Browsing Heterogeneous Document Collections by a Segmentation-Free Word Spotting Method

—In this paper, we present a segmentation-free word spotting method that is able to deal with heterogeneous document image collections. We propose a patch-based framework where patches are represented by a bag-of-visual-words model powered by SIFT descriptors. A later refinement of the feature vectors is performed by applying the latent semantic indexing technique. The proposed method performs well on both handwritten and typewritten historical document images. We have also tested our method on documents written in nonLatin scripts. Keywords-Word Spotting, Heterogeneous Document Collections, Dense SIFT Features, Latent Semantic Indexing.

• Type: Journal
• Year: 2011
• Where: ICDAR
• Authors: Marçal Rusiñol, David Aldavert, Ricardo Toledo, Josep Lladós
• Keywords: Document Analysis, Document Collections, Feature Vectors, ICDAR 2011, Image Collections