Infrared image enhancement algorithm based on improved wavelet threshold function and weighted guided filtering

Abstract Aiming at the problems such as poor visual effect of infrared thermal imaging under low illumination conditions, an enhanced image recognition method based on wavelet decomposition is proposed for this paper. First, according to decomposition, divided into a low-frequency sub-band (LFS) and high-frequency (HFS) in each orientation, HFS orientation denoised using modified threshold function strengthen denoising image; Second, multi-scale Retinex (MSR) algorithm weighted guided filtering (WGIF) used evaluate component basic layer LFS, WGIF-segmented detail images are fused with MSR processed ones effectively highlight texture details LFS; Finally, LFS wavelets reconstructed (WR) obtain images. This paper applies low-resolution (resolution 32x32 pixels) module, results combining subjective objective evaluation indexes show that overall property index superior other contrasting algorithms can improve quality.