punishes the segmentation losses of a network by using a percentage difference value between the ground truth and the segmented masks. We obtain the percentage difference by taking into account Biederman's semantic relationship concepts, in which we use three contexts (semantic, spatial, and scale) to evaluate the relationships of the objects in an image. Our proposal achieved promising results in the evaluated scenarios: iris, sclera, and ALL (iris + sclera) segmentations, utperforming the literature baseline techniques. The ORCNet with ResNet-152 outperforms the best baseline (EncNet with ResNet-152) on average by 2.27%, 28.26% and 6.43% in terms of F-Score, Error Rate and Intersection Over Union, respectively. We also provide (for research purposes) 3,191 manually labeled masks for the MICHE-I database, as another contribution of our work.

Bernardo Biesseck, Pedro Vidal, Luiz Coelho et al.

A robust face recognition model must be trained using datasets that include a large number of subjects and numerous samples per subject under varying conditions (such as pose, expression, age, noise, and occlusion). Due to ethical and privacy concerns, large-scale real face datasets have been discontinued, such as MS1MV3, and synthetic face generators have been proposed, utilizing GANs and Diffusion Models, such as SYNFace, SFace, DigiFace-1M, IDiff-Face, DCFace, and GANDiffFace, aiming to supply this demand. Some of these methods can produce high-fidelity realistic faces, but with low intra-class variance, while others generate high-variance faces with low identity consistency. In this paper, we propose a Triple Condition Diffusion Model (TCDiff) to improve face style transfer from real to synthetic faces through 2D and 3D facial constraints, enhancing face identity consistency while keeping the necessary high intra-class variance. Face recognition experiments using 1k, 2k, and 5k classes of our new dataset for training outperform state-of-the-art synthetic datasets in real face benchmarks such as LFW, CFP-FP, AgeDB, and BUPT. Our source code is available at: https://github.com/BOVIFOCR/tcdiff.

Furkan Kasım, Terrance E. Boult, Rensso Mora et al.

In the current landscape of biometrics and surveillance, the ability to accurately recognize faces in uncontrolled settings is paramount. The Watchlist Challenge addresses this critical need by focusing on face detection and open-set identification in real-world surveillance scenarios. This paper presents a comprehensive evaluation of participating algorithms, using the enhanced UnConstrained College Students (UCCS) dataset with new evaluation protocols. In total, four participants submitted four face detection and nine open-set face recognition systems. The evaluation demonstrates that while detection capabilities are generally robust, closed-set identification performance varies significantly, with models pre-trained on large-scale datasets showing superior performance. However, open-set scenarios require further improvement, especially at higher true positive identification rates, i.e., lower thresholds.

Lucas Wojcik, Luiz Coelho, Roger Granada et al.

Object Recognition and Document Skew Estimation have come a long way in terms of performance and efficiency. New models follow one of two directions: improving performance using larger models, and improving efficiency using smaller models. However, real-time document detection and rectification is a niche that is largely unexplored by the literature, yet it remains a vital step for automatic information retrieval from visual documents. In this work, we strive towards an efficient document detection pipeline that is satisfactory in terms of Optical Character Recognition (OCR) retrieval and faster than other available solutions. We adapt IWPOD-Net, a license plate detection network, and train it for detection on NBID, a synthetic ID card dataset. We experiment with data augmentation and cross-dataset validation with MIDV (another synthetic ID and passport document dataset) to find the optimal scenario for the model. Other methods from both the Object Recognition and Skew Estimation state-of-the-art are evaluated for comparison with our approach. We use each method to detect and rectify the document, which is then read by an OCR system. The OCR output is then evaluated using a novel OCR quality metric based on the Levenshtein distance. Since the end goal is to improve automatic information retrieval, we use the overall OCR quality as a performance metric. We observe that with a promising model, document rectification does not have to be perfect to attain state-of-the-art performance scores. We show that our model is smaller and more efficient than current state-of-the-art solutions while retaining a competitive OCR quality metric. All code is available at https://github.com/BOVIFOCR/iwpod-doc-corners.git

Valfride Nascimento, Rayson Laroca, Jorge de A. Lambert et al.

Recent years have seen significant developments in the field of License Plate Recognition (LPR) through the integration of deep learning techniques and the increasing availability of training data. Nevertheless, reconstructing license plates (LPs) from low-resolution (LR) surveillance footage remains challenging. To address this issue, we introduce a Single-Image Super-Resolution (SISR) approach that integrates attention and transformer modules to enhance the detection of structural and textural features in LR images. Our approach incorporates sub-pixel convolution layers (also known as PixelShuffle) and a loss function that uses an Optical Character Recognition (OCR) model for feature extraction. We trained the proposed architecture on synthetic images created by applying heavy Gaussian noise to high-resolution LP images from two public datasets, followed by bicubic downsampling. As a result, the generated images have a Structural Similarity Index Measure (SSIM) of less than 0.10. Our results show that our approach for reconstructing these low-resolution synthesized images outperforms existing ones in both quantitative and qualitative measures. Our code is publicly available at https://github.com/valfride/lpr-rsr-ext/

Valter Estevam, Rayson Laroca, Helio Pedrini et al.

We introduce a method to learn unsupervised semantic visual information based on the premise that complex events can be decomposed into simpler events and that these simple events are shared across several complex events. We first employ a clustering method to group representations producing a visual codebook. Then, we learn a dense representation by encoding the co-occurrence probability matrix for the codebook entries. This representation leverages the performance of the dense video captioning task in a scenario with only visual features. For example, we replace the audio signal in the BMT method and produce temporal proposals with comparable performance. Furthermore, we concatenate the visual representation with our descriptor in a vanilla transformer method to achieve state-of-the-art performance in the captioning subtask compared to the methods that explore only visual features, as well as a competitive performance with multi-modal methods. Our code is available at https://github.com/valterlej/dvcusi.

Icaro O. de Oliveira, Rayson Laroca, David Menotti et al.

This work addresses the problem of vehicle identification through non-overlapping cameras. As our main contribution, we introduce a novel dataset for vehicle identification, called Vehicle-Rear, that contains more than three hours of high-resolution videos, with accurate information about the make, model, color and year of nearly 3,000 vehicles, in addition to the position and identification of their license plates. To explore our dataset we design a two-stream CNN that simultaneously uses two of the most distinctive and persistent features available: the vehicle's appearance and its license plate. This is an attempt to tackle a major problem: false alarms caused by vehicles with similar designs or by very close license plate identifiers. In the first network stream, shape similarities are identified by a Siamese CNN that uses a pair of low-resolution vehicle patches recorded by two different cameras. In the second stream, we use a CNN for OCR to extract textual information, confidence scores, and string similarities from a pair of high-resolution license plate patches. Then, features from both streams are merged by a sequence of fully connected layers for decision. In our experiments, we compared the two-stream network against several well-known CNN architectures using single or multiple vehicle features. The architectures, trained models, and dataset are publicly available at https://github.com/icarofua/vehicle-rear.

Hatef Otroshi Shahreza, Christophe Ecabert, Anjith George et al.

Large-scale face recognition datasets are collected by crawling the Internet and without individuals' consent, raising legal, ethical, and privacy concerns. With the recent advances in generative models, recently several works proposed generating synthetic face recognition datasets to mitigate concerns in web-crawled face recognition datasets. This paper presents the summary of the Synthetic Data for Face Recognition (SDFR) Competition held in conjunction with the 18th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2024) and established to investigate the use of synthetic data for training face recognition models. The SDFR competition was split into two tasks, allowing participants to train face recognition systems using new synthetic datasets and/or existing ones. In the first task, the face recognition backbone was fixed and the dataset size was limited, while the second task provided almost complete freedom on the model backbone, the dataset, and the training pipeline. The submitted models were trained on existing and also new synthetic datasets and used clever methods to improve training with synthetic data. The submissions were evaluated and ranked on a diverse set of seven benchmarking datasets. The paper gives an overview of the submitted face recognition models and reports achieved performance compared to baseline models trained on real and synthetic datasets. Furthermore, the evaluation of submissions is extended to bias assessment across different demography groups. Lastly, an outlook on the current state of the research in training face recognition models using synthetic data is presented, and existing problems as well as potential future directions are also discussed.

Ivan DeAndres-Tame, Ruben Tolosana, Pietro Melzi et al.

Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new sub-tasks that allow participants to explore novel face generative methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.

Ivan DeAndres-Tame, Ruben Tolosana, Pietro Melzi et al.

Synthetic data is gaining increasing popularity for face recognition technologies, mainly due to the privacy concerns and challenges associated with obtaining real data, including diverse scenarios, quality, and demographic groups, among others. It also offers some advantages over real data, such as the large amount of data that can be generated or the ability to customize it to adapt to specific problem-solving needs. To effectively use such data, face recognition models should also be specifically designed to exploit synthetic data to its fullest potential. In order to promote the proposal of novel Generative AI methods and synthetic data, and investigate the application of synthetic data to better train face recognition systems, we introduce the 2nd FRCSyn-onGoing challenge, based on the 2nd Face Recognition Challenge in the Era of Synthetic Data (FRCSyn), originally launched at CVPR 2024. This is an ongoing challenge that provides researchers with an accessible platform to benchmark i) the proposal of novel Generative AI methods and synthetic data, and ii) novel face recognition systems that are specifically proposed to take advantage of synthetic data. We focus on exploring the use of synthetic data both individually and in combination with real data to solve current challenges in face recognition such as demographic bias, domain adaptation, and performance constraints in demanding situations, such as age disparities between training and testing, changes in the pose, or occlusions. Very interesting findings are obtained in this second edition, including a direct comparison with the first one, in which synthetic databases were restricted to DCFace and GANDiffFace.

Valfride Nascimento, Gabriel E. Lima, Rafael O. Ribeiro et al.

Recent advancements in super-resolution for License Plate Recognition (LPR) have sought to address challenges posed by low-resolution (LR) and degraded images in surveillance, traffic monitoring, and forensic applications. However, existing studies have relied on private datasets and simplistic degradation models. To address this gap, we introduce UFPR-SR-Plates, a novel dataset containing 10,000 tracks with 100,000 paired low and high-resolution license plate images captured under real-world conditions. We establish a benchmark using multiple sequential LR and high-resolution (HR) images per vehicle -- five of each -- and two state-of-the-art models for super-resolution of license plates. We also investigate three fusion strategies to evaluate how combining predictions from a leading Optical Character Recognition (OCR) model for multiple super-resolved license plates enhances overall performance. Our findings demonstrate that super-resolution significantly boosts LPR performance, with further improvements observed when applying majority vote-based fusion techniques. Specifically, the Layout-Aware and Character-Driven Network (LCDNet) model combined with the Majority Vote by Character Position (MVCP) strategy led to the highest recognition rates, increasing from 1.7% with low-resolution images to 31.1% with super-resolution, and up to 44.7% when combining OCR outputs from five super-resolved images. These findings underscore the critical role of super-resolution and temporal information in enhancing LPR accuracy under real-world, adverse conditions. The proposed dataset is publicly available to support further research and can be accessed at: https://valfride.github.io/nascimento2024toward/

Pedro Vidal, Bernardo Biesseck, Luiz E. L. Coelho et al.

Facial recognition has become a widely used method for authentication and identification, with applications for secure access and locating missing persons. Its success is largely attributed to deep learning, which leverages large datasets and effective loss functions to learn discriminative features. Despite these advances, facial recognition still faces challenges in explainability, demographic bias, privacy, and robustness to aging, pose variations, lighting changes, occlusions, and facial expressions. Privacy regulations have also led to the degradation of several datasets, raising legal, ethical, and privacy concerns. Synthetic facial data generation has been proposed as a promising solution. It mitigates privacy issues, enables experimentation with controlled facial attributes, alleviates demographic bias, and provides supplementary data to improve models trained on real data. This study compares the effectiveness of synthetic facial datasets generated using different techniques in facial recognition tasks. We evaluate accuracy, rank-1, rank-5, and the true positive rate at a false positive rate of 0.01% on eight leading datasets, offering a comparative analysis not extensively explored in the literature. Results demonstrate the ability of synthetic data to capture realistic variations while emphasizing the need for further research to close the performance gap with real data. Techniques such as diffusion models, GANs, and 3D models show substantial progress; however, challenges remain.

Pedro Silva, Guilherme A. L. Silva, Pablo Coelho et al.

Deep Metric Learning (DML) aims to learn embedding functions that map semantically similar inputs to proximate points in a metric space while separating dissimilar ones. Existing methods, such as pairwise losses, are hindered by complex sampling requirements and slow convergence. In contrast, proxy-based losses, despite their improved scalability, often fail to optimize global distribution properties. The Decidability-based Loss (D-Loss) addresses this by targeting the decidability index (d') to enhance distribution separability, but its reliance on large mini-batches imposes significant computational constraints. We introduce Proxy-Decidability Loss (PD-Loss), a novel objective that integrates learnable proxies with the statistical framework of d' to optimize embedding spaces efficiently. By estimating genuine and impostor distributions through proxies, PD-Loss combines the computational efficiency of proxy-based methods with the principled separability of D-Loss, offering a scalable approach to distribution-aware DML. Experiments across various tasks, including fine-grained classification and face verification, demonstrate that PD-Loss achieves performance comparable to that of state-of-the-art methods while introducing a new perspective on embedding optimization, with potential for broader applications.

David Vinicius da Silva, Valter Estevam, David Menotti

The limited amount of labeled data for training the Brazilian Sign Language (Libras) to Portuguese Translation models is a challenging problem due to video collection and annotation costs. This paper proposes generating sign language content by concatenating short clips containing isolated signals for training Sign Language Translation models. We employ the V-LIBRASIL dataset, composed of 4,089 sign videos for 1,364 signs, interpreted by at least three persons, to create hundreds of thousands of sentences with their respective Libras translation, and then, to feed the model. More specifically, we propose several experiments varying the vocabulary size and sentence structure, generating datasets with approximately 170K, 300K, and 500K videos. Our results achieve meaningful scores of 9.2% and 26.2% for BLEU-4 and METEOR, respectively. Our technique enables the creation or extension of existing datasets at a much lower cost than the collection and annotation of thousands of sentences providing clear directions for future works.

Cristiano B. de Oliveira, Joao C. Neves, Rafael O. Ribeiro et al.

The Palácio do Planalto, office of the President of Brazil, was invaded by protesters on January 8, 2023. Surveillance videos taken from inside the building were subsequently released by the Brazilian Supreme Court for public scrutiny. We used segments of such footage to create the UFPR-Planalto801 dataset for people tracking and re-identification in a real-world scenario. This dataset consists of more than 500,000 images. This paper presents a tracking approach targeting this dataset. The method proposed in this paper relies on the use of known state-of-the-art trackers combined in a multilevel hierarchy to correct the ID association over the trajectories. We evaluated our method using IDF1, MOTA, MOTP and HOTA metrics. The results show improvements for every tracker used in the experiments, with IDF1 score increasing by a margin up to 9.5%.

Gabriel Salomon, Rayson Laroca, David Menotti

The replacement of analog meters with smart meters is costly, laborious, and far from complete in developing countries. The Energy Company of Parana (Copel) (Brazil) performs more than 4 million meter readings (almost entirely of non-smart devices) per month, and we estimate that 850 thousand of them are from dial meters. Therefore, an image-based automatic reading system can reduce human errors, create a proof of reading, and enable the customers to perform the reading themselves through a mobile application. We propose novel approaches for Automatic Dial Meter Reading (ADMR) and introduce a new dataset for ADMR in unconstrained scenarios, called UFPR-ADMR-v2. Our best-performing method combines YOLOv4 with a novel regression approach (AngReg), and explores several postprocessing techniques. Compared to previous works, it decreased the Mean Absolute Error (MAE) from 1,343 to 129 and achieved a meter recognition rate (MRR) of 98.90% -- with an error tolerance of 1 Kilowatt-hour (kWh).

Rayson Laroca, Everton V. Cardoso, Diego R. Lucio et al.

Automatic License Plate Recognition (ALPR) systems have shown remarkable performance on license plates (LPs) from multiple regions due to advances in deep learning and the increasing availability of datasets. The evaluation of deep ALPR systems is usually done within each dataset; therefore, it is questionable if such results are a reliable indicator of generalization ability. In this paper, we propose a traditional-split versus leave-one-dataset-out experimental setup to empirically assess the cross-dataset generalization of 12 Optical Character Recognition (OCR) models applied to LP recognition on nine publicly available datasets with a great variety in several aspects (e.g., acquisition settings, image resolution, and LP layouts). We also introduce a public dataset for end-to-end ALPR that is the first to contain images of vehicles with Mercosur LPs and the one with the highest number of motorcycle images. The experimental results shed light on the limitations of the traditional-split protocol for evaluating approaches in the ALPR context, as there are significant drops in performance for most datasets when training and testing the models in a leave-one-dataset-out fashion.

Pedro Silva, Gladston Moreira, Vander Freitas et al.

Nowadays, deep learning is the standard approach for a wide range of problems, including biometrics, such as face recognition and speech recognition, etc. Biometric problems often use deep learning models to extract features from images, also known as embeddings. Moreover, the loss function used during training strongly influences the quality of the generated embeddings. In this work, a loss function based on the decidability index is proposed to improve the quality of embeddings for the verification routine. Our proposal, the D-loss, avoids some Triplet-based loss disadvantages such as the use of hard samples and tricky parameter tuning, which can lead to slow convergence. The proposed approach is compared against the Softmax (cross-entropy), Triplets Soft-Hard, and the Multi Similarity losses in four different benchmarks: MNIST, Fashion-MNIST, CIFAR10 and CASIA-IrisV4. The achieved results show the efficacy of the proposal when compared to other popular metrics in the literature. The D-loss computation, besides being simple, non-parametric and easy to implement, favors both the inter-class and intra-class scenarios.

Luiz A. Zanlorensi, Rayson Laroca, Diego R. Lucio et al.

Recently, ocular biometrics in unconstrained environments using images obtained at visible wavelength have gained the researchers' attention, especially with images captured by mobile devices. Periocular recognition has been demonstrated to be an alternative when the iris trait is not available due to occlusions or low image resolution. However, the periocular trait does not have the high uniqueness presented in the iris trait. Thus, the use of datasets containing many subjects is essential to assess biometric systems' capacity to extract discriminating information from the periocular region. Also, to address the within-class variability caused by lighting and attributes in the periocular region, it is of paramount importance to use datasets with images of the same subject captured in distinct sessions. As the datasets available in the literature do not present all these factors, in this work, we present a new periocular dataset containing samples from 1,122 subjects, acquired in 3 sessions by 196 different mobile devices. The images were captured under unconstrained environments with just a single instruction to the participants: to place their eyes on a region of interest. We also performed an extensive benchmark with several Convolutional Neural Network (CNN) architectures and models that have been employed in state-of-the-art approaches based on Multi-class Classification, Multitask Learning, Pairwise Filters Network, and Siamese Network. The results achieved in the closed- and open-world protocol, considering the identification and verification tasks, show that this area still needs research and development.

Rayson Laroca, Alessander Cidral Boslooper, David Menotti

In this work, we present a robust and efficient solution for counting and identifying train wagons using computer vision and deep learning. The proposed solution is cost-effective and can easily replace solutions based on radiofrequency identification (RFID), which are known to have high installation and maintenance costs. According to our experiments, our two-stage methodology achieves impressive results on real-world scenarios, i.e., 100% accuracy in the counting stage and 99.7% recognition rate in the identification one. Moreover, the system is able to automatically reject some of the train wagons successfully counted, as they have damaged identification codes. The results achieved were surprising considering that the proposed system requires low processing power (i.e., it can run in low-end setups) and that we used a relatively small number of images to train our Convolutional Neural Network (CNN) for character recognition. The proposed method is registered, under number BR512020000808-9, with the National Institute of Industrial Property (Brazil).

Rayson Laroca, Alessandra B. Araujo, Luiz A. Zanlorensi et al.

Existing approaches for image-based Automatic Meter Reading (AMR) have been evaluated on images captured in well-controlled scenarios. However, real-world meter reading presents unconstrained scenarios that are way more challenging due to dirt, various lighting conditions, scale variations, in-plane and out-of-plane rotations, among other factors. In this work, we present an end-to-end approach for AMR focusing on unconstrained scenarios. Our main contribution is the insertion of a new stage in the AMR pipeline, called corner detection and counter classification, which enables the counter region to be rectified -- as well as the rejection of illegible/faulty meters -- prior to the recognition stage. We also introduce a publicly available dataset, called Copel-AMR, that contains 12,500 meter images acquired in the field by the service company's employees themselves, including 2,500 images of faulty meters or cases where the reading is illegible due to occlusions. Experimental evaluation demonstrates that the proposed system, which has three networks operating in a cascaded mode, outperforms all baselines in terms of recognition rate while still being quite efficient. Moreover, as very few reading errors are tolerated in real-world applications, we show that our AMR system achieves impressive recognition rates (i.e., > 99%) when rejecting readings made with lower confidence values.

Gabriela Y. Kimura, Diego R. Lucio, Alceu S. Britto et al.

The iris pattern has significantly improved the biometric recognition field due to its high level of stability and uniqueness. Such physical feature has played an important role in security and other related areas. However, presentation attacks, also known as spoofing techniques, can be used to bypass the biometric system with artifacts such as printed images, artificial eyes, and textured contact lenses. To improve the security of these systems, many liveness detection methods have been proposed, and the first Internacional Iris Liveness Detection competition was launched in 2013 to evaluate their effectiveness. In this paper, we propose a hyperparameter tuning of the CASIA algorithm, submitted by the Chinese Academy of Sciences to the third competition of Iris Liveness Detection, in 2017. The modifications proposed promoted an overall improvement, with an 8.48% Attack Presentation Classification Error Rate (APCER) and 0.18% Bonafide Presentation Classification Error Rate (BPCER) for the evaluation of the combined datasets. Other threshold values were evaluated in an attempt to reduce the trade-off between the APCER and the BPCER on the evaluated datasets and worked out successfully.

Luiz A. Zanlorensi, Hugo Proença, David Menotti

Ocular biometric systems working in unconstrained environments usually face the problem of small within-class compactness caused by the multiple factors that jointly degrade the quality of the obtained data. In this work, we propose an attribute normalization strategy based on deep learning generative frameworks, that reduces the variability of the samples used in pairwise comparisons, without reducing their discriminability. The proposed method can be seen as a preprocessing step that contributes for data regularization and improves the recognition accuracy, being fully agnostic to the recognition strategy used. As proof of concept, we consider the "eyeglasses" and "gaze" factors, comparing the levels of performance of five different recognition methods with/without using the proposed normalization strategy. Also, we introduce a new dataset for unconstrained periocular recognition, composed of images acquired by mobile devices, particularly suited to perceive the impact of "wearing eyeglasses" in recognition effectiveness. Our experiments were performed in two different datasets, and support the usefulness of our attribute normalization scheme to improve the recognition performance.

Luiz A. Zanlorensi, Rayson Laroca, Eduardo Luz et al.

The use of the iris and periocular region as biometric traits has been extensively investigated, mainly due to the singularity of the iris features and the use of the periocular region when the image resolution is not sufficient to extract iris information. In addition to providing information about an individual's identity, features extracted from these traits can also be explored to obtain other information such as the individual's gender, the influence of drug use, the use of contact lenses, spoofing, among others. This work presents a survey of the databases created for ocular recognition, detailing their protocols and how their images were acquired. We also describe and discuss the most popular ocular recognition competitions (contests), highlighting the submitted algorithms that achieved the best results using only iris trait and also fusing iris and periocular region information. Finally, we describe some relevant works applying deep learning techniques to ocular recognition and point out new challenges and future directions. Considering that there are a large number of ocular databases, and each one is usually designed for a specific problem, we believe this survey can provide a broad overview of the challenges in ocular biometrics.

Valter Estevam, Helio Pedrini, David Menotti

Zero-Shot Action Recognition has attracted attention in the last years and many approaches have been proposed for recognition of objects, events and actions in images and videos. There is a demand for methods that can classify instances from classes that are not present in the training of models, especially in the complex problem of automatic video understanding, since collecting, annotating and labeling videos are difficult and laborious tasks. We have identified that there are many methods available in the literature, however, it is difficult to categorize which techniques can be considered state of the art. Despite the existence of some surveys about zero-shot action recognition in still images and experimental protocol, there is no work focused on videos. Therefore, we present a survey of the methods that comprise techniques to perform visual feature extraction and semantic feature extraction as well to learn the mapping between these features considering specifically zero-shot action recognition in videos. We also provide a complete description of datasets, experiments and protocols, presenting open issues and directions for future work, essential for the development of the computer vision research field.

Rayson Laroca, Luiz A. Zanlorensi, Gabriel R. Gonçalves et al.

This paper presents an efficient and layout-independent Automatic License Plate Recognition (ALPR) system based on the state-of-the-art YOLO object detector that contains a unified approach for license plate (LP) detection and layout classification to improve the recognition results using post-processing rules. The system is conceived by evaluating and optimizing different models, aiming at achieving the best speed/accuracy trade-off at each stage. The networks are trained using images from several datasets, with the addition of various data augmentation techniques, so that they are robust under different conditions. The proposed system achieved an average end-to-end recognition rate of 96.9% across eight public datasets (from five different regions) used in the experiments, outperforming both previous works and commercial systems in the ChineseLP, OpenALPR-EU, SSIG-SegPlate and UFPR-ALPR datasets. In the other datasets, the proposed approach achieved competitive results to those attained by the baselines. Our system also achieved impressive frames per second (FPS) rates on a high-end GPU, being able to perform in real time even when there are four vehicles in the scene. An additional contribution is that we manually labeled 38,351 bounding boxes on 6,239 images from public datasets and made the annotations publicly available to the research community.

Rayson Laroca, Victor Barroso, Matheus A. Diniz et al.

In this paper, we tackle Automatic Meter Reading (AMR) by leveraging the high capability of Convolutional Neural Networks (CNNs). We design a two-stage approach that employs the Fast-YOLO object detector for counter detection and evaluates three different CNN-based approaches for counter recognition. In the AMR literature, most datasets are not available to the research community since the images belong to a service company. In this sense, we introduce a new public dataset, called UFPR-AMR dataset, with 2,000 fully and manually annotated images. This dataset is, to the best of our knowledge, three times larger than the largest public dataset found in the literature and contains a well-defined evaluation protocol to assist the development and evaluation of AMR methods. Furthermore, we propose the use of a data augmentation technique to generate a balanced training set with many more examples to train the CNN models for counter recognition. In the proposed dataset, impressive results were obtained and a detailed speed/accuracy trade-off evaluation of each model was performed. In a public dataset, state-of-the-art results were achieved using less than 200 images for training.

Cides S. Bezerra, Rayson Laroca, Diego R. Lucio et al.

The iris can be considered as one of the most important biometric traits due to its high degree of uniqueness. Iris-based biometrics applications depend mainly on the iris segmentation whose suitability is not robust for different environments such as near-infrared (NIR) and visible (VIS) ones. In this paper, two approaches for robust iris segmentation based on Fully Convolutional Networks (FCNs) and Generative Adversarial Networks (GANs) are described. Similar to a common convolutional network, but without the fully connected layers (i.e., the classification layers), an FCN employs at its end a combination of pooling layers from different convolutional layers. Based on the game theory, a GAN is designed as two networks competing with each other to generate the best segmentation. The proposed segmentation networks achieved promising results in all evaluated datasets (i.e., BioSec, CasiaI3, CasiaT4, IITD-1) of NIR images and (NICE.I, CrEye-Iris and MICHE-I) of VIS images in both non-cooperative and cooperative domains, outperforming the baselines techniques which are the best ones found so far in the literature, i.e., a new state of the art for these datasets. Furthermore, we manually labeled 2,431 images from CasiaT4, CrEye-Iris and MICHE-I datasets, making the masks available for research purposes.

Luiz A. Zanlorensi, Eduardo Luz, Rayson Laroca et al.

The use of iris as a biometric trait is widely used because of its high level of distinction and uniqueness. Nowadays, one of the major research challenges relies on the recognition of iris images obtained in visible spectrum under unconstrained environments. In this scenario, the acquired iris are affected by capture distance, rotation, blur, motion blur, low contrast and specular reflection, creating noises that disturb the iris recognition systems. Besides delineating the iris region, usually preprocessing techniques such as normalization and segmentation of noisy iris images are employed to minimize these problems. But these techniques inevitably run into some errors. In this context, we propose the use of deep representations, more specifically, architectures based on VGG and ResNet-50 networks, for dealing with the images using (and not) iris segmentation and normalization. We use transfer learning from the face domain and also propose a specific data augmentation technique for iris images. Our results show that the approach using non-normalized and only circle-delimited iris images reaches a new state of the art in the official protocol of the NICE.II competition, a subset of the UBIRIS database, one of the most challenging databases on unconstrained environments, reporting an average Equal Error Rate (EER) of 13.98% which represents an absolute reduction of about 5%.

Rayson Laroca, Evair Severo, Luiz A. Zanlorensi et al.

Automatic License Plate Recognition (ALPR) has been a frequent topic of research due to many practical applications. However, many of the current solutions are still not robust in real-world situations, commonly depending on many constraints. This paper presents a robust and efficient ALPR system based on the state-of-the-art YOLO object detector. The Convolutional Neural Networks (CNNs) are trained and fine-tuned for each ALPR stage so that they are robust under different conditions (e.g., variations in camera, lighting, and background). Specially for character segmentation and recognition, we design a two-stage approach employing simple data augmentation tricks such as inverted License Plates (LPs) and flipped characters. The resulting ALPR approach achieved impressive results in two datasets. First, in the SSIG dataset, composed of 2,000 frames from 101 vehicle videos, our system achieved a recognition rate of 93.53% and 47 Frames Per Second (FPS), performing better than both Sighthound and OpenALPR commercial systems (89.80% and 93.03%, respectively) and considerably outperforming previous results (81.80%). Second, targeting a more realistic scenario, we introduce a larger public dataset, called UFPR-ALPR dataset, designed to ALPR. This dataset contains 150 videos and 4,500 frames captured when both camera and vehicles are moving and also contains different types of vehicles (cars, motorcycles, buses and trucks). In our proposed dataset, the trial versions of commercial systems achieved recognition rates below 70%. On the other hand, our system performed better, with recognition rate of 78.33% and 35 FPS.

R. F. Prates, G. Cámara-Chávez, William R. Schwartz et al.

Due to the increasingly need for automatic traffic monitoring, vehicle license plate detection is of high interest to perform automatic toll collection, traffic law enforcement, parking lot access control, among others. In this paper, a sliding window approach based on Histogram of Oriented Gradients (HOG) features is used for Brazilian license plate detection. This approach consists in scanning the whole image in a multiscale fashion such that the license plate is located precisely. The main contribution of this work consists in a deep study of the best setup for HOG descriptors on the detection of Brazilian license plates, in which HOG have never been applied before. We also demonstrate the reliability of this method ensured by a recall higher than 98% (with a precision higher than 78%) in a publicly available data set.