Face verification with balanced thresholds
Publication in refereed journal

香港中文大學研究人員

引用次數
替代計量分析
.

其它資訊
摘要The process of face verification is guided by a prelearned global threshold, which, however, is often inconsistent with class-specific optimal thresholds. It is, hence, beneficial to pursue a balance of the class-specific thresholds in the model-learning stage. In this paper, we present a new dimensionality reduction algorithm tailored to the verification task that ensures threshold balance. This is achieved by the following aspects. First, feasibility is guaranteed by employing an affine transformation matrix, instead of the conventional projection matrix, for dimensionality reduction, and, hence, we call the proposed algorithm threshold balanced transformation (TBT). Then, the affine transformation matrix, constrained as the product of an orthogonal matrix and a diagonal matrix, is optimized to improve the threshold balance and classification capability in an iterative manner. Unlike most algorithms for face verification which are directly transplanted from face identification literature, TBT is specifically designed for face verification and clarifies the intrinsic distinction between these two tasks. Experiments on three benchmark face databases demonstrate that TBT significantly outperforms the state-of-the-art subspace techniques for face verification.
著者Yan SC, Xu D, Tang XO
期刊名稱IEEE Transactions on Image Processing
出版年份2007
月份1
日期1
卷號16
期次1
出版社IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
頁次262 - 268
國際標準期刊號1057-7149
電子國際標準期刊號1941-0042
語言英式英語
關鍵詞dimensionality reduction; face verification; subspace learning; threshold balance
Web of Science 學科類別Computer Science; Computer Science, Artificial Intelligence; COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE; Engineering; Engineering, Electrical & Electronic; ENGINEERING, ELECTRICAL & ELECTRONIC

上次更新時間 2020-20-09 於 00:54