Answers are grounded in this paper and cite their sources.
This observation demonstrates 99.51% accuracy using CNN and boosting classifiers in handwritten digit recognition, indicating improvements in machine learning techniques.
Patters are in many typeslike audio/video, character/digit etc. Pattern recognition refers to the task of identifying the pattern in an expert manner. Different researchers have applied different Machine Learning (ML) and Deep Neural Network (DNN) techniques for pattern recognition in different domains. This research is targeted to develop an expert system for hand written digit recognition. In this research a pattern recognition model is presented by using hybrid technique of Convolutional Neural Network (CNN) with three different boosting classifiers. The model is tested with handwritten digit data set downloaded from MNIST and EMNIST. The classification process initiated by applying CNN, used for features extraction and then three standard gradient boosting classification algorithms named Ada-Boosting classifier (ABC), Extreme Gradient Boosting classifier (XGB) and Light Gradient Boosting Machine (LGBM) is applied for classification. The experimental result shows that the integrated method of CNN and LGBM produce best accuracy of 99.51% and 99.7025% with MNIST and EMNIST dataset respectively.
No takes yet. Share an insight, caveat, or question.
Banerjee et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: