Pattern Spotting and Image Retrieval in Historical Documents using Deep Hashing
This work addresses the challenge of efficiently searching and retrieving patterns in historical document images, which is incremental as it builds on existing deep learning methods with specific optimizations.
This paper tackles the problem of image retrieval and pattern spotting in historical documents by proposing a deep learning approach that uses region proposal and feature extraction with real-valued or binary code representations. The results show it outperforms other deep models by 2.56 percentage points, reduces search time by up to 200x, and cuts storage cost by up to 6,000x compared to related works.
This paper presents a deep learning approach for image retrieval and pattern spotting in digital collections of historical documents. First, a region proposal algorithm detects object candidates in the document page images. Next, deep learning models are used for feature extraction, considering two distinct variants, which provide either real-valued or binary code representations. Finally, candidate images are ranked by computing the feature similarity with a given input query. A robust experimental protocol evaluates the proposed approach considering each representation scheme (real-valued and binary code) on the DocExplore image database. The experimental results show that the proposed deep models compare favorably to the state-of-the-art image retrieval approaches for images of historical documents, outperforming other deep models by 2.56 percentage points using the same techniques for pattern spotting. Besides, the proposed approach also reduces the search time by up to 200x and the storage cost up to 6,000x when compared to related works based on real-valued representations.