Hbr - Case Study Analyais

...

follows:

Table 1: Average Recognition results

Language

English

Hindi

Avg. Mean Confidence per word

69

24

Avg. Time taken per word

153ms

681ms

Light and Noise susceptibility

LOW

HIGH

Average Accuracy

97.9%

79.2%

- Conclusion

This paper tells about OCR system for Signboard character recognition. The systems have the ability to yield excellent results.The character extraction step of optical character recognition is the most important one. This system offers an upper edge by having an advantage i.e. its scalability, i.e. although it is configured to read a predefined set of formats, currently English and Hindi, it can be configured to recognize new language formats.It also translates the captured text to languages viz English,Hindi,French and German.One can directly get the additional information about the captured text via the application.

Future research aims at new applications such as extraction of text from video images.

ACKNOWLEDGMENT

The authors would like to thank Department of Computer Engineering, and indebted to our guide Prof. Mansi Kambli for her guidance and sagacity without which this paper would not have been designed. She provided us with valuable advice which helped us to accomplish the design of this paper. Also we would like to appreciate the support and encouragement of our colleagues who helped us in correcting our mistakes and proceeding further to produce the paper with the required standards.

References

- Bansal, V. and Sinha, R.M.K. “A Complete OCR for Printed Hindi Text in Devanagari Script”, Sixth International Conference on Document Analysis and Recognition, IEEE Publication, Seatle USA, 2001, Page(s):800-804.

- Pal, U., Chaudhuri, B. B. ''Indian Script Character recognition: A survey'', Pattern Recognition, vol. 37, pp. 1887-1899, 2004.

- Saba, T., Sulong, G. and Rehman, A. “A Survey on Methods and Strategies on Touched Characters Segmentation”, International Journal of Research and Reviews in Computer Science (IJRRCS) Vol. 1, No. 2, June 2010.

- Tesseract-OCR An OCR Engine that was developed at HP Labs between 1985 and 1995... and now at Google. Available at: http://code.google.com/p/tesseract- ocr/wiki/TrainingTesseract3

- Download the Android SDK. Available at: http://developer.android.com/sdk/

- Android Developers Homepage. Available at: http://developer.android.com/index.html

- Eclipse IDE for JAVA Developers. Available at: http://eclipse.org/downloads/packages/eclipse-ide-java- developers/galileosr2

- Open source Tesseract OCR Engine, available at http://code.google.com/p/tesseract-ocr/

- Simple Android Photo Capture. Available at: http://labs.makemachine.net/2010/03/simple-android- photo-capture/