Laser & Optoelectronics Progress, Volume. 56, Issue 6, 061004(2019)
Key Frame Extraction of Hysteroscopy Videos Based on Image Quality and Attention
In order to solve the problem of low accuracy rate caused by the equal length segmentation of the attention curve in the traditional methods, a scheme is proposed, in which the key video segments are extracted based on the image quality curve. The frame with the highest attention value is selected from each segment as the key frame. On the local database, the precision and F-measure are 52.94% and 62.77%, 5.23% and 2.65% higher than those by the Muhammad method, respectively.
Get Citation
Copy Citation Text
Qiangqiang Miao. Key Frame Extraction of Hysteroscopy Videos Based on Image Quality and Attention[J]. Laser & Optoelectronics Progress, 2019, 56(6): 061004
Category: Image Processing
Received: Sep. 3, 2018
Accepted: Oct. 17, 2018
Published Online: Jul. 30, 2019
The Author Email: Miao Qiangqiang (amiao@whut.edu.cn)