An Improved Target Segmentation Method for Adhesive Particles Based on Concave Point Matching

Abstract

The invention discloses an improved method for segmenting cohesive particle objects based on pit point matching, which belongs to the technical field of image processing. The present invention first performs image preprocessing to obtain the contour and concave points of the target to be segmented; then, performs preliminary segmentation based on morphological operations, thereby effectively reducing the number of concave points for matching processing; then, segmentation processing based on local concave point matching , that is, first perform local pit matching processing, and then realize the first segmentation processing based on the matching result; finally, perform the second segmentation processing based on distance transformation processing to solve the technical problem of isolated pit points. The present invention can be used in technical fields such as agricultural planting, segmentation, etc., and its segmentation accuracy is high.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to the segmentation processing of cohesive particle objects. Background technique [0002] In recent years, product detection and classification technology has been a research hotspot in various scientific fields, and the production, processing and detection of granular products play an important role in the actual production process. Due to the large number of granular targets, manual measurement and statistics are very difficult. Therefore, image processing technology is used to convert them into two-dimensional images, and then the cohesive targets are separated reasonably and accurately. [0003] At present, the better segmentation methods of cohesive objects include morphological segmentation algorithm, watershed segmentation algorithm, concave point matching algorithm, etc. These algorithms are not universal for different cohesive multi-objects. The morph...

AI Technical Summary

Problems solved by technology

The existing segmentation algorithms often have mis-segmentation and over-segmentation problems for images with serious adhesion;

[0006] (2) Low efficiency

The existing segmentation algorithm has low operating efficiency and wastes a lot of computing cost, which needs to be further improved;

[0007] (3) Limitations

The existing segmentation algorithm based on global pit matching has great limitations. The premise of this algorithm is that there must be two pits to form a pit pair, and isolated pits may appear after the pit matching algorithm. These Isolated pits cannot be segmented using the pit matching algorithm

Images