Abstract
Non-uniformity is a common phenomenon in infrared imaging system, which seriously affects imaging quality. In view of the problems of existing non-uniformity correction of infrared images, such as loss of image details and blurred edge of image, an improved non-uniformity correction method of infrared images based on convolution neural network using long-short connections (LSC-CNN) is proposed. The proposed method designs a long-short connection residual network structure suitable for non-uniformity correction of infrared image.The network depth is increased to fully learn the noise by short connections, image sizes are adjusted to reduce the number of parameters, the long connection is used to solve the problem of image information loss caused by transposed convolution, and a multiply operation is carried out to enhance the contrast of corrected images. Besides, batch normalization is utilized to improve the training speed. The experimental results show that LSC-CNN has excellent performance in non-uniformity correction of infrared images whether qualitative evaluation or quantitative evaluation. LSC-CNN is especially effective in image detail preservation and image edge protection whose average PSNR exceeds 37.5 dB and the average SSIM is greater than 0.98.
Highlights
The non-uniformity in the infrared imaging systems seriously affects the imaging quality, which is mainly manifested as fixed-pattern noise (FPN)
The non-uniformity correction of infrared image is the key to improve the quality of infrared image, and the research focus of infrared image processing
An improved non-uniformity correction method of infrared images based on convolution neural network using long-short connections, LSC-CNN, is proposed, which uses a residual network and introduces short connect into the infrared image non-uniformity correction
Summary
The non-uniformity in the infrared imaging systems seriously affects the imaging quality, which is mainly manifested as fixed-pattern noise (FPN). The non-uniformity correction of infrared image is the key to improve the quality of infrared image, and the research focus of infrared image processing. Infrared images have less detail information than visible images, so the image quality will be seriously affected if the noise removals are not enough. To resolve these issues, this paper applies deep-learning to non-uniformity correction of infrared image, establishes a noise simulation model, learns the noise characteristics of infrared images, and separates the noise in the input noisy image. Compared with the existing non-uniformity correction methods, the proposed method achieves excellent performance and is especially effective in image detail preservation and image edge protection
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.
