Maryam Tahmasbi

Neda Rahimpour Anaraki, Alireza Azadbakht, Maryam Tahmasbi et al.

Recently, there has been a high demand for accelerating and improving the detection of automatic cadastral mapping. As this problem is in its starting point, there are many methods of computer vision and deep learning that have not been considered yet. In this paper, we focus on deep learning and provide three geometric post-processing methods that improve the quality of the work. Our framework includes two parts, each of which consists of a few phases. Our solution to this problem uses instance segmentation. In the first part, we use Mask R-CNN with the backbone of pre-trained ResNet-50 on the ImageNet dataset. In the second phase, we apply three geometric post-processing methods to the output of the first part to get better overall output. Here, we also use computational geometry to introduce a new method for simplifying lines which we call it pocket-based simplification algorithm. For evaluating the quality of our solution, we use popular formulas in this field which are recall, precision and F-score. The highest recall we gain is 95 percent which also maintains high Precision of 72 percent. This resulted in an F-score of 82 percent. Implementing instance segmentation using Mask R-CNN with some geometric post-processes to its output gives us promising results for this field. Also, results show that pocket-based simplification algorithms work better for simplifying lines than Douglas-Puecker algorithm.

Neda Rahimpour Anaraki, Maryam Tahmasbi, Saeed Reza Kheradpisheh

Finding the cadastral boundaries of farmlands is a crucial concern for land administration. Therefore, using deep learning methods to expedite and simplify the extraction of cadastral boundaries from satellite and unmanned aerial vehicle (UAV) images is critical. In this paper, we employ transfer learning to train a U-Net model with a ResNet34 backbone to detect cadastral boundaries through three-class semantic segmentation: "boundary", "field", and "background". We evaluate the performance on two satellite images from farmlands in Iran using "precision", "recall", and "F-score", achieving high values of 88%, 75%, and 81%, respectively, which indicate promising results.

Narges Mirehi, Maryam Tahmasbi

Hand Gesture Recognition (HGR) is of major importance for Human-Computer Interaction (HCI) applications. In this paper, we present a new hand gesture recognition approach called GNG-IEMD. In this approach, first, we use a Growing Neural Gas (GNG) graph to model the image. Then we extract features from this graph. These features are not geometric or pixel-based, so do not depend on scale, rotation, and articulation. The dissimilarity between hand gestures is measured with a novel Improved Earth Mover\textquotesingle s Distance (IEMD) metric. We evaluate the performance of the proposed approach on challenging public datasets including NTU Hand Digits, HKU, HKU multi-angle, and UESTC-ASL and compare the results with state-of-the-art approaches. The experimental results demonstrate the performance of the proposed approach.

Narges Mirehi, Maryam Tahmasbi, Alireza Tavakoli Targhi

Shape recognition is the main challenging problem in computer vision. Different approaches and tools are used to solve this problem. Most existing approaches to object recognition are based on pixels. Pixel-based methods are dependent on the geometry and nature of the pixels, so the destruction of pixels reduces their performance. In this paper, we study the ability of graphs as shape recognition. We construct a graph that captures the topological and geometrical properties of the object. Then, using the coordinate and relation of its vertices, we extract features that are robust to noise, rotation, scale variation, and articulation. To evaluate our method, we provide different comparisons with state-of-the-art results on various known benchmarks, including Kimia's, Tari56, Tetrapod, and Articulated dataset. We provide an analysis of our method against different variations. The results confirm our performance, especially against noise.

Rashidedin Jahandideh, Alireza Tavakoli Targhi, Maryam Tahmasbi

Images taken from the Internet have been used alongside Deep Learning for many different tasks such as: smile detection, ethnicity, hair style, hair colour, gender and age prediction. After witnessing these usages, we were wondering what other attributes can be predicted from facial images available on the Internet. In this paper we tackle the prediction of physical attributes from face images using Convolutional Neural Networks trained on our dataset named FIRW. We crawled around 61, 000 images from the web, then use face detection to crop faces from these real world images. We choose ResNet-50 as our base network architecture. This network was pretrained for the task of face recognition by using the VGG-Face dataset, and we finetune it by using our own dataset to predict physical attributes. Separate networks are trained for the prediction of body type, ethnicity, gender, height and weight; our models achieve the following accuracies for theses tasks, respectively: 84.58%, 87.34%, 97.97%, 70.51%, 63.99%. To validate our choice of ResNet-50 as the base architecture, we also tackle the famous CelebA dataset. Our models achieve an averagy accuracy of 91.19% on CelebA, which is comparable to state-of-the-art approaches.

Amirhossein Dadashzadeh, Alireza Tavakoli Targhi, Maryam Tahmasbi et al.

We propose a two-stage convolutional neural network (CNN) architecture for robust recognition of hand gestures, called HGR-Net, where the first stage performs accurate semantic segmentation to determine hand regions, and the second stage identifies the gesture. The segmentation stage architecture is based on the combination of fully convolutional residual network and atrous spatial pyramid pooling. Although the segmentation sub-network is trained without depth information, it is particularly robust against challenges such as illumination variations and complex backgrounds. The recognition stage deploys a two-stream CNN, which fuses the information from the red-green-blue and segmented images by combining their deep representations in a fully connected layer before classification. Extensive experiments on public datasets show that our architecture achieves almost as good as state-of-the-art performance in segmentation and recognition of static hand gestures, at a fraction of training time, run time, and model size. Our method can operate at an average of 23 ms per frame.