作者：
Xie, BinHe, XiaoyuLi, YiCent S Univ
Sch Informat Sci & Engn Changsha Hunan Peoples R China Cent S Univ
Xiangya Hosp China Mobile Joint Lab Mobile Hlth Minist Educ Changsha Hunan Peoples R China
In the area of human-computer interaction (HCI) and computer vision, gesturerecognition has always been a research hotspot. With the appearance of depth camera, gesturerecognition using rgb-d camera has gradually be...
详细信息
In the area of human-computer interaction (HCI) and computer vision, gesturerecognition has always been a research hotspot. With the appearance of depth camera, gesturerecognition using rgb-d camera has gradually become mainstream in this field. However, how to effectively use depth information to construct a robust gesturerecognition system is still a problem. In this paper, an rgb-d static gesture recognition method based on fine-tuning Inception V3 is proposed, which can eliminate the steps of gesture segmentation and feature extraction in traditional algorithms. Compared with general CNN algorithms, the authors adopt a two-stage training strategy to fine-tune the model. This method sets a feature concatenate layer of rgb anddepth images in the CNN structure, using depth information to promote the performance of gesturerecognition. Finally, on the American Sign Language (ASL) recognitiondataset, the authors compared their method with other traditional machine learning methods, CNN algorithms, and the rgb input only method. Among three groups of comparative experiments, the authors' method reached the highest accuracy of 91.35%, reaching the state-of-the-art currently on ASL dataset.
暂无评论