{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-learning-autoencoder-approach-for","title":"Deep Learning Autoencoder Approach for Handwritten Arabic Digits Recognition","arxiv_id":"1706.06720","date":"2017-06-21","proceeding":null,"authors":["Mohamed Loey","Ahmed El-Sawy","Hazem EL-Bakry"],"abstract":"This paper presents a new unsupervised learning approach with stacked\nautoencoder (SAE) for Arabic handwritten digits categorization. Recently,\nArabic handwritten digits recognition has been an important area due to its\napplications in several fields. This work is focusing on the recognition part\nof handwritten Arabic digits recognition that face several challenges,\nincluding the unlimited variation in human handwriting and the large public\ndatabases. Arabic digits contains ten numbers that were descended from the\nIndian digits system. Stacked autoencoder (SAE) tested and trained the MADBase\ndatabase (Arabic handwritten digits images) that contain 10000 testing images\nand 60000 training images. We show that the use of SAE leads to significant\nimprovements across different machine-learning classification algorithms. SAE\nis giving an average accuracy of 98.5%.","url_abs":"http://arxiv.org/abs/1706.06720v1","url_pdf":"http://arxiv.org/pdf/1706.06720v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-learning-autoencoder-approach-for","repo_url":"https://github.com/zaabl/Arabic-Optical-Character-Recognizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.06720","atlas_url":"https://app.syntology.ai/?focus=1706.06720","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}