Abstract | ||
---|---|---|
We present two novel methods for face verification. Our first method - "attribute" classifiers - uses binary classi- fiers trained to recognize the presence or absence of de- scribable aspects of visual appearance (e.g., gender, race, and age). Our second method - "simile" classifiers - re- moves the manual labeling required for attribute classifica- tion and instead learns the similarity of faces, or regions of faces, to specific reference people. Neither method re- quires costly, often brittle, alignment between image pairs; yet, both methods produce compact visual descriptions, and work on real-world images. Furthermore, both the attribute and simile classifiers improve on the current state-of-the-art for the LFW data set, reducing the error rates compared to the current best by 23:92% and 26:34%, respectively, and 31:68% when combined. For further testing across pose, illumination, and expression, we introduce a new data set - termed PubFig - of real-world images of public figures (celebrities and politicians) acquired from the internet. This data set is both larger (60,000 images) and deeper (300 images per individual) than existing data sets of its kind. Finally, we present an evaluation of human performance. Figure 1: Attribute Classifiers: An attribute classifier can be trained to recognize the presence or absence of a describable as- pect of visual appearance. The responses for several such attribute classifiers are shown for a pair of images of Halle Berry. Note that the "flash" and "shiny skin" attributes produce very differ- ent responses, while the responses for the remaining attributes are in strong agreement despite the changes in pose, illumination, ex- pression, and image quality. We use these attributes for face verifi- cation, achieving a 23:92% drop in error rates on the LFW bench- mark compared to the existing state-of-the-art. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICCV.2009.5459250 | Kyoto |
Keywords | DocType | Volume |
face recognition,pattern classification,Internet,LFW data set,attribute classifier method,face verification,simile classifier method | Conference | 2009 |
Issue | ISSN | ISBN |
1 | 1550-5499 E-ISBN : 978-1-4244-4419-9 | 978-1-4244-4419-9 |
Citations | PageRank | References |
637 | 35.99 | 25 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Neeraj Kumar | 1 | 1623 | 74.67 |
Alexander C. Berg | 2 | 10554 | 630.24 |
Peter N. Belhumeur | 3 | 824 | 103.39 |
Shree K. Nayar | 4 | 12394 | 1538.46 |