Recognizing faces with single sample per subject using fusion of transforms
Journal Title: International Journal on Computer Science and Engineering - Year 2016, Vol 8, Issue 7
Abstract
Face recognition has attracted attention of the researchers. Face recognition becomes challenging if various factors are considered such as varying illumination, pose, facial expression and somewhat occlusion. The face recognition becomes more challenging if the single sample per person is available. In this paper a fusion of method is proposed to deal with single sample per person. Gabor transform is good for eliminating the orientation differences. An efficient ridgelet transform is proposed which effectively collects the meaningful rotational features. The results obtained from these two transforms are combined to classify the face image using support vector machine and distance based classifier. Experiments on FEI, JAFFE, ORL, UMIST, MUCT face datasets shows that the proposed method improves the performance in the scenario of one training sample per person.
Authors and Affiliations
Sujata G. Bhele , Vijay H. Mankar
Keywords
Related Articles
- EP ID EP128487
- DOI -
- Views 117
- Downloads 0
Performance of SIFT based Video Retrieval
Video has become an important element of multimedia computing and communication environments, with applications as varied as broadcasting, education, publishing and military intelligence. In Video Retrieval system, each...
Job-Oriented Monitoring of Clusters
There has been a lot of development in the field of clusters and grids. Recently, the use of clusters has been on rise in every possible field. This paper proposes a system that monitors jobs on large computational clust...
Task Scheduling Algorithm to Reduce the Number of Processors using Merge Conditions
Some task scheduling algorithms generate the shortest schedule, when its input DAG satisfies a specified condition. Among those scheduling algorithms, TDS algorithm proposed a DAG condition where allocation of two parent...
Reclaiming Individuality of Mysterious Passage
Authorship attribution, the science of inferring characteristics of author from characteristics of documents written by that author become an urgent need to find the original author of anonymous text. In this paper, a no...
RGB & GRAY SCALE COMPONENT ON MPQ-BTC IN IMAGE COMPRESSION
Block Truncation Coding (BTC) is novel digital technique in image processing using which images can be coded efficiently. BTC has played an important role in the sense that many coding techniques have been developed base...