TY - GEN
T1 - Integrating spatial and discriminant strength for feature selection and linear dimensionality reduction
AU - Qi, Li
AU - Kambhamettu, Chandra
AU - Jieping, Ye
PY - 2006
Y1 - 2006
N2 - Interest strength assignment to image points is important for selecting good features. Strength assignments using spatial information aim to detect interest points repeatable across different image/illumination transformations, and have been widely adopted in many interest point detectors. Recently, strength assignment schemes using discriminant information received attention, and studies showed the superiority of discriminant strength. In this paper, we introduce a strength assignment scheme integrating spatial and discriminant information, with the motivation that strong spatial information can be helpful in improving the robustness of the discriminant strength estimation, e.g., in under-sampled training scenario. Our integrated strength uses a new discriminant strength assignment, so-called locality oriented Fisher criterion score. The integrated strength leads to new methods for feature selection and weighted linear dimensionality reduction. Experimental results in two case studies (embryo developmental stage classification and face recognition) show the favorable performance of the proposed methods.
AB - Interest strength assignment to image points is important for selecting good features. Strength assignments using spatial information aim to detect interest points repeatable across different image/illumination transformations, and have been widely adopted in many interest point detectors. Recently, strength assignment schemes using discriminant information received attention, and studies showed the superiority of discriminant strength. In this paper, we introduce a strength assignment scheme integrating spatial and discriminant information, with the motivation that strong spatial information can be helpful in improving the robustness of the discriminant strength estimation, e.g., in under-sampled training scenario. Our integrated strength uses a new discriminant strength assignment, so-called locality oriented Fisher criterion score. The integrated strength leads to new methods for feature selection and weighted linear dimensionality reduction. Experimental results in two case studies (embryo developmental stage classification and face recognition) show the favorable performance of the proposed methods.
UR - http://www.scopus.com/inward/record.url?scp=33845522246&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33845522246&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2006.104
DO - 10.1109/CVPRW.2006.104
M3 - Conference contribution
AN - SCOPUS:33845522246
SN - 0769526462
SN - 9780769526461
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
BT - 2006 Conference on Computer Vision and Pattern Recognition Workshop
T2 - 2006 Conference on Computer Vision and Pattern Recognition Workshops
Y2 - 17 June 2006 through 22 June 2006
ER -