Handwritten Arabic Text Recognition using Principal Component Analysis and Support Vector Machines

Abstract

In this paper, an offline holistic handwritten Arabic text recognition system based on Principal Component Analysis (PCA) and Support Vector Machine (SVM) classifiers is proposed. The proposed system consists of three primary stages: preliminary processing, feature extraction using PCA, and classification using the polynomial, linear, and Gaussian SVM classifiers. In this proposed system, text skeleton is first extracted and the images of the text are normalized into uniform size for extraction of the global features of the Arabic words using PCA. Recognition performance of this proposed system was evaluated on version 2 of the IFN/ENIT database of handwritten Arabic text using the polynomial, linear, and Gaussian SVM classifiers. The classification results of the proposed system were compared with the results produced by a benchmark. TRS that is depending on the Discrete Cosine Transform (DCT) method using numerous normalization sizes of Arabic text images. The experimental testing results support the effectiveness of the proposed system in holistic recognition of the handwritten Arabic text.

A hybrid Feature Selection Approach for Arabic Handwritten Text Based on Genetic Algorithm and Support Vector Machine

“…The selected features were tested on the IFN/ENIT dataset, it achieved 94.2% recognition rate using ANN classifier. Al-Saqqar et al [15] introduced an offline system for holistic recognition of the handwritten Arabic text based on PCA and SVM classifiers. This system was evaluated on version 2 of the IFN/ENIT database of handwritten Arabic text using the linear, Gaussian, and polynomial SVM classifiers.…”

“…The supreme goal of any Arabic Text Recognition (ATR) System is to mimic the human understanding abilities in order for the computer to read and understand text and perform text processing in a similar way to that of the human mind [15], [10]. In the domain of pattern recognition using Artificial Intelligence (AI) methods, handwritten text recognition is one of the most sophisticated problems [4].…”

“…The eventual goal of feature extraction is to provide an efficient representation of the text image using a set of distinct features [6], [15]. Review of the literature reveals that there are three main feature extraction techniques were used for Arabic handwritten text recognition: (i) statistical techniques such as Mean, Standard Deviation and PCA, (ii) Geometrical or structural techniques for extracting lines, dots, holes and many others, (iii) space transform techniques such as Discreet Cosine Transform (DCT) method [6], [12], [18].…”

A Holistic Model for Recognition of Handwritten Arabic Text Based on the Local Binary Pattern Technique

“…The ultimate goal of feature extraction phase is to ensure an efficient representation of a given text image using a set of proper features [2,6]. Those features are categorized into: low, medium and high-level features.…”

“…This model progresses in four steps: skeleton extraction, text image normalization, LBP for feature extraction, and classification via the polynomial, linear, and Gaussian SVM and ANN classifiers. The major contributions of this study are: (i) extraction of the handwritten Arabic text features by applying the LBP method; (ii) evaluation of the derived features on version 2 of the IFN/ENIT database of handwritten Arabic text using two machinelearning approaches (SVM and ANN), where the proposed model is tested using the polynomial, linear, and Gaussian SVM classifiers and three ANN training methods (Levenberg-Marqurdt (LM), Bayesian Regularization (BR) , and Scaled Conjugate Gradient (SCG)); and (iii) holding a comparison in recognition accuracy between the proposed HATRS and two benchmark HATRSs, one depending on Discrete Cosine Transform (DCT) and one depending on Principal Component Analysis, which have been developed by Al-Saqqar et al [6].…”