A method for handwritten word spotting based on particle swarm optimisation and multi‐layer perceptron. Issue 2 (1st April 2018)

• Record Type: Journal Article
• Authors: Tavoli, Reza; Keyvanpour, Mohammadreza
• Is Part Of: IET software. Volume 12:Issue 2(2018)
• Page Start: 152
• Page End: 159
• Publication Date: 2018-04-01
• Subjects: handwritten character recognition -- document image processing -- multilayer perceptrons -- particle swarm optimisation -- natural language processing -- learning (artificial intelligence) -- image retrieval; PSOMLP-HWS -- particle swarm optimisation -- multilayer perceptron neural network -- handwritten word spotting -- handwritten keyword spotting -- neural network architecture -- new particle coding -- new fitness function -- coding particle -- neural network node activation -- neural network node deactivation -- AMA Arabic dataset -- IAM English dataset -- IFN-Farsi dataset -- template-based methods -- word image query -- learning-based methods; Computer software -- Periodicals; Software engineering -- Periodicals; 005.1
• DOI: 10.1049/iet-sen.2017.0071
• Languages: English
• ISSNs: 1751-8806

Abstract

Abstract : This study presents a new method for handwritten keyword spotting. The innovation in this paper is to provide a model based on neural network architecture and an output based on the margin. At first, a neural network is designed such that its output determines whether a test word as an input is spotted or rejected. The intended neural network has one input layer, two middle layers, and one output layer. Another innovation in this study is optimising neural network weights based on swarm optimisation method. This optimisation model is used to train the neural network, so that the output has adequate margin for classification. The new components of the proposed classifier include new particle coding and new fitness function. Two layers are considered in coding particle, one for activating and deactivating neural network nodes and the other layer for acquiring proper values for weights. Different experiments with variety of parameters were designed for the multi‐layer perceptron neural network. The experiments on three datasets: AMA Arabic dataset, IAM English dataset, and IFN/Farsi dataset yielded 83, 77, and 69% values, respectively, in the best condition. The results demonstrate that the proposed method has been better than the previous ones.