1 May 2017 Intelligent multi-spectral IR image segmentation
Author Affiliations +
This article presents a neural network based multi-spectral image segmentation method. A neural network is trained on the selected features of both the objects and background in the longwave (LW) Infrared (IR) images. Multiple iterations of training are performed until the accuracy of the segmentation reaches satisfactory level. The segmentation boundary of the LW image is used to segment the midwave (MW) and shortwave (SW) IR images. A second neural network detects the local discontinuities and refines the accuracy of the local boundaries. This article compares the neural network based segmentation method to the Wavelet-threshold and Grab-Cut methods. Test results have shown increased accuracy and robustness of this segmentation scheme for multi-spectral IR images.
Conference Presentation
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Thomas Lu, Thomas Lu, Andrew Luong, Andrew Luong, Stephen Heim, Stephen Heim, Maharshi Patel, Maharshi Patel, Kang Chen, Kang Chen, Tien-Hsin Chao, Tien-Hsin Chao, Edward Chow, Edward Chow, Gilbert Torres, Gilbert Torres, "Intelligent multi-spectral IR image segmentation", Proc. SPIE 10203, Pattern Recognition and Tracking XXVIII, 1020303 (1 May 2017); doi: 10.1117/12.2262730; https://doi.org/10.1117/12.2262730

Back to Top