BROWSE
Detail
Conference Paper
An Expression-Invariant Facial Image Retrieval using SIFT and GLBP
Cited - time in 
Share 
Share
- Authors
- Sohee Park, Geonwoo Kim
- Issue Date
- 2017-12
- Citation
- International Conference on Computer Science and its Applications (CSA) 2017, pp.1-6
- Language
- English
- Type
- Conference Paper
- Abstract
- This paper presents an expression-invariant face search method for the real environment. This method is based on Scale Invariant Feature Transform (SIFT) matching and Gabor – Local Binary Pattern (GLBP) histogram for simple and non-statistical approach. We already presented the performance of SIFT and GLBP based face search with partial occlusion. The main characteristic of this approach is to measure the similarity between two images using SIFT. In this paper, we presents the performance of our approach in the expression-invariant face search as well as occluded face images. For demonstration the superiority of our approach, we used the famous benchmark database with expressional face images. The results show that our approach achieves better performance compared to GLBP search algorithm on AR face database.
- KSP Keywords
- AR face database, Face image, Facial image, Image retrieval, Occluded Face, Partial Occlusion, Real environment, Search Algorithm(GSA), local binary pattern(LBP), measure the similarity, scale invariant feature transform(SIFT)