Abstract
OCR is used to recognize written or optical generated text by the computer. Machine learning and artificial intelligence are relying frequently on such automation process with high accuracy. This paper present setting of the threshold value is once for whole bounding box algorithm rather than the random threshold value. Region properties of the image measure in the second and final module of our article. In the proposed approach, the final extraction of optical character is done by removing all the feature vectors having pixels less than 30. This process will subsequently increase the accuracy of recognition and visual effects as well. Old and new data sets are implemented by the proposed algorithm. After that, a comparative analysis was done for both outputs of the proposed algorithm. Proposed algorithm extracts different optical characters at the same time so as to reduce time complexity as well.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chaudhuri A et al (2017) Optical character recognition systems for different languages with soft computing. Stud Fuzziness Soft Comput 352. https://doi.org/10.1007/978-3-319-50252-6_2, Springer International Publishing AG
Cho S-B (1997) Neural-network classifiers for recognizing totally unconstrained handwritten numerals. IEEE Trans Neural Netw 8(1), January 1997
Chaudhuri BB, Pal U, Mitra M Automatic recognition of printed oriya script
Basa D, Meher S (2011) Handwritten Odia character recognition. In: Presented in the national conference on recent advances in microwave tubes, devices and communication systems, Jagannath Gupta Institute of Engineering and Technology, Jaipur, March 4–5 2011.
Plamondon R, Srihari SN (2000) On-line and off-line handwritting character recognition: a comprehensive survey. 1EEE Trans Pattern Anal Mach Intell 22(1)
Vamvakas G, Gatos B, Stamatopoulos N, Perantonis SJ (2016) A complete optical character recognition methodology for historical documents. In: The eighth IAPR workshop on document analysis systems, January 4–5
Vamvakas G, Gatos B, Stathopoulos N, Perantonis SJ (2008) A complete optical character recognition methodology for historical documents. In: The eighth IAPR workshop on document analysis systems
Kimura F, Wakabayashi T, Miyake Y (1996) On feature extraction for limited class problem, August 25–29
Deshmukh S, Ragha L (2009) Analysis of directional features—stroke and contour for handwritten character recognition. In: 2009 ieee international advance computing conference (IACC 2009) Patiala, India, pp 6–7, March 2009
Blumenstein M, Verma BK, Basli H (2003) A novel feature extraction technique for the recognition of segmented handwritten characters In: 7th international conference on document analysis and recognition (ICDAR’03) Edinburgh, Scotland, pp 137–141
Bhowmik T, Parui SK, Bhattacharya U, Shaw B An HMM based recognition scheme for handwritten Oriya numerals
Pai N, Kolkure VS Optical character recognition: an encompassing review. IJRET: Int J Res Eng Technol eISSN: 2319-1163 | pISSN: 2321-7308
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chaturvedi, P., Saxena, M., Sharma, B. (2019). A Bounding Box Approach for Performing Dynamic Optical Character Recognition in MATLAB. In: Rathore, V., Worring, M., Mishra, D., Joshi, A., Maheshwari, S. (eds) Emerging Trends in Expert Applications and Security. Advances in Intelligent Systems and Computing, vol 841. Springer, Singapore. https://doi.org/10.1007/978-981-13-2285-3_15
Download citation
DOI: https://doi.org/10.1007/978-981-13-2285-3_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2284-6
Online ISBN: 978-981-13-2285-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)