Multi-focus image fusion method based on improved sml and guided filter
A multi-focus image, guided filtering technology, applied in the field of image processing, can solve problems such as loss of source image information, and achieve the effects of good consistency, fast calculation speed, and accurate detection results
Active Publication Date: 2019-09-10
WUHAN FENJIN INTELLIGENT MACHINE CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present invention is to solve the source image information loss problem existing in the existing multi-focus image fusion method, and provides a fast multi-focus image fusion method based on improved SML (Sum of Modified Laplacian, SML) and guided filtering , while improving the fusion image quality
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0043] Such as figure 1 As shown, the specific implementation of the fast multi-focus image fusion method based on improved SML and guided filtering proposed by the present invention includes the following steps:
[0044] Step 1: For the registered input image I A (x,y) and I B (x, y), where (x, y) is the image coordinate position, I A (x,y) and I B (x,y) is the grayscale image of the same scene focusing on different targets, such as figure 2 with image 3 , figure 2 The middle boy is on the focal plane, with high definition and rich details, while the girl and the statue in the defocused area are blurred. On the contrary, image 3 The boy in the middle is blurred in the defocused area, and the girl in the focused area is clear and rich in details; two focus detection images S are obtained by using the improved SML me...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a multi-focus image fusion method based on improved SML and guided filtering, comprising the steps of: using the improved SML method to process two multi-focus input images after registration to obtain two focus detection images; The focus detection map is alternately processed by morphological opening and closing to obtain the corresponding focus area reconstruction map; the value of the same bit in the two focus area reconstruction maps is compared to obtain a binary segmentation map in which the focus area is separated from the defocus area; Perform small-area filtering on the binary segmentation map to obtain the initial fusion decision map; use one of the input images as a guide image, and use the initial fusion decision map as the guided filtering input image, and perform guided filtering operations to obtain an accurate fusion decision map; use weighted fusion rules Calculate the fused image. The method of the invention combines the advantages of pixel-based and region-based fusion methods, and has the advantages of fast calculation speed and more source image information.
Description
technical field [0001] The invention belongs to the field of image processing, and relates to a multi-focus image fusion method, in particular to a multi-focus image fusion method based on improved SML and guided filtering. Background technique [0002] Image fusion technology is widely used in remote sensing, medical imaging, computer vision and other fields. It is used to combine multiple input images into a single fusion image. The resulting fusion image has more human or machine perception information than any input image. . Multi-focus image fusion is an important branch of this field. In digital photography applications, imaging devices such as digital single-lens reflex cameras often have difficulty focusing on all important objects in a scene due to the limited depth of field of optical lenses. A feasible solution is multi-focus image fusion technology, which combines multiple images with different focus settings in the same scene into a single all-focus image, so ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/50G06K9/62
CPCG06T5/50G06F18/25
Inventor 王淑青李叶伟朱道利潘健邹煜要若天刘宗毛月祥周博文蔡颖靖王坤
Owner WUHAN FENJIN INTELLIGENT MACHINE CO LTD