mobile camera based text detection
Download as PPTX, PDF4 likes2,364 views
This document presents an introduction to a project on mobile camera based text detection and translation. It discusses existing OCR systems from 1929 to the late 1990s. The proposed system will use a mobile camera to capture images, detect text edges and corners, retrieve text by matching to stored images, translate the text using Google APIs, and display the results. It provides block diagrams of the system workflow and components. It describes the hardware, software, and communication requirements. It discusses testing done on image quality and character recognition rates. Potential applications include assisting tourists and recognizing road signs. Advantages include being Android based and not requiring data entry or databases. Limitations include needing high quality images and internet for translation. The conclusion states this will be a
![Bibliography
1. Michael Hsueh “Interactive Text Recognition and Translation on a Mobile Device “
[Technical Report No. UCB/EECS-2011-57 ]
2. Yassin M.Y.Hasan and Lina J.Karam “Morphological Text Extraction from Images” IEEE
Transaction on Image Processing Vol.9 No.11, Nov 2000
3. Nobuyuki Otsu, A threshold selection method from gray-level histograms. IEEE
Trans.Sys.,Man., Cyber 9(1):62-66
4. Celine Mancas-Thillou, Bernard Gosselin, Color text extraction with selective metric
based clustering. Computer Vision and Image Understanding 2007
5. B. Epshtein, Detecting Text in Natural Scenes with Stroke Width Transform. Image
Rochester NY, pp. 1-8.
6. Derek Ma , Qiuhau Lin, Tong Zhang “Mobile Camera Based Text Detection and
Translation” – research paper
7. WWW.wikipedia.org/optical_character_recognization
16](https://image.slidesharecdn.com/demo1-140211084136-phpapp01/85/mobile-camera-based-text-detection-16-320.jpg)
mobile camera based text detection
- 1. An Introduction demo on Mobile Camera Based Text Detection & Translation Under The Guidance Of: Prof. Shweta Patil. Presented By: Akash Y Shindhe Manjunath N Nayak Sachin B Biradar Vallabh G Potadar
- 2. Contents Introduction History Existing System Proposed System System Flow Requirement Block Diagram Test & Results Applications Advantages & Limitation Conclusion Bibliography 2
- 3. Introduction… Our project ‘Mobile camera based text detection and translation’ retrieves text from an images and converts it into text format, then it is translated to specified language. 3
- 4. Existing System In 1929, first OCR device was invented but it was mechanical device In about 1965, earliest form of OCR was implemented in one of the first generation computers for Airline Ticket stock. Revolutionary in 1971, it was implemented in postal services OCR systems where reading and printing of routing bar code was done on the postal code. In 1974, the modifications was done which would allow blind people to have a computer read text to them out loud. In late 90’s, Webcam was used for OCR process. 4
- 5. Working… Capture image Detect edges Detect corners Match with stored image file Retrieve text from image Translate using Google API Show Result 5
- 6. Working Diagram Fig. a: Working diagram 6
- 7. System flow Algorithms: Edge detection Image feature filtering Image binarization Optical character recognition Text correction Text translation Display of translation 7
- 8. Requirement Mobile Hardware Requirements: • ARM 11 processor or higher • Memory 1 GB • 256 MB RAM • Mobile camera 3.2 mega pixel and above Software Requirements: • Operating System – Android Mob OS 2.2+ • Windows 7 OS • Mat lab OCR,ADT bundles Communication Requirements: • Internet Connection is required • Android Mobile OS inbuilt web browser 8
- 9. Block Diagram Captured Image Text Feature Filtering Match Image File Library Retrieve Text Google APIs Translate Text Display Output Text Fig. b: Block diagram 9
- 10. Example c.1 c.2 c.5 Fig c.1 Fig c.2 Fig c.3 Fig c.4 Fig c.5 c.3 c.4 Fig. c: Example 10
- 11. Test & Results Image quality : As image quality degraded recognition rate will decrease Recognition rate of character ‘A’ , ‘B’ , ‘L’ will be higher than recognition rate of character ‘y’ , ‘u’ , ‘c’. Fig. d: Test & result 11
- 12. Applications Tourist understanding native language. Instant recognition of texts, street and e-mail addresses, links, and telephone numbers. Unknown language guideline. Easy to recognize road signs scripts. 12
- 13. Advantages Android Mobile OS based platform. No tiresome manual data entry. Versatility and ease of use. No database is needed For data entry 13
- 14. Limitations Image taken by Mobile camera should be of good quality. Mobile should be of high specifications For translation of extracted text , Internet connection is required. 14
- 15. Conclusion This project which we want to implement is an Android Mobile OS based application which is web based real time mobile application for real-time text extraction, recognition and translation. 15
- 16. Bibliography 1. Michael Hsueh “Interactive Text Recognition and Translation on a Mobile Device “ [Technical Report No. UCB/EECS-2011-57 ] 2. Yassin M.Y.Hasan and Lina J.Karam “Morphological Text Extraction from Images” IEEE Transaction on Image Processing Vol.9 No.11, Nov 2000 3. Nobuyuki Otsu, A threshold selection method from gray-level histograms. IEEE Trans.Sys.,Man., Cyber 9(1):62-66 4. Celine Mancas-Thillou, Bernard Gosselin, Color text extraction with selective metric based clustering. Computer Vision and Image Understanding 2007 5. B. Epshtein, Detecting Text in Natural Scenes with Stroke Width Transform. Image Rochester NY, pp. 1-8. 6. Derek Ma , Qiuhau Lin, Tong Zhang “Mobile Camera Based Text Detection and Translation” – research paper 7. WWW.wikipedia.org/optical_character_recognization 16