Description

Segmentation of handwritten document images into text-lines and words is an essential task for optical character recognition. However, since the features of handwritten document are irregular and diverse depending on the person, it is considered a challenging problem. In order to address the problem, we formulate the word segmentation problem as a binary quadratic assignment problem that considers pairwise correlations between the gaps as well as the likelihoods of individual gaps. Even though many parameters are involved in our formulation, we estimate all parameters based on the Structured SVM framework so that the proposed method works well regardless of writing styles and written languages without user-defined parameters. Experimental results on ICDAR 2009/2013 handwriting segmentation databases show that proposed method achieves the state-of-the-art performance on Latin-based and Indian languages. But in this paper there is the problem of word spotting and word recognition on images. In the proposed system, this is achieved by a combination of label embedding and attributes learning, and a common subspace regression. Then the images and strings represent the same word which are close to each other allowing one to cast recognition and retrieval tasks. Compared with the existing method, the advantage of our method has a fixed length, low dimensional and very fast to compute. In the preprocessing the given dataset is filtered by using median filter. After that, in the segmentation process every image is cropped identically by the bounding box segmentation. Then in the feature extraction is done by Gabor wavelet for each and every character which is cropped from bounding box. For classifying the image we use KNN classifier. Matlab software and its image processing toolbox have been used in images processing and analysis. We test our approach for the given dataset of both handwritten documents and natural images showing results comparable or better than the state-of-the-art on spotting and recognition tasks.