Devanagari Handwritten Character Recognition using fine-tuned Deep Convolutional Neural Network on trivial dataset
- PDF / 1,230,333 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 29 Downloads / 221 Views
Sådhanå (2020)45:243 https://doi.org/10.1007/s12046-020-01484-1
Sadhana(0123456789().,-volV)FT3](012345 6789().,-volV)
Devanagari Handwritten Character Recognition using fine-tuned Deep Convolutional Neural Network on trivial dataset SHALAKA PRASAD DEORE1,2,* and ALBERT PRAVIN1 1
Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, India 2 Department of Computer Engineering, M.E.S. College of Engineering, Pune, S.P Pune University, Pune, India e-mail: [email protected]; [email protected] MS received 6 December 2019; revised 3 August 2020; accepted 17 August 2020 Abstract. In order to rapidly build an automatic and precise system for image recognition and categorization, deep learning is a vital technology. Handwritten character classification also gaining more attention due to its major contribution in automation and specially to develop applications for helping visually impaired people. Here, the proposed work highlighting on fine-tuning approach and analysis of state-of-the-art Deep Convolutional Neural Network (DCNN) designed for Devanagari Handwritten characters classification. A new Devanagari handwritten characters dataset is generated which is publicly available. Datasets consist of total 5800 isolated images of 58 unique character classes: 12 vowels, 36 consonants and 10 numerals. In addition to this database, a two-stage VGG16 deep learning model is implemented to recognize those characters using two advanced adaptive gradient methods. A two-stage approach of deep learning is developed to enhance overall success of the proposed Devanagari Handwritten Character Recognition System (DHCRS). The first model achieves 94.84% testing accuracy with training loss of 0.18 on new dataset. Moreover, the second fine-tuned model requires very fewer trainable parameters and notably less training time to achieve state-of-the-art performance on a very small dataset. It achieves 96.55% testing accuracy with training loss of 0.12. We also tested the proposed model on four different benchmark datasets of isolated characters as well as digits of Indic scripts. For all the datasets tested, we achieved the promising results. Keywords. Deep learning; Deep Convolutional Neural Network; VGG16; bottleneck features; fine-tuned; computing time.
1. Introduction Pattern identification is a perpetual area of specialization in the context of artificial intelligence, computer vision and machine learning [1]. Optical Character Recognition (OCR) is one of the leading dynamic applications of an image classification and gaining additional interest due to its numerous applications. The applications include automatic postal card sorting [2, 3], digital signature verification [4], automatic processing of bank cheques [5], processing of historical documents [6] and automatic handwritten text detection in classroom teaching [7]. So there is a prodigious need of OCR in the area of pattern identification. OCR method is used to recognise handwritten, printed or typed text by using its sca
Data Loading...
