Digit recognition using decimal coding and artificial neural network

Abstract

Current artificial neural network image recognition techniques use all the pixels of an image as input. In this paper, we present an efficient method for handwritten digit recognition that involves extracting the characteristics of a digit image by coding each row of the image as a decimal value, i.e., by transforming the binary representation into a decimal value. This method is called the decimal coding of rows. The set of decimal values calculated from the initial image is arranged as a vector and normalized; these values represent the inputs to the artificial neural network. The approach proposed in this work uses a multilayer perceptron neural network for the classification, recognition, and prediction of handwritten digits from 0 to 9. In this study, a dataset of 1797 samples were obtained from a digit database imported from the Scikit-learn library. Backpropagation was used as a learning algorithm to train the multilayer perceptron neural network. The results show that the proposed approach achieves better performance than two other schemes in terms of recognition accuracy and execution time.

Oversampling based on generative adversarial networks to overcome imbalance data in predicting fraud insurance claim

“…Deep learning is also suitable for big, multi-dimensional data that can be executed through a hidden network structure that supports important information for increased accuracy (Li et al, 2018). This method allows simultaneous classification, recognition, and prediction (Datsi et al, 2022). Recently, a new deep learning family called generative adversarial networks (GANs) was introduced.…”

Classifying horse activities with big data using machine learning

“…In the context of big data, machine learning methods enable us uncovering of complex patterns and making accurate predictions, e.g., for diagnosis in health (Al-Dousari et al, 2021;Oshinubi et al, 2021;Nallamuth & Palanichamy, 2015;Colak et al, 2016), opinion target identification (Khan et al, 2016), text classification (Jain & Kumar, 2018), image retrieval (Mehmood et al, 2018), and recognition (Datsi et al, 2021). In this study, we focus on the power of machine learning with big data for animal activity recognition.…”