Face detection by facets: combined bottom-up and top-down search using compound templates

New techniques are needed to effectively search the image and feature space of larger and more complex domains. One such technique uses subfeatures and spatial models to represent a compound object, such as a face. From these compound models, hypothesis based search then combines bottom-up and top-down search processes to localize the search within the image and feature space. Detected subfeatures become evidence for facial hypotheses, which then guide local searches for the remaining subfeatures, based upon the expected facial configuration. We describe this compound technique and present a comparison of the compound templates technique with a single template technique in a mug shot style face domain. Attention is paid to performance, including both efficiency and accuracy. The results are complex, and the strengths, weaknesses, and various trade-offs of the two techniques are detailed.