LDA-Based Word Image Representation for Keyword Spotting on Historical Mongolian Documents

摘要

The original Bag-of-Visual-Words approach discards the spatial relations of the visual words. In this paper, a LDA-based topic model is adopted to obtain the semantic relations of visual words for each word image. Because the LDA-based topic model usually hurts retrieval performance when directly employs itself. Therefore, the LDA-based topic model is linearly combined with a visual language model for each word image in this study. After that, the basic query likelihood model is used for realizing the procedure of retrieval. The experimental results on our dataset show that the proposed LDA-based representation approach can efficiently and accurately attain to the aim of keyword spotting on a collection of historical Mongolian documents. Meanwhile, the proposed approach improves the performance significantly than the original BoVW approach.