Segmentation-free word spotting with exemplar SVMs

Jon Almazán, Albert Gordo, Alicia Fornés, Ernest Valveny

Research output: Contribution to journalArticleResearchpeer-review

62 Citations (Scopus)


© 2014 Elsevier Ltd. 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.
Original languageEnglish
Pages (from-to)3967-3978
JournalPattern Recognition
Publication statusPublished - 1 Dec 2014


  • Compression
  • Query expansion
  • Reranking
  • Segmentation-free
  • Unsupervised learning
  • Word spotting


Dive into the research topics of 'Segmentation-free word spotting with exemplar SVMs'. Together they form a unique fingerprint.

Cite this