Procedia Computer Science · 2016 · 213 citations · 38 references
ComputingArabicComputer ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningImage ClassificationOptical Character RecognitionOverfittingPattern RecognitionSupport Vector MachinesConvolutional Neural NetworksDropoutHandwriting RecognitionHandwriting Recognition EvaluationHandwritten Arabic RecognitionHandwritten Character RecognitionSupport Vector ClassificationSupport Vector Machine Classification
Convolutional networks efficiently extract features, while SVMs serve as effective recognizers. The study proposes a new offline Arabic handwriting recognition model that integrates a CNN and an SVM with dropout. The architecture replaces the CNN’s trainable classifier with an SVM, applies dropout to mitigate over‑fitting, and is evaluated on the HACDB and IFN/ENIT datasets. The model automatically extracts features and classifies Arabic characters, achieving significantly higher accuracy than a CNN‑based SVM without dropout and outperforming the standard CNN, with results comparable to state‑of‑the‑art OCR.
In this paper we explore a new model focused on integrating two classifiers; Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for offline Arabic handwriting recognition (OAHR) on which the dropout technique was applied. The suggested system altered the trainable classifier of the CNN by the SVM classifier. A convolutional network is beneficial for extracting features information and SVM functions as a recognizer. It was found that this model both automatically extracts features from the raw images and performs classification. Additionally, we protected our model against over-fitting due to the powerful performance of dropout. In this work, the recognition on the handwritten Arabic characters was evaluated; the training and test sets were taken from the HACDB and IFN/ENIT databases. Simulation results proved that the new design based-SVM of the CNN classifier architecture with dropout performs significantly more efficiently than CNN based-SVM model without dropout and the standard CNN classifier. The performance of our model is compared with character recognition accuracies gained from state-of-the-art Arabic Optical Character Recognition, producing favorable results.
38
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Corinna Cortes, Vladimir Vapnik · Machine Learning · 1995 · 40.5K citations · Full text
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Corinna Cortes, Vladimir Vapnik · Machine Learning · 1995 · 33K citations · Full text