32
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      RGB-D static gesture recognition based on convolutional neural network

      research-article
      1 , 2 , 1 , 2 , 1 , 2 ,
      The Journal of Engineering
      The Institution of Engineering and Technology
      The 2nd 2018 Asian Conference on Artificial Intelligence Technology (ACAIT 2018) (ACAIT)
      8–10 June 2018
      human computer interaction, feature extraction, gesture recognition, learning (artificial intelligence), neural nets, computer vision, image segmentation, image colour analysis, convolutional neural network, computer vision, depth camera, RGB-D camera, depth information, robust gesture recognition system, RGB-D static gesture recognition method, gesture segmentation, feature extraction, depth images, American Sign Language Recognition dataset, RGB input, traditional machine learning methods, ASL recognition dataset, CNN algorithms, RGB input only method, fine-tuning Inception V3, CNN structure

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          In the area of human–computer interaction (HCI) and computer vision, gesture recognition has always been a research hotspot. With the appearance of depth camera, gesture recognition using RGB-D camera has gradually become mainstream in this field. However, how to effectively use depth information to construct a robust gesture recognition 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 and depth images in the CNN structure, using depth information to promote the performance of gesture recognition. Finally, on the American Sign Language (ASL) Recognition dataset, 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.

          Most cited references8

          • Record: found
          • Abstract: not found
          • Article: not found

          Recent methods and databases in vision-based hand gesture recognition: A review

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Very deep convolutional networks for large-scale image recognition[J]

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Deep attention network for joint hand gesture localization and recognition using static RGB-D images

                Bookmark

                Author and article information

                Contributors
                Conference
                JOE
                The Journal of Engineering
                J. Eng.
                The Institution of Engineering and Technology
                2051-3305
                16 August 2018
                2 October 2018
                November 2018
                : 2018
                : 16
                : 1515-1520
                Affiliations
                [1 ] School of Information Science and Engineering, Central South University , Changsha, People's Republic of China
                [2 ] Mobile Health Ministry of Education, China Mobile Joint Laboratory, Xiangya Hospital Central South University , Changsha, People's Republic of China
                Article
                JOE.2018.8327 JOE.2018.8327.R1
                10.1049/joe.2018.8327
                28d217e5-ed61-4587-b332-03c42c7524cc

                This is an open access article published by the IET under the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/3.0/)

                The 2nd 2018 Asian Conference on Artificial Intelligence Technology (ACAIT 2018)
                ACAIT
                2
                Chongqing University of Technology, China
                8–10 June 2018
                History
                : 19 July 2018
                : 4 August 2018
                : 6 August 2018
                Page count
                Pages: 0
                Categories
                ee-cer
                cn-ait-2018
                The 2nd 2018 Asian Conference on Artificial Intelligence Technology (ACAIT 2018)

                Software engineering,Data structures & Algorithms,Robotics,Networking & Internet architecture,Artificial intelligence,Human-computer-interaction
                computer vision,image segmentation,human computer interaction,feature extraction,gesture recognition,learning (artificial intelligence),neural nets,image colour analysis,convolutional neural network,depth camera,RGB-D camera,depth information,robust gesture recognition system,RGB-D static gesture recognition method,gesture segmentation,depth images,American Sign Language Recognition dataset,RGB input,traditional machine learning methods,ASL recognition dataset,CNN algorithms,RGB input only method,fine-tuning Inception V3,CNN structure

                Comments

                Comment on this article