Supervised Mid-Level Features for Word Image Representation

This paper addresses the problem of learning word im-age representations: given the cropped image of a word, we are interested in finding a descriptive, robust, and compact fixed-length representation. Machine learning techniques can then be supplied with these representations to produce models useful for word retrieval or recognition tasks. Al-though many works have focused on the machine learning aspect once a global representation has been produced, lit-tle work has been devoted to the construction of those base image representations: most works use standard coding and aggregation techniques directly on top of standard com-puter vision features such as SIFT or HOG. We propose to learn local mid-level features suitable for building word image representations. These features are learnt by leveraging character bounding box annotations on a small set of training images. However, contrary to other approaches that use character bounding box infor-mation, our approach does not rely on detecting the indi-vidual characters explicitly at testing time. Our local mid-level features can then be aggregated to produce a global word image signature. When pairing these features with the recent word attributes framework of [4], we obtain re-sults comparable with or better than the state-of-the-art on matching and recognition tasks using global descriptors of only 96 dimensions. 1