A Meetei Mayek Handwritten Digit Recognition System

Optical Character Recognition is an appealing field of work for research where an image containing text is given as input and text in the image is translated into an editable format. This paper proposes Meetei/Meitei Mayek Handwritten Digit Recognition System where an Isolated Handwritten Meetei Mayek Digit Database consisting of 10000 plus digits has been developed. This proposed Handwritten Meetei Mayek Digit Recognition System is an important component of Manipuri Meetei Mayek Optical Character Recognition system which is under development. For feature extraction, we have used State-of-Art techniques—Histogram of Oriented Gradients and Bag of Features Descriptor for Speeded Up Robust Features. Five classifiers have been employed for classification viz. Support Vector Machine, with Linear, Polynomial and Radial Basis Function kernels, K-Nearest Neighbours and Bootstrap Aggregating and compared in terms of accuracy. Support Vector Machine using Radial Basis Function Kernel has found to achieve the recognition accuracy with the highest value compared with the other classifiers with the extracted Histogram of Oriented Gradients and Bag of Features for Speeded Up Robust Features.

Download Full-text

Handwritten Digit Recognition Using Deep Learning

International Journal of Scientific Research in Science and Technology ◽

10.32628/cseit217439 ◽

2021 ◽

pp. 153-158

Author(s):

Bhagyashree P M ◽

L K Likhitha ◽

D S Rajesh

Keyword(s):

Deep Learning ◽

Learning Strategies ◽

Character Recognition ◽

Optical Character Recognition ◽

Handwriting Recognition ◽

Handwritten Digit Recognition ◽

Digit Recognition ◽

Handwritten Digit ◽

Overall Performance ◽

Similar Accuracy

Traditional systems of handwritten Digit Recognition have depended on handcrafted functions and a massive amount of previous knowledge. Training an Optical character recognition (OCR) system primarily based totally on those stipulations is a hard task. Research in the handwriting recognition subject is centered on deep learning strategies and has accomplished breakthrough overall performance in the previous couple of years. Convolutional neural networks (CNNs) are very powerful in perceiving the structure of handwritten digits in ways that assist in automated extraction of features and make CNN the most appropriate technique for solving handwriting recognition problems. Here, our goal is to attain similar accuracy through the use of a pure CNN structure.CNN structure is proposed to be able to attain accuracy even higher than that of ensemble architectures, alongside decreased operational complexity and price. The proposed method gives 99.87 accuracy for real-world handwritten digit prediction with less than 0.1 % loss on training with 60000 digits while 10000 under validation.

Download Full-text

Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)

Sensors ◽

10.3390/s20123344 ◽

2020 ◽

Vol 20 (12) ◽

pp. 3344 ◽

Cited By ~ 3

Author(s):

Savita Ahlawat ◽

Amit Choudhary ◽

Anand Nayyar ◽

Saurabh Singh ◽

Byungun Yoon

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Character Recognition ◽

Optical Character Recognition ◽

Recognition Accuracy ◽

Handwriting Recognition ◽

Computational Cost ◽

Handwritten Digit Recognition ◽

Digit Recognition ◽

Handwritten Digit

Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network’s recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.

Download Full-text

A Novel Approach Towards Handwritten Digit Recognition Using Refraction Property of Light Rays

International Journal of Computer Vision and Image Processing ◽

10.4018/ijcvip.2020070101 ◽

2020 ◽

Vol 10 (3) ◽

pp. 1-17 ◽

Cited By ~ 1

Author(s):

Roopkatha Samanta ◽

Soulib Ghosh ◽

Agneet Chatterjee ◽

Ram Sarkar

Keyword(s):

Character Recognition ◽

Optical Character Recognition ◽

State Of The Art ◽

Feature Descriptor ◽

Handwritten Digit Recognition ◽

Digit Recognition ◽

Novel Approach ◽

Light Rays ◽

Handwritten Digit ◽

Invariant Shape

Due to the enormous application, handwritten digit recognition (HDR) has become an extremely important domain in optical character recognition (OCR)-related research. The predominant challenges faced in this domain include different photometric inconsistencies together with computational complexity. In this paper, the authors proposed a language invariant shape-based feature descriptor using the refraction property of light rays. It is to be noted that the proposed approach is novel as an adaptation of refraction property is completely new in this domain. The proposed method is assessed using five datasets of five different languages. Among the five datasets, four are offline (written Devanagari, Bangla, Arabic, and Telugu) and one is online (written in Assamese) handwritten digit datasets. The approach provides admirable outcomes for online digits whereas; it yields satisfactory results for offline handwritten digits. The method gives good result for both online and offline handwritten digits, which proves its robustness. It is also computationally less expensive compared to other state-of-the-art methods including deep learning-based models.

Download Full-text