Image fusion method and image processing apparatus

摘要

An image fusion method and an image processing apparatus are provided. A first image is generated based on a first photographing parameter, and a second image is generated based on a second photographing parameter. A first pixel reference value of each of first pixels is calculated by using a self-define mask according to color components and a luminance component of the first pixels on the first image. A second pixel reference value of each of second pixels is calculated by using the self-define mask according to color components and a luminance component of the second pixels on the second image. A synthesizing reference map recording a plurality of synthesizing weights is obtained by comparing the first pixel reference value and the corresponding second pixel reference value. A fusion image is obtained by synthesizing the first image and the second image according to the synthesizing reference map.

主权项

1. An image fusion method, for an image processing apparatus, comprising:
obtaining a first image and a second image associated with the same scene, wherein the first image is generated based on a first photographing parameter, and the second image is generated based on a second photographing parameter; calculating a first pixel reference value of each of a plurality of first pixels by using a self-define mask according to color components and a luminance component of each of the first pixels on the first image, and calculating a second pixel reference value of each of a plurality of second pixels by using the self-define mask according to color components and a luminance component of each of the second pixels on the second image; comparing the first pixel reference value of each of the first pixels with the second pixel reference value of each of the corresponding second pixels to obtain a plurality of synthesizing weights respectively associated with a plurality of pixel positions, and recording the synthesizing weights respectively associated with the pixel positions into a synthesizing reference map; and obtaining a fusion image by synthesizing the first image and the second image according to the synthesizing reference map, the first pixels and the second pixels, wherein the step of calculating the first pixel reference value of each of the first pixels by using the self-define mask according to the color components and the luminance component of each of the first pixels on the first image comprises: calculating a color saturation of each of the first pixels by using a first color component and a second color component of each of the first pixels, and using the luminance component of each of the first pixels as a luminance of each of the first pixels; dividing the color saturation of each of the first pixels by the luminance to obtain a first saturation-luminance ratio value of each of the first pixels; and calculating the first pixel reference value of each of the first pixels by using the self-define mask and the first saturation-luminance ratio value of each of the first pixels.