A Survey of Handwritten Character Recognition with MNIST and EMNIST
Open Access
- 4 August 2019
- journal article
- review article
- Published by MDPI AG in Applied Sciences
- Vol. 9 (15), 3169
- https://doi.org/10.3390/app9153169
Abstract
This paper summarizes the top state-of-the-art contributions reported on the MNIST dataset for handwritten digit recognition. This dataset has been extensively used to validate novel techniques in computer vision, and in recent years, many authors have explored the performance of convolutional neural networks (CNNs) and other deep learning techniques over this dataset. To the best of our knowledge, this paper is the first exhaustive and updated review of this dataset; there are some online rankings, but they are outdated, and most published papers survey only closely related works, omitting most of the literature. This paper makes a distinction between those works using some kind of data augmentation and works using the original dataset out-of-the-box. Also, works using CNNs are reported separately; as they are becoming the state-of-the-art approach for solving this problem. Nowadays, a significant amount of works have attained a test error rate smaller than 1% on this dataset; which is becoming non-challenging. By mid-2017, a new dataset was introduced: EMNIST, which involves both digits and letters, with a larger amount of data acquired from a database different than MNIST’s. In this paper, EMNIST is explained and some results are surveyed.Keywords
This publication has 29 references indexed in Scilit:
- Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ AlgorithmPLOS ONE, 2015
- Online and adaptive pseudoinverse solutions for ELM weightsNeurocomputing, 2015
- Invariant Scattering Convolution NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Shear responses of $[\bar{1}\,1\,0]$ -tilt {1 1 5}/{1 1 1} asymmetric tilt grain boundaries in fcc metals by atomistic simulationsModelling and Simulation in Materials Science and Engineering, 2013
- Deep, Big, Simple Neural Nets for Handwritten Digit RecognitionNeural Computation, 2010
- A trainable feature extractor for handwritten digit recognitionPattern Recognition, 2007
- Supervised Learning of Fuzzy ARTMAP Neural Networks Through Particle Swarm OptimisationJournal of Pattern Recognition Research, 2007
- Automatic recognition of handwritten numerical strings: a recognition and verification strategyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Shape matching and object recognition using shape contextsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998