Now a days digital video is very popular as an exchange medium
due to large improvement in video recording and compression techniques and
increasing of network-speed. Therefore audiovisual recordings are used more frequently
in e-learning and e-lecturing systems. OCR from videography is a technique that
can locate any text inside a digital video file via reading and automatic extraction of any notes and captions
that gives the actual information (like – the names of people, places or
description of objects etc.) about the video being presented. Detecting the video-content
requires many technologies: image detection, language processing, search
strategies, video segmentation and filtration etc. Reading the extracted notes
and captions gives more appropriate information to understand the video-content.
Applying OCR on video and combining the results with various detecting techniques
can improve the detection result. Although integrated character recognition in
text-based videos is greatly needed.
Automatic character segmentation was performed
for titles and credits in motion picture videos in however;
papers have insufficient consideration of character
recognition. There are similar research fields which concern
character recognition of videos. In character extraction from
the car license plate using video images is presented and
characters in scene images are segmented and recognized
based adaptive thresholding. While these results are related,
character recognition for the video presents its own
difficulties because of different conditions of title character
size and complex backgrounds. In video caption resolution
of character is lower; also, the background complexity is
more severe than in other research. The first problem is low
resolution of the characters. The size of an image is limited
by title number of scan lines defined in the NTSC standard
a character of the video caption are small to avoid
of interesting objects such as people’s faces. Therefore, the
resolution of characters in the video caption is insufficient
to implement stable and robust Video OCR systems.
Another problem is the existence of complex backgrounds.
Characters superimposed on videos often have hue and
brightness similar to the background, making extraction
extremely difficult. These problems in video OCR have
opened an area for research.
Video OCR is a technique that can greatly help to locate
topics of interest in a large digital video via the automatic
extraction and reading of captions and annotations. Video
OCR process and all the process modules required in video
OCR are explained in section III. Applications of video
OCR are explained in section IV. Conclusion based on
relative work is explained in chapter V.