author = "Cardenas, Edwin Jonathan Escobedo and Ch{\'a}vez, Guillermo 
          affiliation = "{Federal University of Ouro Preto} and {Federal University of Ouro 
                title = "Finger Spelling Recognition from Depth data using Direction 
                         Cosines and Histogram of Cumulative Magnitudes",
            booktitle = "Proceedings...",
                 year = "2015",
               editor = "Papa, Jo{\~a}o Paulo and Sander, Pedro Vieira and Marroquim, 
                         Ricardo Guerra and Farrell, Ryan",
         organization = "Conference on Graphics, Patterns and Images, 28. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "Finger spelling recognition, depth information, points cloud, 
                         directional cosines, support vector machine (SVM).",
             abstract = "In this paper, we propose a new approach for finger spelling 
                         recognition using depth information captured by Kinect sensor. We 
                         only use depth information to characterize hand configurations 
                         corresponding to alphabet letters. First, we use depth data to 
                         generate a binary hand mask which is used to segment the hand area 
                         from background. Then, the major hand axis is determined and 
                         aligned with Y axis in order to achieve rotation invariance. 
                         Later, we convert the depth data in a 3D point cloud. The point 
                         cloud is divided into subregions and in each one, using direction 
                         cosines, we calculated three histograms of cumulative magnitudes 
                         Hx, Hy and Hz corresponding to each axis. Finally, these 
                         histograms were concatenated and used as input to our Support 
                         Vector Machine (SVM) classifier. The performance of this approach 
                         is quantitatively and qualitatively evaluated on a dataset of real 
                         images of American Sign Language (ASL) hand shapes. The dataset 
                         used is composed of 60000 depth images. According to our 
                         experiments, our approach has an accuracy rate of 99.37%, 
                         outperforming other state-of-the-art methods.",
  conference-location = "Salvador",
      conference-year = "Aug. 26-29, 2015",
             language = "en",
           targetfile = "PID3771875.pdf",
        urlaccessdate = "2021, Dec. 03"