Abstract
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.
Highlights
Fini Keni Celsia, Green Arther Sandag impaired, and normal people
In this study the researchers made a model in the classification of Sign Language using Convolution Neural Network (CNN) and Artificial Neural Network (ANN)
The results of this study were taken from three stages of 100 epoch each carried out in the train process, where for the first train process got 99% accuracy results, the second train process got 100% accuracy results, and the third train process achieved 99% accuracy results
Summary
Komunikasi merupakan bagian yang penting dari manusia sebagai makhluk sosial. Komunikasi merupakan pertukaran informasi dari satu atau kelompok individu ke individu lainnya [1]. Orang yang normal sampai saat ini membutuhkan penerjemah bahasa isyarat, untuk berkomunikasi dengan para tuna rungu dan tuna wicara. Berdasar penelitian yang dilakukan oleh [10] untuk mengidentifikasi bahasa isyarat menggunakan deep convolutional network pada gambar bahasa isyarat Amerika yang mencakup huruf dan angka dan ditemukan bahwa algoritma DeepCNN yang merupakan salah satu jenis algoritma deep implie Vol 11, No 2, Juli 2021 125. Penelitian yang dilakukan oleh [11] dalam mengenali bahasa isyarat menggunakan deep learning pada gambar bahasa isyarat Amerika yang mencakup 26 huruf dan 10 angka menghasilkan tingkat akurasi sebesar 98.05%. Peneliti menggunakan algoritma CNN dan ANN untuk mengklasifikasi gambar digit dalam Bahasa isyarat, sehingga penelitian ini dapat bermanfaat bagi masyarakat agar bisa berkomunikasi dengan penderita tuna rungu dan tuna wicara tanpa bantuan penerjemah bahasa isyarat
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
