Comparison of convolutional neural network and bag of features for multi-font digit recognition
This paper evaluates the recognition performance of Convolutional Neural Network (CNN) and Bag of Features (BoF) for multiple font digit recognition. Font digit recognition is part of character recognition that is used to translate images from many document-input tasks such as handwritten, typewritt...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Advanced Engineering and Science
2019
|
| Subjects: | |
| Online Access: | View Fulltext in Publisher View in Scopus |
| LEADER | 01831nam a2200229Ia 4500 | ||
|---|---|---|---|
| 001 | 10.11591-ijeecs.v15.i3.pp1322-1328 | ||
| 008 | 220121s2019 CNT 000 0 und d | ||
| 020 | |a 25024752 (ISSN) | ||
| 245 | 1 | 0 | |a Comparison of convolutional neural network and bag of features for multi-font digit recognition |
| 260 | 0 | |b Institute of Advanced Engineering and Science |c 2019 | |
| 650 | 0 | 4 | |a Bag of features (BoF) |
| 650 | 0 | 4 | |a CNN |
| 650 | 0 | 4 | |a Deep learning |
| 650 | 0 | 4 | |a Font digit recognition |
| 856 | |z View Fulltext in Publisher |u https://doi.org/10.11591/ijeecs.v15.i3.pp1322-1328 | ||
| 856 | |z View in Scopus |u https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102213915&doi=10.11591%2fijeecs.v15.i3.pp1322-1328&partnerID=40&md5=9e7b1bcd3ed555cffbd7b3d2451f518d | ||
| 520 | 3 | |a This paper evaluates the recognition performance of Convolutional Neural Network (CNN) and Bag of Features (BoF) for multiple font digit recognition. Font digit recognition is part of character recognition that is used to translate images from many document-input tasks such as handwritten, typewritten and printed text. BoF is a popular machine learning method while CNN is a popular deep learning method. Experiments were performed by applying BoF with Speeded-up Robust Feature (SURF) and Support Vector Machine (SVM) classifier and compared with CNN on Chars74K dataset. The recognition accuracy produced by BoF is just slightly lower than CNN where the accuracy of CNN is 0.96 while the accuracy of BoF is 0.94. © 2019 Institute of Advanced Engineering and Science. All rights reserved. | |
| 700 | 1 | 0 | |a Hidayah, S.N.S.M.N. |e author |
| 700 | 1 | 0 | |a Ibrahim, Z. |e author |
| 700 | 1 | 0 | |a Kadir, N.H.M. |e author |
| 700 | 1 | 0 | |a Mohammad, N. |e author |
| 773 | |t Indonesian Journal of Electrical Engineering and Computer Science |x 25024752 (ISSN) |g 15 3, 1322-1328 | ||