An Efficient Word Recognition System Based on Effective Classification Method

Computer Engineering

word spotting is a technique which can extract the text from input image. This paper addresses the problems of word spotting and word recognition on images. . In recognition, the goal is to recognize the content of the word image, usually aided by a dictionary or lexicon. Here we describe an approach in which both word images and text strings are embedded in a common vectorial subspace. This is achieved by a combination of label embedding and attributes learning, and a common subspace regression. In this subspace, images and strings that represent the same word are close together, allowing one to cast recognition and retrieval tasks as a nearest neighbor problem. In this work we shall also assume that the location of the words in the images is provided, i.e., we have access to images of cropped words. If those were not available, text localization and segmentation techniques could be used. In this paper the word can be recognized through this process using different algorithms.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.