Multi-resolution food insect species visual recognition method

Abstract

The invention discloses a multi-resolution visual recognition method for grain insect species, which uses the OTSU algorithm to binarize three images of grain insects taken with low, medium and high resolution respectively, and uses the Blob algorithm to extract low, medium and high-resolution images respectively. The connected regions of grain insect images with three high and high resolutions are used to locate the suspected grain insect target area on the low resolution grain insect image; according to the magnification ratio of medium and low resolution images and the suspected grain insect target The area is reverse positioned, and the area parameters and perimeter parameters are calculated to determine whether it is a grain insect area; finally, on the basis of the connected areas of the high-resolution grain insect image extracted by the Blob algorithm, according to the magnification ratio of the high- and medium-resolution images and the determined medium The resolution grain insect area is used for reverse positioning, and the local binary mode grain insect texture feature and the random forest classifier are used to identify the grain insect. The invention utilizes the advantages of the development tool and the image processing algorithm to realize efficient and accurate identification of the types of grain insects.

Description

technical field [0001] The invention relates to the field of detection of stored grain conditions, in particular to a multi-resolution visual recognition method for grain insect species. Background technique [0002] Maintaining a certain amount, variety and quality of grain reserves is an important measure to ensure national food security. Among them, the harm of stored grain pests has been one of the more prominent problems in this field for a long time. Grain insect identification is an effective means of grain insect integrated control. The main methods are sampling method, trapping method, voice recognition method, near-infrared method and visual detection method. Since the American scholar Zayas used vision technology to conduct offline research on the grain beetle adults in bulk wheat bins, it has opened up a new way for the rapid detection and classification of grain insects. The visual recognition method has the advantages of high accuracy, less labor, visualizat...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a multi-resolution visual identification method for grain insect species, so as to solve the problem that the existing grain insect visual detection method cannot overcome the influence of the actual granary storage composite environment

Images