Patent attributes
A smart marking system for a surgical video and a method thereof are disclosed. The image recognition is performed for each surgical video to generate object information corresponding to each surgical video. The object information is used as feature data of the surgical video corresponding thereto. After a video to be analyzed is loaded, eigenvalue analysis and statistics are performed according to the video to be analyzed and all the feature data to calculate a similarity rate between the video to be analyzed and each surgical video. A surgical name corresponding to the surgical video with the highest similarity rate is selected to mark as a surgical name corresponding to the video to be analyzed. The video to be analyzed and the surgical name corresponding thereto are stored in a database as the surgical video. Thus, the efficiency of marking the surgical videos is improved.
