Extracting text form video_using_matlab

18
EXTRACTION OF TEXT FROM VIDEO USING MATLAB Presented By: P.Likhitha Under the esteemed supervision of M.Naresh Babu,M.Tech; Assistant Professor Department of ECE SREE VIDYANIKETHAN ENGINEERING COLLEGE (AUTONOMOUS) Sri Sainathnagar, A.Rangampet, Tirupathi-5171

Transcript of Extracting text form video_using_matlab

Page 1: Extracting text form video_using_matlab

EXTRACTION OF TEXT FROM VIDEO USING MATLAB

Presented By:P.Likhitha

Under the esteemed supervision ofM.Naresh Babu,M.Tech;Assistant ProfessorDepartment of ECE

SREE VIDYANIKETHAN ENGINEERING COLLEGE (AUTONOMOUS)

Sri Sainathnagar, A.Rangampet, Tirupathi-517102

Page 2: Extracting text form video_using_matlab

CONTENTS:

Introduction Text Extraction Process of Extraction Algorithm Flowchart Advantages Disadvantages Applications Conclusion

Page 3: Extracting text form video_using_matlab

INTRODUCTION As computer, compress technology, storage media and high speed

communication skill are developed dramatically; digital video has become one of the most important elements in many applications such as education, news and games.

Text is obviously an important element in video. So extracting text appears as a key clue for understanding contents of video and for instance for classifying automatically some videos.

Videotext detection and recognition has been identified as one of the key components for the video retrieval and analysis system.

Videotext detection and recognition can be used in many applications, such as semantic video indexing, summarization, video surveillance and security, multilingual video information access, etc.

Page 4: Extracting text form video_using_matlab

EXTRACTING TEXT FROM VIDEO

PreProcessing

HELLO

HELLO

HELLO

Page 5: Extracting text form video_using_matlab

TEXT EXTRACTION

Text Extraction is a process by which we convert Printed document/Scanned Page or Image in which text are available to ASCII Character that a Computer can Recognize.

GENERAL APTITUDEComputer ScienceElectronics & Communication Engineering

Page 6: Extracting text form video_using_matlab

PROCESS OF TEXT EXTRACTION:

1Preprocessing

3Recognitio

n

2Segmentation

Page 7: Extracting text form video_using_matlab

GRAY SCALE NOISE REMOVAL THRESHOLDING

PREPROCESSING

Page 8: Extracting text form video_using_matlab

PREPROCESSING:

Gray Scale

•Noise Removal is used to Enhance the Image•For Enhancing We have used Median Filter•FilteredImage = Median Filter(Origional Image, FilterSize)•We have used FilterSize [5,5]

Noise Removal

•Edge Detection•Dilate Image•Detect Text Area Using Histrogram•Personal Thresholding to Text Area

Thresholding

1 2 3

Page 9: Extracting text form video_using_matlab

SEGMENTATION

Segmentation means fragmenting.Here the fragmenting is according to the line to word,word to character.

Page 10: Extracting text form video_using_matlab

RECOGNITION In Recognition mainly it includes: Feature Extraction

Classifier Text

Document

Page 11: Extracting text form video_using_matlab

EDGING

Page 12: Extracting text form video_using_matlab

ALGORITHM

  Take the frame RGB to Gray image defining the angles Edge detection Defining thresholds for vertical and horizontal text segmentation X and Y projection using threshold Binarization

Page 13: Extracting text form video_using_matlab

FLOWCHART

Page 14: Extracting text form video_using_matlab

ADVANTAGES:

Cheaper

Page 15: Extracting text form video_using_matlab

DISADVANTAGES:

Background and text may be ambiguous. Text color may change: text can have arbitrary and non-uniform color. Background and text are sometimes reversed. Text may move. Unknown text size, position, orientation, and layout: captions lack the structure usually associated with documents. Unconstrained background: the background can have colors similar to the text colour. The background may include streaks that appear very similar to character strokes. Low contrast: low bit-rate video compression can cause loss of contrast between character strokes and the background

Page 16: Extracting text form video_using_matlab

APPLICATIONS:

Banking (To read Credit Card) Libraries (To convert Scanned Page to Image) Govt. Sector (Form Processing) Used in Car Number Plate Recognition System Undesirable Text removal from images.

Page 17: Extracting text form video_using_matlab

FUTURE SCOPE:

Future Scope We have implemented the project considering English language; it can be further extended to other languages. If enlarged in future implementations, it will largely improve the efficiency of the algorithm.

Page 18: Extracting text form video_using_matlab

REFERENCES

1. OCR for Devnagari Script by Mahesh Goyani2. Edge Based Text Extraction From Complex Images by Xiaoqing Liu and

Jagath Samarbandhu3. Automatic Text Detection using Morphological Operations and

Inpainting by Khyati Vaghela4. Font and Background Color Independent Text Binarization by T.Kasar ,

J.Kumar , A.G. Ramkrishnan