Open AccessAn improved Performance of Segmentation Evaluation Based on Feature Extraction using Kinect Sensors
Author(s) -
Mahmood H. Enad,
Mohanad Aljanabi,
Haider K. Latif,
Jameel Kaduim Abed
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/745/1/012047
Subject(s) - artificial intelligence , rgb color model , computer vision , computer science , segmentation , feature (linguistics) , feature extraction , image segmentation , filter (signal processing) , philosophy , linguistics
Kinect sensor suggestions new viewpoints for the advance and application of inexpensive, portable and easy-to-use indication less motion capture skill. The goal of this work is to estimate accuracy of the Kinect cameras for full body motion investigation. This study developed an application that of using multiple depth and RGB Kinect sensors for that reasonable system that prepared with multi-depth of sensing was used in this work. Additional application confirmed the Kinect camera validity the evaluated of postural control and different images of biomedical for segmentation skin lesions. In this work, multi-depth assessment and segmentation are conjointly addressed using RGB input image under Median filter with post-processing. Compared with our algorithm outputs an organized-to-use highly suitable for creating 3D Kinect sensors with pre and post-processing steps. The multi-depth extracted image features have higher measurement and accuracy. The results are dealing out the depth and RGB picture with segmentation evaluation depend on feature extraction technique to enhance accuracy.