Mahdi Jampour

TL;DR: This paper has proposed an appearance feature-based approach which process data using Histogram of Oriented Gradients (HOG), a very efficient feature descriptor for handwritten digits which is stable on illumination variation because it is a gradient-based descriptor.

TL;DR: This paper has prepared pseudo random numbers by Lorenz chaotic system for operators of Genetic Algorithm to avoid local convergence and shows that the proposed method is much more efficient in comparison with the traditional Genetic Al algorithm for solving optimization problems.

TL;DR: This work proposes a novel approach to recognizing facial expressions over a large range of head poses, and introduces a non-linear form for the mapping of the features that depends on the pose of the input image.

TL;DR: This work proposes an end-to-end system that relies on a straightforward yet well-designed deep network and very efficient feature extraction, emphasizing feature engineering, and empirically demonstrates that the conjugated network outperforms the original ResNet and can work well for real-world applications in which patches with few letters exist.

TL;DR: A novel data-driven approach for face inpainting that makes use of the observable region of an occluded face as well as its inferred high-level facial attributes, namely gender, ethnicity, and expression, to generate more natural facial appearances.