Fusion of Zero-Normalized Pixel Correlation Coefficient and Higher-Order Color Moments for Keyframe Extraction
Keyframe extraction of videos is useful in many application areas such as video copy detection, retrieval, indexing, summarization. In this paper, we propose a novel shot-based keyframe extraction algorithm. The proposed algorithm is capable of detecting both shots and keyframes of any video efficiently. For extraction of keyframes, frames of video are clustered into shot transitions. These shot transitions of the video are obtained using higher-order color moments and zero-normalized pixel correlation coefficients. In each shot, all the frames are scanned to detect frame with highest standard deviation in that particular shot and chosen as keyframe to that shot. The proposed method is tested on videos of personal interviews with luminaries. Performance of the proposed method is evaluated on the basis of five parameters—recall, figure of merit, detection percentage, accuracy and missing factor. The proposed method is able to detect both abrupt and gradual shot transitions with comparatively less computational complexity. The exhaustive analysis of results shows the sound performance of the proposed method over the methods used in this study.
KeywordsZero-normalized pixel correlation coefficient Color moments Shot detection Cut shot transition Gradual shot transition Keyframe extraction
- 3.Birinci, M., Kiranyaz, S. (2014). A perceptual scheme for fully automatic video shot boundary detection. 29(3), 410–423.Google Scholar
- 7.Loukas, C., Nikiteas, N., Schizas, D., Georgiou, E. (2016). Shot boundary detection in endoscopic surgery videos using a variational Bayesian framework. 11(11), 1937–1949.Google Scholar
- 9.Jadhava, P. S., & Jadhav, D. S. (2015). Video summarization using higher order color moments. In Proceedings of the International Conference on Advanced Computing Technologies and Applications (ICACTA) (Vol. 45, pp. 275–281).Google Scholar
- 10.Sheena, C. V., Narayanan, N. K. (2015). Key-frame extraction by analysis of histograms of video keyframes using statistical methods, In Proceedings of the 4th International Conference on Eco-friendly Computing and Communication Systems (Vol. 70, pp. 36–40).Google Scholar
- 12.Hannane, R., Elboushaki, A., Afdel, K., Naghabhushan, P., Javed, M. (2016). An efficient method for video shot boundary detection and keyframe extraction using SIFT-point distribution histogram. International Journal of Multimedia Information Retrieval. 10.1007%2Fs13735-016-0095-6.Google Scholar
- 13.Thakre, K. S., Rajurkar, A. M., Manthalkar, R. R. (2015). Video partitioning and secured keyframe extraction of MPEG video. In Proceedings of the International Conference on Information Security & Privacy (ICISP2015), Nagpur, India, Procedia Computer Science, (Vol. 45, pp. 275–281).Google Scholar
- 15.Lee. Virtual Dub home page. http://www.virtualdub.org/index.html.
- 16.Poornima, K., & Kanchana, R. (2012). A method to align images using image segmentation. International Journal of Soft Computing and Engineering, 2(1), 294–298.Google Scholar