TY - GEN
T1 - Recognizing handwritten characters with local descriptors and bags of visual words
AU - Surinta, Olarik
AU - Karaaba, Mahir F.
AU - Mishra, Tusar K.
AU - Schomaker, Lambert R.B.
AU - Wiering, Marco A.
N1 - Publisher Copyright:
© Springer International Publishing Switzerland 2015.
PY - 2015
Y1 - 2015
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/84951791486
UR - https://www.scopus.com/inward/citedby.url?scp=84951791486&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-23983-5_24
DO - 10.1007/978-3-319-23983-5_24
M3 - Conference contribution
AN - SCOPUS:84951791486
SN - 9783319239811
T3 - Communications in Computer and Information Science
SP - 255
EP - 264
BT - Engineering Applications of Neural Networks - 16th International Conference, EANN 2015, Proceedings
A2 - Iliadis, Lazaros
A2 - Jayne, Chrisina
PB - Springer Verlag
T2 - 16th International Conference on Engineering Applications of Neural Networks, EANN 2015
Y2 - 25 September 2015 through 28 September 2015
ER -