M
Mahdi Jampour
Researcher at Graz University of Technology
Publications - 32
Citations - 358
Mahdi Jampour is an academic researcher from Graz University of Technology. The author has contributed to research in topics: Computer science & Fractal. The author has an hindex of 9, co-authored 28 publications receiving 247 citations. Previous affiliations of Mahdi Jampour include Shahid Bahonar University of Kerman & Islamic Azad University.
Papers
More filters
Journal ArticleDOI
Efficient Handwritten Digit Recognition based on Histogram of Oriented Gradients and SVM
Reza Ebrahimzadeh,Mahdi Jampour +1 more
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.
Journal ArticleDOI
Chaotic Genetic Algorithm based on Lorenz Chaotic System for Optimization Problems
Reza Ebrahimzadeh,Mahdi Jampour +1 more
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.
Journal ArticleDOI
Pose-specific non-linear mappings in feature space towards multiview facial expression recognition
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.
Journal ArticleDOI
A deep learning framework for text-independent writer identification
Malihe Javidi,Mahdi Jampour +1 more
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.
Journal ArticleDOI
Face inpainting based on high-level facial attributes
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.