The week's pick
Random Articles
Reseach Article
OCR using the Artificial Neural Network with Character Localization using Combined PCA and MSER Features
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 150 - Number 4 |
| Year of Publication: 2016 |
| Authors: Sonu Rani, Navpreet Kaur |
10.5120/ijca2016911486
|
Sonu Rani, Navpreet Kaur . OCR using the Artificial Neural Network with Character Localization using Combined PCA and MSER Features. International Journal of Computer Applications. 150, 4 ( Sep 2016), 16-19. DOI=10.5120/ijca2016911486
Abstract
The optical character recognition models are the algorithms to detect and extract the text from the image data. The optical character recognition (OCR) algorithms and the applications have gained the popularity among the IT researchers in the recent years. The OCR models have been utilized with the paper text scanning, natural scene text recognition, online sharing image tagging, etc. In this paper, the model has been proposed for the natural scene text recognition, which has been found the greater popularity over the years. The natural text recognition model has been found efficient in the case of automatic text recognition from the sign boards, LED boards and other such information collection from other visual sources. The proposed model specifically designed to work over the LED boards for the detection and extraction of the LED text, which is written in the combination of the small LED lights to form the shape of the character. The proposed model has been designed with the combination of the shape recognition, text region detection and character recognition method using the maximally stable extremal regions (MSER), principal component analysis (PCA) and the artificial neural networks (ANN). The proposed model has been designed as the robust text region detection and localization solution along with the text recognition method. The proposed model has undergone the various experiments for the evaluation of the performance from the various aspects altogether. The proposed solution has performed as per the expectation and outperformed the existing model in the terms of detection and recognition accuracy.
References
- Gupta, Neha, and V. K. Banga. "Localization of Text in Complex Images Using Haar Wavelet Transform." International Journal of Innovative Technology and Exploring Engineering (IJITEE) 1 (2012): 111.
- Ikica, Andrej, and Peter Peer. "An improved edge profile based method for text detection in images of natural scenes." In EUROCON-International Conference on Computer as a Tool (EUROCON), 2011 IEEE, pp. 1-4. IEEE, 2011.
- Iqbal, Khalid, Xu-Cheng Yin, Hong-Wei Hao, Sohail Asghar, and Hazrat Ali. "Bayesian network scores based text localization in scene images." In Neural Networks (IJCNN), 2014 International Joint Conference on, pp. 2218-2225. IEEE, 2014.
- Jo, Kanghyun. "LED Dot matrix text recognition method in natural scene", Neuro computing, vol 1, issue 1, pp. 1033-1041, Science Direct (Elsevier), 2015.
- Kaur, Tajinder, and Nirvair Neeru. "Text Detection and Recognition from Natural Scene", vol 4, no. 7, pp. 3211-3216, IJARCET 2015.
- Kaur, Tajinder, and Nirvair Neeru. "Text Extraction from Natural Scene using PCA", vol 5, issue 7, pp. 272-277, IJCSET 2015.
- Mishra, Anand, Karteek Alahari, and C. V. Jawahar. "Top-down and bottom-up cues for scene text recognition." In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 2687-2694. IEEE, 2012.
- Yin, Xu-Cheng, Xuwang Yin, Kaizhu Huang, and Hong-Wei Hao. "Robust text detection in natural scene images." Pattern Analysis and Machine Intelligence, IEEE Transactions on 36, no. 5 (2014): 970-983.
Index Terms
Keywords