- Home
- Archives
- 2026
- Vol. 5 Issue 3
- Article
Secure Face Recognition Using Local Binary Patterns and AES–GCM Authenticated Encryption
Authors
1 Researcher Scholar, Department of Computer Applications, Hindusthan College of Arts & Science, Coimbatore, Tamilnadu, India. 2 Professor, Department of Computer Applications, Hindusthan College of Arts & Science, Coimbatore, Tamilnadu, India. 3 Assistant Professor, Department of Digital Science, Karunya Institute of Technology and Sciences (Deemed University), Coimbatore, Tamilnadu, India.
Article Information
- Published In
- Volume 5, Issue 3 (2026)
- Published Online
- September-December 2026
- Pages
- 932-936
- Article Type
- Original Article
Abstract
View PDFFor the applications of face recognition, not only the accurate identity verification but also the protection of the sensitive facial data are required in this paper, a hybrid model of local binary pattern feature extraction and Advanced Encryption Standard (AES) in Galois/Counter Mode (GCM) mode is proposed for the authenticated image encryption. Images of the face are pre-processed and represented in terms of texture histograms which are compared with enrolled images. The image protection section is used to encrypt the facial image data, and generates an image protection authentication tag for verification of the integrity of the image data during decryption. A prototype application accesses, recognizes, encrypts and recovers images in a single application. The screenshots shown here are intended to illustrate these operations, but are not intended to provide accuracy of recognition or processing speed or tamper resistance. The method provides a guideline for implementation of the fusion of texture-based recognition and real protection of image storage and transmission. During the recognition phase, plaintext representations of faces are used; during the matching phase, the records of facial images are encrypted. For measuring recognition performance, encryption/decryption overhead, and correct rejection of modified records are required to have quantitative testing.
Related Articles
Share Article
*Instagram doesn't support direct link sharing from web. Copy the link and share it in your Instagram story or post.