How far can you get with a modern face recognition test set using only simple features?
- 1 June 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2591-2598
- https://doi.org/10.1109/cvpr.2009.5206605
Abstract
In recent years, large databases of natural images have become increasingly popular in the evaluation of face and object recognition algorithms. However, Pinto et al. previously illustrated an inherent danger in using such sets, showing that an extremely basic recognition system, built on a trivial feature set, was able to take advantage of low-level regularities in popular object and face recognition sets, performing on par with many state-of-the-art systems. Recently, several groups have raised the performance “bar” for these sets, using more advanced classification tools. However, it is difficult to know whether these improvements are due to progress towards solving the core computational problem, or are due to further improvements in the exploitation of low-level regularities. Here, we show that even modest optimization of the simple model introduced by Pinto et al. using modern multiple kernel learning (MKL) techniques once again yields “state-of-the-art” performance levels on a standard face recognition set (“labeled faces in the wild”). However, at the same time, even with the inclusion of MKL techniques, systems based on these simple features still fail on a synthetic face recognition test that includes more “realistic” view variation by design. These results underscore the importance of building test sets focussed on capturing the central computational challenges of real-world face recognition.Keywords
This publication has 12 references indexed in Scilit:
- Evaluation of Face Datasets as Tools for Assessing the Performance of Face Recognition MethodsInternational Journal of Computer Vision, 2008
- Why is Real-World Visual Object Recognition Hard?PLoS Computational Biology, 2008
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- More efficiency in multiple kernel learningPublished by Association for Computing Machinery (ACM) ,2007
- Learning Visual Similarity Measures for Comparing Never Seen ObjectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- PeekaboomPublished by Association for Computing Machinery (ACM) ,2006
- Dataset Issues in Object RecognitionLecture Notes in Computer Science, 2006
- Learning methods for generic object recognition with invariance to pose and lightingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Multiple kernel learning, conic duality, and the SMO algorithmPublished by Association for Computing Machinery (ACM) ,2004
- The CMU pose, illumination, and expression databaseIeee Transactions On Pattern Analysis and Machine Intelligence, 2003