Handwritten Urdu Characters and Digits Recognition Using Transfer Learning and Augmentation With AlexNet

نویسندگان

چکیده

Automated recognition of handwritten characters and digits is a challenging task. Although significant amount literature exists for automatic English other major languages in the world, there wide research gap due to lack Urdu language. The variations writing style, shape size individual similarities with add complexity accurate classification characters. Deep neural networks have emerged as powerful technology automated character patters object images. deep are known provide remarkable results on large-scale datasets millions images, however use small image still challenging. purpose this present framework higher accuracy by utilizing theory transfer learning pre-trained Convolution Neural Networks (CNN). performance evaluated different ways: using AlexNet CNN model Support Vector Machine (SVM) classifier, fine-tuned extracting features classification. We hyper-parameters achieve data augmentation performed avoid over-fitting. Experimental quantitative comparisons demonstrate effectiveness proposed AlexNet. based outperforms related state-of-the-art thereby achieving 97.08%, 98.21%, 94.92% urdu characters, hybrid respectively. presented methods can be applied diverse domains such text retrieval, reading postal addresses, bank’s cheque processing, preserving digitization manuscripts from old ages.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Handwritten digits recognition using OpenCV

The automated recognition of handwritten digits is a largely studied problem which connects the fields of Computer Vision and Machine Learning and has many applications in real life. In this project, I detail an introductory investigation of the performance of classification in several contexts. Namely, relying on the OpenCV implementations of k-Nearest Neighbor, Random Forests, and Support Vec...

متن کامل

Use of the Shearlet Transform and Transfer Learning in Offline Handwritten Signature Verification and Recognition

Despite the growing growth of technology, handwritten signature has been selected as the first option between biometrics by users. In this paper, a new methodology for offline handwritten signature verification and recognition based on the Shearlet transform and transfer learning is proposed. Since, a large percentage of handwritten signatures are composed of curves and the performance of a sig...

متن کامل

Automatic Recognition of Offline Handwritten Urdu Digits In Unconstrained Environment Using Daubechies Wavelet Transforms

This paper presents an optical character recognition system for the handwritten Urdu Digits. A lot of work has been done in recognition of characters and numerals of various languages like Devanagari, English, Chinese, and Arabic etc. But in case of handwritten Urdu Digits very less work has been reported. Different Daubechies Wavelet transforms are used in this work for feature extraction. Als...

متن کامل

Recognition of Handwritten Bangla Basic Characters and Digits using Convex Hull based Feature Set

In dealing with the problem of recognition of handwritten character patterns of varying shapes and sizes, selection of a proper feature set is important to achieve high recognition performance. The current research aims to evaluate the performance of the convex hull based feature set, i.e. 125 features in all computed over different bays attributes of the convex hull of a pattern, for effective...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Access

سال: 2022

ISSN: ['2169-3536']

DOI: https://doi.org/10.1109/access.2022.3208959