A Novel Statistical Feature Analysis-Based Global and LocalMethod for Face Recognition
Face recognition from an image/video has been a fast-growing area in research community, and a sizeable number of facerecognition techniques based on texture analysis have been developed in the past few years. Further, these techniques work well ongray-scale and colored images, but very few techniqu...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi
2020
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/30749/7/A%20Novel%20Statistical%20Feature%20Analysis.pdf http://umpir.ump.edu.my/id/eprint/30749/ https://doi.org/10.1155/2020/4967034 https://doi.org/10.1155/2020/4967034 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Face recognition from an image/video has been a fast-growing area in research community, and a sizeable number of facerecognition techniques based on texture analysis have been developed in the past few years. Further, these techniques work well ongray-scale and colored images, but very few techniques deal with binary and low-resolution images. As the binary image isbecoming the preferred format for low face resolution analysis, there is a need for further studies to provide a complete solutionfor the image-based face recognition system with a higher accuracy rate. To overcome the limitation of the existing methods inextracting distinctive features in low-resolution images due to the contrast between the face and background, we propose astatistical feature analysis technique to fill the gaps. To achieve this, the proposed technique integrates the binary-level occurrencematrix (BLCM) and the fuzzy local binary pattern (FLBP) named FBLCM to extract global and local features of the face frombinary and low-resolution images. *e purpose of FBLCM is to distinctively improve performance of edge sharpness betweenblack and white pixels in the binary image and to extract significant data relating to the features of the face pattern. Experimentalresults on Yale and FEI datasets validate the superiority of the proposed technique over the other top-performing feature analysismethods. *e developed technique has achieved the accuracy of 94.54% when a random forest classifier is used, hence out-performing other techniques such as the gray-level co-occurrence matrix (GLCM), bag of word (BOW), and fuzzy local binarypattern (FLBP), respectively |
|---|