On identification from periocular region utilizing SIFT and SURF. Karahan, Ş., Karaöz, A., Özdemir, Ö. F., Gü, A. G., & Uludag, U. In 2014 22nd European Signal Processing Conference (EUSIPCO), pages 1392-1396, Sep., 2014.
Paper abstract bibtex We concentrate on utilization of facial periocular region for biometric identification. Although this region has superior discriminative characteristics, as compared to mouth and nose, it has not been frequently used as an independent modality for personal identification. We employ a feature-based representation, where the associated periocular image is divided into left and right sides, and descriptor vectors are extracted from these using popular feature extraction algorithms SIFT, SURF, BRISK, ORB, and LBP. We also concatenate descriptor vectors. Utilizing FLANN and Brute Force matchers, we report recognition rates and ROC. For the periocular region image data, obtained from widely used FERET database consisting of 865 subjects, we obtain Rank-1 recognition rate of 96.8% for full frontal and different facial expressions in same session cases. We include a summary of existing methods, and show that the proposed method produces lower/comparable error rates with respect to the current state of the art.
@InProceedings{6952498,
author = {Ş. Karahan and A. Karaöz and Ö. F. Özdemir and A. G. Gü and U. Uludag},
booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},
title = {On identification from periocular region utilizing SIFT and SURF},
year = {2014},
pages = {1392-1396},
abstract = {We concentrate on utilization of facial periocular region for biometric identification. Although this region has superior discriminative characteristics, as compared to mouth and nose, it has not been frequently used as an independent modality for personal identification. We employ a feature-based representation, where the associated periocular image is divided into left and right sides, and descriptor vectors are extracted from these using popular feature extraction algorithms SIFT, SURF, BRISK, ORB, and LBP. We also concatenate descriptor vectors. Utilizing FLANN and Brute Force matchers, we report recognition rates and ROC. For the periocular region image data, obtained from widely used FERET database consisting of 865 subjects, we obtain Rank-1 recognition rate of 96.8% for full frontal and different facial expressions in same session cases. We include a summary of existing methods, and show that the proposed method produces lower/comparable error rates with respect to the current state of the art.},
keywords = {biometrics (access control);face recognition;feature extraction;periocular region;SIFT;SURF;biometric identification;personal identification;feature based representation;associated periocular image;descriptor vectors;feature extraction;BRISK;ORB;LBP;Feature extraction;Vectors;Databases;Face;Detectors;Computer vision;Face recognition;Face;Periocular Region;SIFT;SURF;BRISK;ORB;LBP;FLANN;Brute-Force Matcher;FERET;Identification},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569925709.pdf},
}
Downloads: 0
{"_id":"zAaG8HkaxGatQ4nJF","bibbaseid":"karahan-karaz-zdemir-g-uludag-onidentificationfromperiocularregionutilizingsiftandsurf-2014","authorIDs":[],"author_short":["Karahan, Ş.","Karaöz, A.","Özdemir, Ö. F.","Gü, A. G.","Uludag, U."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Ş."],"propositions":[],"lastnames":["Karahan"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Karaöz"],"suffixes":[]},{"firstnames":["Ö.","F."],"propositions":[],"lastnames":["Özdemir"],"suffixes":[]},{"firstnames":["A.","G."],"propositions":[],"lastnames":["Gü"],"suffixes":[]},{"firstnames":["U."],"propositions":[],"lastnames":["Uludag"],"suffixes":[]}],"booktitle":"2014 22nd European Signal Processing Conference (EUSIPCO)","title":"On identification from periocular region utilizing SIFT and SURF","year":"2014","pages":"1392-1396","abstract":"We concentrate on utilization of facial periocular region for biometric identification. Although this region has superior discriminative characteristics, as compared to mouth and nose, it has not been frequently used as an independent modality for personal identification. We employ a feature-based representation, where the associated periocular image is divided into left and right sides, and descriptor vectors are extracted from these using popular feature extraction algorithms SIFT, SURF, BRISK, ORB, and LBP. We also concatenate descriptor vectors. Utilizing FLANN and Brute Force matchers, we report recognition rates and ROC. For the periocular region image data, obtained from widely used FERET database consisting of 865 subjects, we obtain Rank-1 recognition rate of 96.8% for full frontal and different facial expressions in same session cases. We include a summary of existing methods, and show that the proposed method produces lower/comparable error rates with respect to the current state of the art.","keywords":"biometrics (access control);face recognition;feature extraction;periocular region;SIFT;SURF;biometric identification;personal identification;feature based representation;associated periocular image;descriptor vectors;feature extraction;BRISK;ORB;LBP;Feature extraction;Vectors;Databases;Face;Detectors;Computer vision;Face recognition;Face;Periocular Region;SIFT;SURF;BRISK;ORB;LBP;FLANN;Brute-Force Matcher;FERET;Identification","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569925709.pdf","bibtex":"@InProceedings{6952498,\n author = {Ş. Karahan and A. Karaöz and Ö. F. Özdemir and A. G. Gü and U. Uludag},\n booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},\n title = {On identification from periocular region utilizing SIFT and SURF},\n year = {2014},\n pages = {1392-1396},\n abstract = {We concentrate on utilization of facial periocular region for biometric identification. Although this region has superior discriminative characteristics, as compared to mouth and nose, it has not been frequently used as an independent modality for personal identification. We employ a feature-based representation, where the associated periocular image is divided into left and right sides, and descriptor vectors are extracted from these using popular feature extraction algorithms SIFT, SURF, BRISK, ORB, and LBP. We also concatenate descriptor vectors. Utilizing FLANN and Brute Force matchers, we report recognition rates and ROC. For the periocular region image data, obtained from widely used FERET database consisting of 865 subjects, we obtain Rank-1 recognition rate of 96.8% for full frontal and different facial expressions in same session cases. We include a summary of existing methods, and show that the proposed method produces lower/comparable error rates with respect to the current state of the art.},\n keywords = {biometrics (access control);face recognition;feature extraction;periocular region;SIFT;SURF;biometric identification;personal identification;feature based representation;associated periocular image;descriptor vectors;feature extraction;BRISK;ORB;LBP;Feature extraction;Vectors;Databases;Face;Detectors;Computer vision;Face recognition;Face;Periocular Region;SIFT;SURF;BRISK;ORB;LBP;FLANN;Brute-Force Matcher;FERET;Identification},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569925709.pdf},\n}\n\n","author_short":["Karahan, Ş.","Karaöz, A.","Özdemir, Ö. F.","Gü, A. G.","Uludag, U."],"key":"6952498","id":"6952498","bibbaseid":"karahan-karaz-zdemir-g-uludag-onidentificationfromperiocularregionutilizingsiftandsurf-2014","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569925709.pdf"},"keyword":["biometrics (access control);face recognition;feature extraction;periocular region;SIFT;SURF;biometric identification;personal identification;feature based representation;associated periocular image;descriptor vectors;feature extraction;BRISK;ORB;LBP;Feature extraction;Vectors;Databases;Face;Detectors;Computer vision;Face recognition;Face;Periocular Region;SIFT;SURF;BRISK;ORB;LBP;FLANN;Brute-Force Matcher;FERET;Identification"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2014url.bib","creationDate":"2021-02-13T17:43:41.689Z","downloads":0,"keywords":["biometrics (access control);face recognition;feature extraction;periocular region;sift;surf;biometric identification;personal identification;feature based representation;associated periocular image;descriptor vectors;feature extraction;brisk;orb;lbp;feature extraction;vectors;databases;face;detectors;computer vision;face recognition;face;periocular region;sift;surf;brisk;orb;lbp;flann;brute-force matcher;feret;identification"],"search_terms":["identification","periocular","region","utilizing","sift","surf","karahan","karaöz","özdemir","gü","uludag"],"title":"On identification from periocular region utilizing SIFT and SURF","year":2014,"dataSources":["A2ezyFL6GG6na7bbs","oZFG3eQZPXnykPgnE"]}