Alireza Tavakoli Targhi

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

Accurate and reliable image segmentation is an essential part of biomedical image analysis. In this paper, we consider the problem of biomedical image segmentation using deep convolutional neural networks. We propose a new end-to-end network architecture that effectively integrates local and global contextual patterns of histologic primitives to obtain a more reliable segmentation result. Specifically, we introduce a deep fully convolution residual network with a new skip connection strategy to control the contextual information passed forward. Moreover, our trained model is also computationally inexpensive due to its small number of network parameters. We evaluate our method on two public datasets for epithelium segmentation and tubule segmentation tasks. Our experimental results show that the proposed method provides a fast and effective way of producing a pixel-wise dense prediction of biomedical images.

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.