A Novel Approach for Key Frames Extraction using Automatic Threshold

Abstract

partitioning a video sequence into shots is the first step toward video-content analysis and content-based video browsing and retrieval. A video shot is defined as a series of interrelated consecutive frames taken contiguously by a single camera and representing a continuous action in time and space. As such, shots are considered to be the primitives for higher level content analysis, indexing, and classification. This paper we analyze novel algorithm for shot boundary detection and key frames extraction. The algorithm differs from conventional methods mainly in the use of compression module and automatic threshold. Matching difference between two consecutive frames is computed with different weights. Shot boundaries are detected with automatic threshold. Key frame is extracted by using reference frame-based approach. Algorithm uses histogram-based algorithms for finding out shot boundaries. Histogram-based algorithms are very applicable to SBD. They provide global information about the video content and are faster without any performance degradations.

Keywords: shot boundary detection; automatic threshold; key frame