Automatic Gastroscopy Video Quality Assessment

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Automatic Gastroscopy Video Quality Assessment
	Wang S(王帅); Tian DY(田冬英); Cong Y(丛杨); Yang YS(杨云生); Tang YD(唐延东); Zhao HC(赵怀慈)
	2014
会议名称	2014 International Conference on Robotics and Biomimetics (ROBIO 2014)
会议日期	December 5-10, 2014
会议地点	Bali, Indonesia
页码	2709-2714
通讯作者	王帅
中文摘要	Automatic endoscope video analysis is an essential function for medical robot and computer-aided diagnosis system. However, the performance of these video analysis algorithms are often degraded by low quality endoscope images under the uncontrolled environment, where some of them are difficult even for human ourselves for analysis, such as oversaturated by reflection, too dark or obscure. In this paper, we formulate the problem of gastroscopy video quality evaluation as a supervised framework and detect non-informative frames from gastroscopy video sequence. In order to achieve this goal, HSV histograms, pyramid of histograms of orientation gradients and uniform Local Binary Pattern are extracted to represent frames. And then the Random Forests classifier is used to classify non-informative frames. Experimental results in our new gastroscopy video dataset with about 110000 frames demonstrate that the accuracy of our method is about 95% with the false positive rate lower than 1.3%.
收录类别	EI ; CPCI（ISTP）
产权排序	1
会议录	2014 International Conference on Robotics and Biomimetics (ROBIO 2014)
会议录出版者	IEEE
会议录出版地	Piscataway, NJ, USA
语种	英语
ISBN号	978-1-4799-7396-5
WOS记录号	WOS:000380399500455
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/15410]
专题	沈阳自动化研究所_机器人学研究室
推荐引用方式 GB/T 7714	Wang S,Tian DY,Cong Y,et al. Automatic Gastroscopy Video Quality Assessment[C]. 见:2014 International Conference on Robotics and Biomimetics (ROBIO 2014). Bali, Indonesia. December 5-10, 2014.