Optical Character Recognition using CRNN
Kambala Monica Sai1, Haritha Chandrika P2, Kasim Bebe3, G. S Roja Pramila4, G. Sankara Rao5
1Kambala Monica Sai*, Computer Science & Engineering, Gayatri Vidya Parishad College of Engineering for Women, Visakhapatnam, India.
2Haritha Chandrika Panuganti, Computer Science & Engineering, Gayatri Vidya Parishad College of Engineering for Women, Visakhapatnam, India.
3Kasim Bebe, Computer Science & Engineering, Gayatri Vidya Parishad College of Engineering for Women, Visakhapatnam, India.
4G. S. Roja Pramila, Computer Science & Engineering, Gayatri Vidya Parishad College of Engineering for Women, Visakhapatnam, India.
5G. Sankara Rao, Computer Science & Engineering, Gayatri Vidya Parishad College of Engineering for Women, Visakhapatnam, India.
Manuscript received on May 07, 2020. | Revised Manuscript received on May 20, 2020. | Manuscript published on June 10, 2020. | PP: 115-120 | Volume-9 Issue-8, June 2020. | Retrieval Number: 100.1/ijitee.H6264069820 | DOI: 10.35940/ijitee.H6264.069820
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Optical Character Recognition (OCR) is a computer vision technique which recognizes text present in any form of images, such as scanned documents and photos. In recent years, OCR has improved significantly in the precise recognition of text from images. Though there are many existing applications, we plan on exploring the domain of deep learning and build an optical character recognition system using deep learning architectures. In the later stage, this OCR system is developed to form a web application which provides the functionalities. The approach applied to achieve this is to implement a hybrid model containing three components namely, the Convolutional Neural Network component, the Recurrent Neural Network component and the Transcription component which decodes the output from RNN into the corresponding label sequence. The process of solving problems involving text recognition required CNN to extract feature maps from images. These sequence of feature vectors undergo sequence modeling through the RNN component predicting label distributions which are later translated using the Connectionist Temporal Classification technique in the transcription layer. The model implemented acts as the backend of the web application developed using the Flask web framework. The complete application is later containerized into an image using Docker. This helps in easy deployment on the application along with its environment across any system.
Keywords: Artificial Intelligence, Connectionist Temporal Classification (CTC), Convolutional Neural Network (CNN), Flask web framework, Long-Short Term Memory (LSTM), Recurrent Neural Network (RNN).
Scope of the Article: Artificial Intelligence