Efficient Recognition Of Unconstrained Hand Written Characters Using Neural Network Algorithms

Abstract

ABSTRACT newline newline newlineKeyword spotting refers to automatic recognition of handwritten text, letter, and manuscripts from historical hand written books and the process of retrieving all instances of a given keyword from a document. Information collection from Libraries all over the world store huge numbers of hand written books of crucial importance for preserving the world s cultural heritage, making these books available for searching and browsing would greatly helpful for researcher and public. It is of interest to derive keyword spotting using a neural network-based system for unconstrained handwriting recognition. Particularly in the field of unconstrained hand writing recognition (HWR) where the writing styles of various writers must be dealt with, severe difficulties are encountered. As such keyword spotting performs template-free spotting. i.e., it is not necessary for a keyword to appear in the training set. The Keyword spotting is accomplished using a modification of the CTC Token Passing algorithm in conjunction with a recurrent neural network. Furthermore, I analyze the performance of the underlying neural networks when using them in a recognition task followed by keyword spotting on the produced transcription. I have proposed a keyword spotting method for hand written text using neural network, with a new version of CTC Token Pass algorithm with fast and reliable keyword spotting can be performed without using any text line or segmenting individual words. newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline newline