Recognition of Persian/Arabic Handwritten Words Using a Combination of Convolutional Neural Networks and Autoencoder (AECNN)

Abstract

Despite extensive research, recognition of Persian and Arabic manuscripts is still a challenging problem due to the complicated and irregular nature of writing, wide vocabulary, and diversity of handwritings. In Persian and Arabic words, letters are joined together, and signs such as dots are placed above or below letters. In the proposed approach, the words are first decomposed into their constituent subwords to enhance the recognition accuracy. Then the signs of subwords are extracted to develop a dictionary of main subwords and signs. The dictionary is then employed to train a classifier. Since the proposed recognition approach is based on unsigned subwords, the classifier may make a mistake in recognizing some subwords of a word. To overcome this, a new subword fusion algorithm is proposed based on the similarity of the main subwords and signs. Here, convolutional neural networks (CNNs) are utilized to train the classifier. An autoencoder (AE) network is employed to extract appropriate features. Thus, a hybrid network is developed and named AECNN. The known Iranshahr dataset, including nearly 17000 images of handwritten names of 503 cities of Iran, was employed to analyze and test the proposed approach. The resultant recognition accuracy is 91.09%. Therefore, the proposed approach is much more capable than the other methods known in the literature.

CNN-based Methods for Offline Arabic Handwriting Recognition: A Review

“…In the first approach, SVM [55-57, 61, 76, 77, 87] and LSTM [62,63,80,89] have proven to be effective classifiers, surpassing the capacity of FCs. In the second approach, deep networks like DBN [81], RBM [90], and AutoEncoder [76,79,91] have exhibited effectiveness in extracting representative features, thereby enhancing the performance of standalone CNNs.…”

“…The same approach was adopted by Khosravi and Chalechale [91], this time employing an AutoEncoder for feature extraction in place of DBN. The encoded image in AutoEncoder is then passed through the CNN layers for further feature extraction and classification.…”