Implementation of Deep Learning on Number Recognition in Sign Language

Measuring the wound area in diabetics is still using a manual way with a wound ruler. Whereas the ruler affixed to the wound will become a contaminated agent that can transmit the infection to other recipients. Digital measurement methods are needed to solve the problem. However, clarifying the boundaries between the wound and the skin requires carefulness and high accuracy. For this reason, it has needed an imaging method that can do segmentation between the wound and the skin boundary for diabetic patients based on digital, called digital planimetry. This study uses a masking contour image processing algorithm from the Hue, Saturation, Value (HSV), Then doing iteration five times and gamma filter. So the result of segmentation is formed. This study concludes that the segmentation with this method has not been able to perform the segment properly, and it requires more masking values, but the results of the 5th iteration got a minor error, which is 0.002%. The digital imaging carried out in this study could be developed to be a digital-based diabetic patient wound measurement tool.

[1]  Dianna Radpour,et al.  Using Deep Convolutional Networks for Gesture Recognition in American Sign Language , 2017, ArXiv.

[2]  Ao Tang,et al.  A Real-Time Hand Posture Recognition System Using Deep Neural Networks , 2015, ACM Trans. Intell. Syst. Technol..

[3]  Ying Xie,et al.  American Sign Language Recognition using Deep Learning and Computer Vision , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[4]  Nihan Kahraman,et al.  A Real-Time System for Recognition of American Sign Language by using Deep Learning , 2018, 2018 41st International Conference on Telecommunications and Signal Processing (TSP).

[5]  Karel Fliegel,et al.  On the accuracy of objective image and video quality models: New methodology for performance evaluation , 2016, 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX).

[6]  Ming C. Leu,et al.  American Sign Language word recognition with a sensory glove using artificial neural networks , 2011, Eng. Appl. Artif. Intell..

[7]  Gui-Bin Bian,et al.  Performance Analysis of Google Colaboratory as a Tool for Accelerating Deep Learning Applications , 2018, IEEE Access.

[8]  Shaikh Anowarul Fattah,et al.  Real-Time American Sign Language Recognition Using Skin Segmentation and Image Category Classification with Convolutional Neural Network and Deep Learning , 2018, TENCON 2018 - 2018 IEEE Region 10 Conference.

[9]  Jungpil Shin,et al.  Hand Gesture Feature Extraction Using Deep Convolutional Neural Network for Recognizing American Sign Language , 2018, 2018 4th International Conference on Frontiers of Signal Processing (ICFSP).

[10]  Lihong Zheng,et al.  Recent Advances of Deep Learning for Sign Language Recognition , 2017, 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[11]  O. Kembuan,et al.  Convolutional Neural Network (CNN) for Image Classification of Indonesia Sign Language Using Tensorflow , 2020, 2020 2nd International Conference on Cybernetics and Intelligent System (ICORIS).

[12]  Dhananjay Kalbande,et al.  Sign Language Recognition Using Deep Learning on Custom Processed Static Gesture Images , 2018, 2018 International Conference on Smart City and Emerging Technology (ICSCET).

[13]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[14]  P. V. V. Kishore,et al.  Deep convolutional neural networks for sign language recognition , 2018, 2018 Conference on Signal Processing And Communication Engineering Systems (SPACES).

[15]  Vassilis Athitsos,et al.  Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition , 2016, PETRA.

[16]  Benjamin Schrauwen,et al.  Sign Language Recognition Using Convolutional Neural Networks , 2014, ECCV Workshops.