Method for fusing multi-focus images in anti-noise environment

Abstract

The invention discloses a method for fusing multi-focus images in an anti-noise environment, which can be used for fusing the multi-focus images, has noise resisting capacity, and can be applied to a common optical system. The method particularly comprises the following steps of: (1) performing Laplacian pyramid decomposition on a source image; (2) performing iterated operation on a decomposed sub-band coefficient by a pulse coupling neural network to obtain a corresponding ignition frequency matrix; (3) performing judgment operation by a judgment operator operational unit to acquire a fusion coefficient; and (4) performing LP inverse transformation on the fusion coefficient by adopting a pseudo-inverse reconstruction method to acquire the final fusion image. The method has the capacity of resisting additive noises and JPEG compression system noises, has a high objective evaluating indicator for the fusion image, and effectively weakens 'false Gibss' phenomena at the edge of the fusion image of the conventional LP method; in addition, the method has high adaptability, is convenient for calculation and is favorable for hardware implementation.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an image fusion method, which can be used to fuse multi-focus images, has anti-noise ability, and can be applied to common optical systems. Background technique [0002] Multi-focus image fusion technology can fuse redundant information and complementary information from multiple images with different focuses of the same scene through a certain method to obtain a comprehensive image and obtain a panoramic and clear scene description. The transformation domain fusion method in the multi-focus image fusion technology has been widely used. [0003] The "Face Image Fusion Method Based on Laplace Pyramid Transformation" (CN101226635) patent technology announced by the State Intellectual Property Office of China discloses a method for fusion of face images based on pyramid transformation. The method includes the following steps: 1) Laplacian pyramid decomposition is per...

AI Technical Summary

Problems solved by technology

This method has high quality of fused images and low computational complexity, but there are still the following deficiencies: 1) For infrared and visible light face images, the influence of noise environment and JPEG compression environment on the fusion quality is not considered; 2) In the construction of image The process of pyramidal data structure requires downsampling operation, which will introduce "artificial" effects (such as the pseudo "Gibss" phenomenon at the edge of the reconstructed image) at the edge of the fused image, which hinders the popularization and application of this method

This method introduces the multi-scale geometric analysis tool non-sampling Contourlet transform, which overcomes the shortcomings of wavelet transform that cannot sparsely represent two-dimensional images, but there are still the following shortcomings: 1) The decomposition coefficients are highly redundant; 2) The low-frequency and high-frequency coefficients are separated Using fusion rules based on direction characteristics has high computational complexity, which limits its popularization and application in ordinary optical systems; 3) The influence of noise environment and JPEG compression environment on image fusion quality is not considered

Images