Residual Neural Network Vs Local Binary Convolutional Neural Networks for Bilingual Handwritten Digit Recognition

2019 ◽  
pp. 25-34
Author(s):  
Ebrahim Al-wajih ◽  
Rozaida Ghazali ◽  
Yana Mazwin Mohmad Hassim
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Handwritten Digit Recognition ◽  
Digit Recognition ◽  
Handwritten Digit

scholarly journals Comparison of the efficiency of neural network algorithms in recognition and classification problems

2020 ◽  
Vol 224 ◽  
pp. 01025
Author(s):  
Alexey Beskopylny ◽  
Alexandr Lyapin ◽  
Nikita Beskopylny ◽  
Elena Kadomtseva
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computation Time ◽  
Classification Problems ◽  
Handwritten Digit Recognition ◽  
Network Algorithms ◽  
Digit Recognition ◽  
Labour Intensity ◽  
Handwritten Digit ◽  
Accuracy Of Results

The article is devoted to the problem of comparing the effectiveness of feedforward (FF) and convolutional neural networks (CNN) algorithms in the problems of handwritten digit recognition and classification. In recent years, the attention of many researchers to the FF and CNN algorithms has given rise to many hybrid models focused on solving specific problems. At the same time, the efficiency of each algorithm in terms of accuracy and labour intensity remains unclear. It is shown that in classical problems, FFs can have advantages over CNN in terms of labour intensity with the same accuracy of results. Using the handwritten digits data from the MNIST database as an example, it is shown that FF algorithms provide greater accuracy and require less computation time than CNN.

scholarly journals Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3344 ◽  
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.

Handwritten digit recognition using neural networks and dynamic zoning with stroke-based descriptors

2017 ◽  
Vol 25 (6) ◽  
pp. 979-990
Author(s):  
David Álvarez-León ◽  
Ramón-Ángel Fernández-Díaz ◽  
Lidia Sánchez-Gonzalez ◽  
José-Manuel Alija-Pérez
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Learning Process ◽  
Multilayer Perceptron ◽  
Handwritten Digit Recognition ◽  
Digit Recognition ◽  
Handwritten Digit ◽  
Dynamic Zoning

Abstract This article presents an Off-line handwritten digit recognition approach based on neural networks. We define a numeric character as a composition of vertical and horizontal strokes. After the preprocessing, we use dynamic zoning to retrieve the positions where vertical strokes – the main strokes — are joined to horizontal strokes. These features are recorded into a representative string and verified using a custom matching pattern. Finally, a multilayer perceptron neural network is fed with the previous data to raise the learning process. The results gathered from the experiments performed on the well-known MNIST handwritten database are compared against other proposals providing promising results.

When Massive GPU Parallelism Ain’t Enough: A Novel Hardware Architecture of 2D-LSTM Neural Network

2022 ◽  
Vol 15 (1) ◽  
pp. 1-35
Author(s):  
Vladimir Rybalkin ◽  
Jonas Ney ◽  
Menbere Kina Tekleyohannes ◽  
Norbert Wehn
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Energy Efficiency ◽  
Semantic Segmentation ◽  
Hardware Architecture ◽  
Handwritten Digit Recognition ◽  
Content Type ◽  
One Dimensional ◽  
Digit Recognition ◽  
Handwritten Digit

Multidimensional Long Short-Term Memory (MD-LSTM) neural network is an extension of one-dimensional LSTM for data with more than one dimension. MD-LSTM achieves state-of-the-art results in various applications, including handwritten text recognition, medical imaging, and many more. However, its implementation suffers from the inherently sequential execution that tremendously slows down both training and inference compared to other neural networks. The main goal of the current research is to provide acceleration for inference of MD-LSTM. We advocate that Field-Programmable Gate Array (FPGA) is an alternative platform for deep learning that can offer a solution when the massive parallelism of GPUs does not provide the necessary performance required by the application. In this article, we present the first hardware architecture for MD-LSTM. We conduct a systematic exploration to analyze a tradeoff between precision and accuracy. We use a challenging dataset for semantic segmentation, namely historical document image binarization from the DIBCO 2017 contest and a well-known MNIST dataset for handwritten digit recognition. Based on our new architecture, we implement FPGA-based accelerators that outperform Nvidia Geforce RTX 2080 Ti with respect to throughput by up to 9.9 and Nvidia Jetson AGX Xavier with respect to energy efficiency by up to 48 . Our accelerators achieve higher throughput, energy efficiency, and resource efficiency than FPGA-based implementations of convolutional neural networks (CNNs) for semantic segmentation tasks. For the handwritten digit recognition task, our FPGA implementations provide higher accuracy and can be considered as a solution when accuracy is a priority. Furthermore, they outperform earlier FPGA implementations of one-dimensional LSTMs with respect to throughput, energy efficiency, and resource efficiency.

scholarly journals Handwritten Digit Recognition using Image Preprocessing and CNN

2020 ◽  
pp. 896-902
Author(s):  
Anshul Dubey ◽  
Ashley Lazarus ◽  
Dharmendra Mangal
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Accuracy Rate ◽  
Handwritten Digit Recognition ◽  
Image Preprocessing ◽  
Digit Recognition ◽  
Handwritten Digit ◽  
Multilayer Architecture ◽  
Recognition Systems ◽  
Zip Code

Handwritten digit recognition, is a technique of identifying and enlisting the recognized digit, that uses neural networks, deep learning and machine learning. The applications and demand of handwritten digit recognition systems such as zip code recognition, car number plate recognition, robotics, banks, mobile applications and numerous more, are soaring every day. It can be done through numerous approaches, but convolutional neural network is considered one of the best methods. The special neural network uses multilayer architecture for identification and classification. Although the accuracy factor can be increased, based on image preprocessing, in this paper we discuss how the accuracy of the system can be increased for better handwritten digit recognition, using convolutional neural networks, image preprocessing; binarization, resizing, rotation. The accuracy rate obtained is 99.33%.

Sign in / Sign up

Export Citation Format

Share Document