• JUser: :_load: Unable to load user with ID: 948

Deep Learning for Document Image Analysis"Prof. Santanu Chaudhury, Dhananjay Chair Professor, FNAE, FNASc, FIAPR, Department of Electrical Enginering, I.I.T, Delhi"

Deep networks provide a new paradigm for feature discovery and recognition.  We can approach problems of document image analysis in the framework of deep learning. We shall examine use of deep learning for scene text recognition. Next we shall present an architecture for text recognition using deep LSTM.  Text recognition involves some initial image processing steps like segmentation of lines and words which can induce error to the recognition system. Without segmentation, learning very long range context is difficult and becomes computationally intractable. Therefore, alternative soft decisions are needed at the pre-processing level. This paper proposes a hybrid text recognizer using a deep recurrent neural network with multiple layers of abstraction and long range context along with a language model to verify the performance of the deep neural network. In this paper we construct a multi-hypotheses tree architecture with candidate segments of line sequences from different segmentation algorithms at its different branches. The deep neural network is trained on perfectly segmented data and tests each of the candidate segments, generating unicode sequences. In the verification step, these unicode sequences are validated using a sub-string match with the language model and best first search is used to find the best possible combination of alternative hypothesis from the tree structure. Thus the verification framework using language models eliminates wrong segmentation outputs and filters recognition errors.