A Survey on using Neural Network based Algorithms for Hand Written Digit Recognition

Abstract

The detection and recognition of handwritten content is the process of converting non-intelligent information such as images into machine edit-able text. This research domain has become an active research area due to vast applications in a number of fields such as handwritten filing of forms or documents in banks, exam form filled by students, users' authentication applications. Generally, the handwritten content recognition process consists of four steps: data preprocessing, segmentation, the feature extraction and selection, application of supervised learning algorithms. In this paper, a detailed survey of existing techniques used for Hand Written Digit Recognition(HWDR) is carried out. This review is novel as it is focused on HWDR and also it only discusses the application of Neural Network (NN) and its modified algorithms. We discuss an overview of NN and different algorithms which have been adopted from NN. In addition, this research study presents a detailed survey of the use of NN and its variants for digit recognition. Each existing work, we elaborate its steps, novelty, use of dataset and advantages and limitations as well. Moreover, we present a Scientometric analysis of HWDR which presents top journals and sources of research content in this research domain. We also present research challenges and potential future work.

Improving the Performance of Automated Optical Inspection (AOI) Using Machine Learning Classifiers

“…From the input layer, the data is passed through the nodes of the different layers and ends in the output layer [1]. ANN is already used in different domains such as speech recognition [8], natural language processing [1], object detection [4], and hand-written word recognition [1,10].…”

Handwritten Bangla Numerical Digit Recognition Using Fine Regulated Deep Neural Network

“…Handwritten detection and recognition are the process of transforming non intelligent information such as images into machine editable content. Ramzan et al (2018) proposed hand written digit recognition (HWDR) methods that only describe the importance of neural network and its available algorithms with different techniques or modified algorithm (Ramzan et al, 2018). Deep hog is a hybrid model that classify the isolated alphanumeric symbols of the Bangla language.…”

Digit recognition using decimal coding and artificial neural network

“…It has become more competitive with other models used in regression and statistics in terms of its usefulness. An ANN contains a set of different types of neural networks, such as single layer perceptrons, feedforward, networks, multilayer perceptrons, recurrent neural networks, and CNN's (Datsi et al, 2019;Ramzan et al, 2018). It stimulates the biological function of nervous systems and can optimize complex systems that are difficult to model using other techniques such as mathematical modeling (Abiodun et al, 2018).…”