Bacterial colony classification method

Abstract

The invention discloses a bacterial colony classification method. The method comprises the following steps of converting an input bacterial colony image into a gray scale image; carrying out local threshold segmentation on the gray scale image, setting a pixel of the gray level image, which is greater than a corresponding local threshold, as 1, and setting a pixel of the gray level image, which is smaller than the local threshold, as 0, so as to generate a binary image; carrying out corrosion expansion operation on the binarized image, carrying out morphological processing, and removing noisy points and burrs; performing connected region analysis on the binarized image to extract a colony connected region, and removing a non-colony region; and when the pixels contained in the colony communication region are greater than a pixel number threshold T, inputting the binary image into a colony classification network or performing classification according to a colony morphological structure to obtain a colony classification result, wherein the colony morphological structure includes a circular colony, an elliptical colony, a sticky colony or a strip-shaped colony. The method has the advantages of improving the accuracy of bacterial colony segmentation and classification and the like.

Description

technical field [0001] The invention relates to the technical field of colony segmentation and classification, in particular to a colony classification method. Background technique [0002] At present, the counting and identification of bacterial colonies are performed manually. The work of manually counting and identifying bacterial colonies is very complicated, and the accuracy of counting and identification cannot be guaranteed. [0003] If the traditional method is used to classify the colony, when the traditional method is used to classify the composite colony, the classification of the traditional method is relatively weak, because the size and shape of the colony in the composite colony are different, and when there is colony adhesion, The formed cohesive colonies will have various shapes; while the traditional classification methods are not robust enough to achieve better classification results in complex situations. [0004] At present, the method of target detecti...

AI Technical Summary

Problems solved by technology

[0002] At present, counting and identifying colonies manually is very complicated, and the accuracy of counting and identification cannot be guaranteed

[0003] If the traditional method is used to classify the colony, when the traditional method is used to classify the composite colony, the classification of the traditional method is relatively weak, because the size and shape of the colony in the composite colony are different, and when there is colony adhesion, The formed cohesive colonies will have various shapes; while the traditional classification methods are not robust enough to achieve better classification results in complex situations.

[0004] At present, the method of target detection is also used to detect the colonies in the petri dish. The method of target detection only performs better for colonies with specific shapes such as circles and ellipses, and the distribution of colonies is relatively sparse. When there are striped colonies, Or in the case of colony adhesion, the detection frame cannot frame a single connected area, which will have a greater impact on the subsequent colony classification. Since the detection frame is a rectangular frame, the shape of the cohesive colony is irregular, and the area to be framed by a rectangular frame , may contain other colonies; the same is true for bar colonies, if two or more bar colonies are slanted and adjacent, they cannot frame an area, and may frame multiple colonies at the same time

Sending the framed multiple colonies into the classification network for classification will affect the classification results, as well as the accuracy and recall of the classification.

Images