Method for automatically cutting granular object in digital image

Abstract

The invention discloses a method for automatically cutting a granular object in a digital image, belonging to the technical field of digital image processing. The method comprises the following steps of: firstly, separating an object from a background by applying an automatic threshold method by aiming at characteristics such as gray level, structural distribution, geometry and the like of the granular object in the digital image, particularly a microscopic image; then, calculating a gradient vector field of the object, and searching a key point in the gradient vector field, wherein the idealkey point has corresponding gradient vector distribution in eight neighborhoods, the gradient value of the key point is zero, and the acquired key point is used as the center of each granular object;next, defining a new effective energy function based on the gray level and a space position so as to calculate a direction gradient to replace the traditional gray level gradient; and finally, searching the boundary of the granular object by applying an active contour model. By using the method, the aggregated granular object can be accurately and effectively cut, particularly, a great number of adhered or overlapped micro-grains exist in a biomedical microscopic image, and therefore, help is provided for the image analysis and identification.

Description

technical field [0001] The invention belongs to the technical field of digital image analysis and processing, in particular to automatic segmentation of granular objects in digital images. Background technique [0002] In digital images, especially in biomedical microscopic images, the structures or microstructures of many objects are granular, such as microscopic images of starchy foods, potatoes, wheat starch granules, thermophiles, cocci, red blood cells, small lymphocytes, etc. The characteristics of the image are: (1) the number of particles is large, in a state of aggregation and distribution; (2) the distance between particles is small, and there are a lot of adhesion and overlapping phenomena; (3) the shape is regular, mostly round or nearly round. When conducting biological and medical basic research, it is often necessary to analyze and process the structure and distribution characteristics of these particles, such as cell / particle counting, virus feature extractio...

AI Technical Summary

Problems solved by technology

Segmentation based on geometric deformation models, whether it is traditional Snake, improved GVF, Ballon force model, or B-spline Snake, can quickly and accurately segment a single target after proper initialization. Although the level set algorithm can transform the search problem of two-dimensional contours to the evolution of surface topology in three-dimensional space, making it more suitable for segmenting multiple targets, it has difficulty in constructing a rate function and has many control parameters. , Insufficient time consumption, etc.

More importantly, these two types of methods are not ideal for objects with a lot of adhesion and overlap in the image. They cannot detect the correct object boundaries and implement accurate and effective segmentation.

Images