Attribute CNNs for Word Spotting in Handwritten Documents
This work addresses the problem of efficiently searching for words in handwritten documents for researchers and archivists, representing an incremental improvement over prior methods.
The authors tackled word spotting in handwritten documents by learning attribute representations with Convolutional Neural Networks (CNNs), achieving state-of-the-art results across multiple datasets.
Word spotting has become a field of strong research interest in document image analysis over the last years. Recently, AttributeSVMs were proposed which predict a binary attribute representation. At their time, this influential method defined the state-of-the-art in segmentation-based word spotting. In this work, we present an approach for learning attribute representations with Convolutional Neural Networks (CNNs). By taking a probabilistic perspective on training CNNs, we derive two different loss functions for binary and real-valued word string embeddings. In addition, we propose two different CNN architectures, specifically designed for word spotting. These architectures are able to be trained in an end-to-end fashion. In a number of experiments, we investigate the influence of different word string embeddings and optimization strategies. We show our Attribute CNNs to achieve state-of-the-art results for segmentation-based word spotting on a large variety of data sets.