Sebastian Sudholt and Gernot A. Fink
Proc. 37th German Conference on Pattern Recognition, 2015.
Aachen, Germany
Word spotting is an effective paradigm for indexing document images with minimal human effort. Here, the use of the Bag-of-Features principle has been shown to achieve competitive results on different benchmarks. Recently, a spatial pyramid approach was used as a word image representation to improve the retrieval results even further. The high dimensionality of the spatial pyramids was attempted to be countered by applying Latent Semantic Analysis. However, this leads to increasingly worse results when reducing to lower dimensions. In this paper, we propose a new approach to reducing the dimensionality of word image descriptors which is based on a modified version of the Isomap Manifold Learning algorithm. This approach is able to not only outperform Latent Semantic Analysis but also to reduce a word image descriptor to up to 0.12% of its original size without losing retrieval precision. We evaluate our approach on two different datasets. A preliminary version of the presented approach won the ICDAR 2015 Competition on Keyword Spotting for Handwritten Documents.