Key-frame Extraction Using Threshold Technique

Triggered by technological innovation, there has been an enormous increase in the utilization of video for many significant applications. Video will be one of the key issues in the upcoming information technology and education. To increase the effectiveness of their content on the web and create new revenue stream, future content owners, publishers and educators will need to deliver video to users in ways that exploit proven economic models for the web and confirm to the demand both qualitative and quantitative of forthcoming internet usage patterns. To extract valid information from video, process video data efficiently, and reduce the transfer stress of network, more and more attention is being paid to the video processing technology. The amount of data in video processing is significantly reduced by using video segmentation and key-frame extraction. So, these two technologies have gradually become focus of research. This paper presents the method of selecting effective key-frames for video browsing where the new strategy is to extract most characteristic frame. The methodology applied here extracts the key frames using a Threshold Technique where the calculated threshold is brought out in comparison with the Difference Histogram of the Images. Experimental results show that the extracted key-frames can summarize the salient features and characteristics of the video maintaining the integrity of the information contained in that video. The method is highly feasible with high efficiency and