Recognizing handwritten characters with local descriptors and bags of visual words

Olarik Surinta*, Mahir F. Karaaba, Tusar K. Mishra, Lambert R.B. Schomaker, Marco A. Wiering

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper we propose the use of several feature extraction methods, which have been shown before to perform well for object recognition, for recognizing handwritten characters. These methods are the histogram of oriented gradients (HOG), a bag of visual words using pixel intensity information (BOW), and a bag of visual words using extracted HOG features (HOG-BOW). These feature extraction algorithms are compared to other well-known techniques: principal component analysis, the discrete cosine transform, and the direct use of pixel intensities. The extracted features are given to three different types of support vector machines for classification, namely a linear SVM, an SVM with the RBF kernel, and a linear SVM using L2-regularization. We have evaluated the six different feature descriptors and three SVM classifiers on three different handwritten character datasets: Bangla, Odia and MNIST. The results show that the HOG-BOW, BOW and HOG method significantly outperform the other methods. The HOG-BOW method performs best with the L2-regularized SVM and obtains very high recognition accuracies on all three datasets.

Original languageEnglish
Title of host publicationEngineering Applications of Neural Networks - 16th International Conference, EANN 2015, Proceedings
EditorsLazaros Iliadis, Chrisina Jayne
PublisherSpringer Verlag
Pages255-264
Number of pages10
ISBN (Print)9783319239811
DOIs
Publication statusPublished - 2015
Event16th International Conference on Engineering Applications of Neural Networks, EANN 2015 - Rhodes, Greece
Duration: 25-09-201528-09-2015

Publication series

NameCommunications in Computer and Information Science
Volume517
ISSN (Print)1865-0929

Conference

Conference16th International Conference on Engineering Applications of Neural Networks, EANN 2015
Country/TerritoryGreece
CityRhodes
Period25-09-1528-09-15

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Recognizing handwritten characters with local descriptors and bags of visual words'. Together they form a unique fingerprint.

Cite this