Leonardo João

I. B. Barcelos, F. de C. Belém, L. de M. João et al.

Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications since it allows for reducing the workload, removing redundant information, and preserving regions with meaningful features. Due to the rapid progress in this area, the literature fails to catch up on more recent works among the compared ones and to categorize the methods according to all existing strategies. This work fills this gap by presenting a comprehensive review with new taxonomy for superpixel segmentation, in which methods are classified according to their processing steps and processing levels of image features. We revisit the recent and popular literature according to our taxonomy and evaluate 20 strategies based on nine criteria: connectivity, compactness, delineation, control over the number of superpixels, color homogeneity, robustness, running time, stability, and visual quality. Our experiments show the trends of each approach in pixel clustering and discuss individual trade-offs. Finally, we provide a new benchmark for superpixel assessment, available at https://github.com/IMScience-PPGINF-PucMinas/superpixel-benchmark.

Leonardo de Melo Joao, Azael de Melo e Sousa, Bianca Martins dos Santos et al.

State-of-the-art (SOTA) object detection methods have succeeded in several applications at the price of relying on heavyweight neural networks, which makes them inefficient and inviable for many applications with computational resource constraints. This work presents a method to build a Convolutional Neural Network (CNN) layer by layer for object detection from user-drawn markers on discriminative regions of representative images. We address the detection of Schistosomiasis mansoni eggs in microscopy images of fecal samples, and the detection of ships in satellite images as application examples. We could create a flyweight CNN without backpropagation from very few input images. Our method explores a recent methodology, Feature Learning from Image Markers (FLIM), to build convolutional feature extractors (encoders) from marker pixels. We extend FLIM to include a single-layer adaptive decoder, whose weights vary with the input image -- a concept never explored in CNNs. Our CNN weighs thousands of times less than SOTA object detectors, being suitable for CPU execution and showing superior or equivalent performance to three methods in five measures.

Leonardo M. Joao, Jancarlo F. Gomes, Silvio J. F. Guimaraes et al.

Salient Object Detection (SOD) with deep learning often requires substantial computational resources and large annotated datasets, making it impractical for resource-constrained applications. Lightweight models address computational demands but typically strive in complex and scarce labeled-data scenarios. Feature Learning from Image Markers (FLIM) learns an encoder's convolutional kernels among image patches extracted from discriminative regions marked on a few representative images, dismissing large annotated datasets, pretraining, and backpropagation. Such a methodology exploits information redundancy commonly found in biomedical image applications. This study presents methods to learn dilated-separable convolutional kernels and multi-dilation layers without backpropagation for FLIM networks. It also proposes a novel network simplification method to reduce kernel redundancy and encoder size. By combining a FLIM encoder with an adaptive decoder, a concept recently introduced to estimate a pointwise convolution per image, this study presents very efficient (named flyweight) SOD models for biomedical images. Experimental results in challenging datasets demonstrate superior efficiency and effectiveness to lightweight models. By requiring significantly fewer parameters and floating-point operations, the results show competitive effectiveness to heavyweight models. These advances highlight the potential of FLIM networks for data-limited and resource-constrained applications with information redundancy.

Leonardo de Melo Joao, Alexandre Xavier Falcao

Saliency Object Detection (SOD) has several applications in image analysis. The methods have evolved from image-intrinsic to object-inspired (deep-learning-based) models. When a model fail, however, there is no alternative to enhance its saliency map. We fill this gap by introducing a hybrid approach, named \textit{Iterative Saliency Enhancement over Superpixel Similarity} (ISESS), that iteratively generates enhanced saliency maps by executing two operations alternately: object-based superpixel segmentation and superpixel-based saliency estimation -- cycling operations never exploited. ISESS estimates seeds for superpixel delineation from a given saliency map and defines superpixel queries in the foreground and background. A new saliency map results from color similarities between queries and superpixels at each iteration. The process repeats and, after a given number of iterations, the generated saliency maps are combined into one by cellular automata. Finally, the resulting map is merged with the initial one by the maximum bewteen their average values per superpixel. We demonstrate that our hybrid model can consistently outperform three state-of-the-art deep-learning-based methods on five image datasets.

Leonardo de Melo Joao, Felipe de Castro Belem, Alexandre Xavier Falcao

Saliency object detection estimates the objects that most stand out in an image. The available unsupervised saliency estimators rely on a pre-determined set of assumptions of how humans perceive saliency to create discriminating features. By fixing the pre-selected assumptions as an integral part of their models, these methods cannot be easily extended for specific settings and different image domains. We then propose a superpixel-based ITerative Saliency Estimation fLexible Framework (ITSELF) that allows any user-defined assumptions to be added to the model when required. Thanks to recent advancements in superpixel segmentation algorithms, saliency-maps can be used to improve superpixel delineation. By combining a saliency-based superpixel algorithm to a superpixel-based saliency estimator, we propose a novel saliency/superpixel self-improving loop to iteratively enhance saliency maps. We compare ITSELF to two state-of-the-art saliency estimators on five metrics and six datasets, four of which are composed of natural-images, and two of biomedical-images. Experiments show that our approach is more robust than the compared methods, presenting competitive results on natural-image datasets and outperforming them on biomedical-image datasets.