Mokhtar Smahi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mokhtar Smahi has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Mourad Chaa
University of Kasdi Merbah, ELEC Laboratory, Faculty of New Information and Communication Technologies, Ouargla, Algeria
1 shared publication Salim Chitroub
University of Sciences and Technology of “Houari Boumediene”, LISIC Laboratory, Faculty of Electrical Engineering, Algiers, Algeria
1 shared publication
Latest Publications
- 1 July 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 34 (04) , 043005-17
Enhanced finger-knuckle identification using discriminative color subspace segmentation and binarized statistical image feature extraction
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.
- 1 July 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 34 (04) , 043005-17
Enhanced finger-knuckle identification using discriminative color subspace segmentation and binarized statistical image feature extraction
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.