Efficient visual attention driven framework for key frames extraction from hysteroscopy videos. (March 2017)

• Record Type: Journal Article
• Authors: Muhammad, Khan; Sajjad, Muhammad; Lee, Mi Young; Baik, Sung Wook
• Is Part Of: Biomedical signal processing and control. Volume 33(2017)
• Page Start: 161
• Page End: 168
• Publication Date: 2017-03
• Subjects: Video summarization -- Diagnostic hysteroscopy -- Visual saliency -- Visual attention model -- Gynecology -- Medical image analysis; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2016.11.011
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: An efficient video summarization framework for keyframes extraction from hysteroscopy videos. Reduction in computational complexity using summed-area tables for summary generation. Extraction of more relevant keyframes and generating summaries of gynecologists' interests. Abstract: Recent years have shown enthusiastic research interests in diagnostic hysteroscopy (DH), where various regions of the female reproductive system are visualized for diagnosing uterine disorders. Currently, the hysteroscopy videos produced during various sessions of patients are stored in medical libraries, which are usually browsed by medical specialists Gynecologists to visualize previous videos of a patient or to study similar cases. However, the abundant redundancy of frames in DH videos make this searching relatively more difficult for gynecologists, wasting their time browsing such large libraries. In this context, video summarization can be used to reduce this redundancy by extracting key frames, thus making the process of browsing and indexing DH videos more efficient. In this letter, we propose an efficient domain-specific visual attention-driven framework for summarizing DH videos. For key frames extraction, multi-scale contrast, texture, curvature, and motion based saliency features are computed for each frame using integral image, which are then fused by a linear weighted fusion scheme to acquire a final saliency map. Experimental results in comparison with other related state-of-the-art schemes confirm the effectiveness and efficiency of the proposed framework.