A5014594854- Face and Expression Recognition
- Image Retrieval and Classification Techniques
- Face recognition and analysis
- Advanced Image and Video Retrieval Techniques
- Chaos-based Image/Signal Encryption
- Video Surveillance and Tracking Methods
- Cryptographic Implementations and Security
- Advanced Steganography and Watermarking Techniques
- Remote Sensing and Land Use
Sidi Mohamed Ben Abdellah University
2019-2024
This paper proposes the use of strings as a new local descriptor for face recognition. The image is first divided into nonoverlapping subregions from which (words) are extracted using principle chain code algorithm and assigned nearest words in dictionary visual (DoVW) with Levenshtein distance (LD) by applying bag (BoVW) paradigm. As result, each region represented histogram words. histograms then assembled descriptor. Our methodology depends on path pursued starting pixel do not require...
This paper proposes a novel approach to face recognition using freeman chain code as feature extractor for representation, and the nearest neighbor classifier matching. The description stage starts with resizing, then dividing image into non-overlapping sub-regions, set of chains (words) are extracted from each region, assigned later word in Dictionary Visual Words (DoVW). As result, patch is represented by histogram visual words. Finally, histograms assembled one describe image. Unlike most...
This paper proposes a novel approach to face recognition using string of minimum values (SMV) as new feature extractor for representation. Unlike most the representative methods, which focus only on micro-structures information in image analysis, by surrounding treated pixel with mask. The proposed descriptor uses chains unit vectors four directions, moving from current next one, pixel, and so on, order encode also global appearance image. Furthermore, seven distance metrics nearest...