Deep Learning Autoencoder Approach for Handwritten Arabic Digits Recognition

Abstract

This paper presents a new unsupervised learning approach with stacked autoencoder (SAE) for Arabic handwritten digits categorization. Recently, Arabic handwritten digits recognition has been an important area due to its applications in several fields. This work is focusing on the recognition part of handwritten Arabic digits recognition that face several challenges, including the unlimited variation in human handwriting and the large public databases. Arabic digits contains ten numbers that were descended from the Indian digits system. Stacked autoencoder (SAE) tested and trained the MADBase database (Arabic handwritten digits images) that contain 10000 testing images and 60000 training images. We show that the use of SAE leads to significant improvements across different machine-learning classification algorithms. SAE is giving an average accuracy of 98.5%.

6 pages

References in corpus (1)

• Natural Language Processing (almost) from Scratch

Cited by in corpus (7)

• Variance Reduced Local SGD with Lower Communication Complexity
• Arabic Handwritten Character Recognition based on Convolution Neural Networks and Support Vector Machine
• Batch Layer Normalization, A new normalization layer for CNNs and RNN
• Multi-script Handwritten Digit Recognition Using Multi-task Learning
• EdgeNet: A novel approach for Arabic numeral classification
• Deep Learning Methods for Signature Verification
• Classification of Chinese Handwritten Numbers with Labeled Projective Dictionary Pair Learning