Handwritten digit recognition: benchmarking of state-of-the-art techniques
By Chenglin Liu, Kazuki Nakashima, Hiroshi Sako, Hiromichi Fujisawa. Pattern Recognition, 2003
587 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/8463169793f30a55058614aa122b926c05057ab7
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Qixiang Ye
- Jitendra Malik
- Dacheng Tao
- Marc Pollefeys
- Yi Yang
- Andrea Vedaldi
- Xiaogang Wang
Citations in the corpus
- Handwritten digit recognition: investigation of normalization and feature extraction techniques (2004, methodology): “A number of high accuracies were collected in [2], wherein a record of high accuracy, 98.”
- A survey of the recent architectures of deep convolutional neural networks (2019, methodology): “s kept working on CNN and tried to optimize its performance. In 2003, Simard et al. improved CNN architecture and showed good results as compared to SVM on a hand digit benchmark dataset; MNIST [64], [68], [70]–[72]. This performance improvement expedited the research in CNN by extending its applica”
- Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR) (2020, methodology): “Sample handwritten digits from MNIST dataset [42].”
- TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks (2016, result): “In section 4.1 we show that we achieve similar to STN results on a benchmark introduced by its authors [11], but with simpler model and with shorter training time.”
- A New Truncation Strategy for the Higher-Order Singular Value Decomposition (2012, background): “It is well known, in the context of classification, that classifiers constructed from the main features of the training images [31] actually perform better than classifiers constructed from the raw image data [50].”
- Convolutional Neural Network (CNN) for Image Detection and Recognition (2018, methodology): “[3] evaluated the performance on MNIST datasets using 3 different classifiers: SVM (support vector machines), KNN (Knearest Neighbor) and CNN (convolutional neural networks).”
- Oriented Response Networks (2017, methodology): “We randomly rotate each sample in the MNIST dataset [29] between [0 , 2 π ] to yield MNIST-rot .”