A Novel Method for Persian Handwritten Digit Recognition Using Support Vector Machine
Publish place: majlesi Journal of Electrical Engineering، Vol: 12، Issue: 3
Publish Year: 1397
نوع سند: مقاله ژورنالی
زبان: English
View: 118
This Paper With 5 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_MJEE-12-3_007
تاریخ نمایه سازی: 25 بهمن 1401
Abstract:
Handwritten digit recognition has got a special role in different applications in the field of digital recognition including; handwritten address detection, check, and document. Persian handwritten digits classification has been facing difficulties due to different handwritten styles, inter-class similarities, and intra-class differences. In this paper, a novel method for detecting Persian handwritten digits is presented. In the proposed method, a combination of Histogram of Oriented Gradients (HOG), ۴-side profiles of the digit image, and some horizontal and vertical samples was used and the dimension of the feature vector was reduced using Principal Component Analysis (PCA). The proposed method applied to the HODA database, and Support Vector Machine (SVM) was used in the classification step. Results revealed that the detection accuracy of such method has ۹۹% accuracy with an adequate rate due to existing unacceptable samples in the database, therefore, the proposed method could improve the outcomes compared to other existing methods.
Keywords:
Histogram of oriented gradients (HOG) , Principle component analysis (PCA) , Support vector machine (SVM)
Authors
Mojtaba Mohammadpoor
Electrical and Computer Engineering Department, University of Gonabad, Gonabad, Iran,
Abbas Mehdizadeh
Department of Electrical and Computer Engineering, University of Gonabad, Gonabad
Hava Alizadeh Noghabi
Department of Computing, Nilai University, Negeri Sembilan
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :