Segmentation-free word spotting with exemplar SVMs

• An unsupervised segmentation-free word spotting method is proposed.
• A sliding window approach is used to locate document regions similar to the query image.
• Exemplar SVM is used to improve the query representation.
• PQ compression allows one to deal with large collections of documents with a minimum loss in accuracy.
• Reranking and query expansion can be applied in word spotting to improve performance.

In this paper we propose an unsupervised segmentation-free method for word spotting in document images. Documents are represented with a grid of HOG descriptors, and a sliding-window approach is used to locate the document regions that are most similar to the query. We use the Exemplar SVM framework to produce a better representation of the query in an unsupervised way. Then, we use a more discriminative representation based on Fisher Vector to rerank the best regions retrieved, and the most promising ones are used to expand the Exemplar SVM training set and improve the query representation. Finally, the document descriptors are precomputed and compressed with Product Quantization. This offers two advantages: first, a large number of documents can be kept in RAM memory at the same time. Second, the sliding window becomes significantly faster since distances between quantized HOG descriptors can be precomputed. Our results significantly outperform other segmentation-free methods in the literature, both in accuracy and in speed and memory usage.