Departmental Bulletin Paper Deep Convolutional Neural Networksによる授業集中度評価システムの構築

吉橋, 亮佑

562015-03-24 , 法政大学大学院理工学・工学研究科
In this paper, we developed an estimation system for degree of audience’s concentration by estimating individual’s behavior with a deep learning approach. Our system firstly detects candidate location of audiences (CLAs) from the movie with AdaBoost classifier composed of Haar-like filters and their integration process. Each CLA is then investigated to determine the target audience is “concentrated”, “not concentrated” or “no exist” with 5-layered deep convolutional neural networks (DCNN). We used a total of 13 movies of which 3 movies were used for training of DCNN and the remains for the evaluation. Our system achieved audience detection performance of precision = 84.8% and recall = 61.8% and estimation accuracy of individual attention as 72.8%.

Number of accesses :  

Other information