Mourad Chaa

Mr. Mourad Chaa


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 March 2019 in IET Image Processing
Verified
Journal Article
Open access
PDF file
MCMourad Chaa
Mourad Chaa
ZAZahid Akhtar
Zahid Akhtar
AAAbdelouahab ATTIA
Abdelouahab ATTIA
Since past decade, efforts are afoot to design better hand‐based automatic person recognition systems. Among the various hand‐based biometric traits, palmprint as a biometric characteristic is now gaining increased attention from both the academic and industrial communities owing to its highly distinctive texture patterns, features richness, and stability. Here, the authors propose a new 3D palmprint recognition framework based on an unsupervised convolutional deep learning network named PCANet. Specifically, the proposed framework first reconstructs illumination‐invariant 3D palmprint images using Single Scale Retinex (SSR) algorithm. Then, PCANet topology is employed to extract discriminative features from SSR images. Finally, a multi‐class support vector machine (SVM) classification scheme is utilised to determine the identity of the person. Extensive experimental analysis on publicly available 3D palmprint PolyU dataset, which is composed of 8000 range images from 200 individuals, shows that proposed method outperforms existing approaches and is also able to attain 99.98% rank‐1 accuracy.

4 February 2022 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
MCMourad Chaa
Mourad Chaa
ZAZahid Akhtar
Zahid Akhtar
ALAbdehai Lati
Abdehai Lati

1 July 2025 in Journal of Electronic Imaging
Verified
Journal Article
Closed access
PDF file
Mokhtar SMAHI‎Mokhtar SMAHI‎
Mokhtar SMAHI‎
SCSalim Chitroub
Salim Chitroub
MCMourad Chaa
Mourad Chaa
For many years, finger knuckle print (FKP) has received many interests in the realm of person recognition. Likewise, extracting color specter features has a rapid rise, improving the performance of some other modalities. In this context, our study investigates the application of color specter segmentation to enhance the performance of the FKP modality as well. Initially, the reprocessed images are segmented into their red, green, and blue; gray; and hue, saturation, and value components. After that, we use the binarized statistical image feature technique to extract features in the form of histograms and concatenate them into a single histogram per image using the weighted concatenation method. Principal component analysis and linear discriminant analysis algorithms are employed to reduce the dimension of this huge histogram. Finally, the nearest neighbor classifier is utilized in the matching step to make the appropriate decision. The Poly-U database is used to do experiments in both unimodal (dorsal FKP) and multimodal (dorsal, major, and minor) systems. Obtained results in terms of identification and verification justify outperforming the FKP color space segmentation and pave the way for future testing of other color specters.