Image segmentation method based on organizational evolutionary cluster algorithm
An image segmentation and clustering algorithm technology, applied in the fields of image processing, pattern recognition and computer vision, which can solve the problems of unfavorable image analysis and understanding, slow convergence speed, sensitive to noise data, etc.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2014-05-28
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the technical field of image processing, and relates to an image segmentation method, in particular to an image segmentation method based on a tissue evolution clustering algorithm, which can be used in the fields of pattern recognition, computer vision and the like. Background technique
[0002] Image segmentation is the basis of subsequent image analysis and image understanding. It has a very wide range of applications in practice. For example, the extraction and measurement of image objects are inseparable from image segmentation. The accuracy of segmentation directly affects the effectiveness of subsequent tasks, so it has very important.
[0003] Image segmentation is a special image processing technology, and its essence is a process of classification according to pixel attributes, namely grayscale, texture, and color.
[0004] Clustering is a kind of unsupervised classification, which is widely used in fields such as en...
Examples
Embodiment Construction
[0074] Such as figure 1 shown.
[0075] The main flowchart step features are:
[0076] Step 101: input the image to be segmented, and extract the grayscale information of the image to be segmented;
[0077] Step 102: applying the tissue evolution clustering algorithm to cluster the two-dimensional grayscale information of the image;
[0078] Step 103: According to the membership degree matrix output in step 102, output cluster labels according to the principle of maximum membership degree;
[0079] Step 104: According to the clustering labels output in step 103, classify the image pixels, implement image segmentation, and output the segmented image.
[0080] Such as figure 2 as shown,
[0081] Described step 102 includes the following steps:
[0082] Step 201: Determine the number of clusters c and the fuzzy weight m, and randomly initialize the cluster prototype, that is, randomly select the gray information of c pixels from the image to be segmented as the cluster cen...