Query-by-example word spotting using multiscale features and classification in the space of representation differences
Query-by-example word spotting using multiscale features and classification in the space of representation differences
Mhiri, Mohamed and Cheriet, Mohamed and Desrosiers, Christian
Proceedings – International Conference on Image Processing, ICIP 2018
Abstract : Word spotting in document images is a challenging problem, due to the large intra-class variability in handwritten shapes and the lack of labeled data. To tackle these challenges, this paper proposes an efficient multiscale representation for word images, which is learned in an unsupervised manner using the spherical k-means algorithm. A pooling function is applied in a spatial grid to obtain a fixed-length vector of features, robust to small shifts in the image. Scale variability in handwritten data is also considered by using patches of various sizes in the encoding process. Another important contribution of this work is to model the training-based word spotting task as a classification problem in the space of representation differences, thereby allowing the learned model to find matches for word classes that were not seen in training. The proposed system is evaluated on the well-known George Washington (GW) dataset. Experimental results show that our system outperforms state-of-the-art word spotting approaches in both training-free and training-based scenarios.
