Multi-scale analysis-based greenhouse field plant leaf margin extraction method and system

Abstract

The invention belongs to the digital image processing technical field and relates to a multi-scale analysis-based greenhouse field plant leaf margin extraction method and system. According to the method, differences of information of images in different scale spaces are utilized, and different segmentation methods are selected, and comprehensive analysis is performed, and as a result, ideal segmentation results can be obtained; after an experimental image is obtained, proper smoothing filtering is performed on the image, and classified processing is performed on different types of pseudo edges in the image; and based on different situations of Canny edge detection in a comprehensive scale space and OTSU threshold segmentation in different scales and different characteristics of various kinds of pseudo edges, with methods such as morphological processing and logical operation methods adopted, internal and external pseudo edges are removed through utilizing bitwise operation, and therefore, edge detection accuracy can be improved, and leaf recognition error rate can be reduced.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a multi-scale analysis-based method for extracting leaf edges of greenhouse field plants and a system thereof. Background technique [0002] Leaf is the manufacturing organ of fruit tree nutrients and the basis of yield formation. A large amount of leaf growth information needs to be obtained in agricultural production. In order to obtain leaf growth information through images and realize automatic monitoring of orchard production, it is necessary to conduct image enhancement and segmentation algorithm research on field fruit tree leaf images. Image segmentation is the basis of image analysis and image understanding, and can provide important information for further image processing. Plant leaf image segmentation can provide an important basis for plant feature extraction, such as leaf area calculation, leaf disease and pest detection, and leaf 3D reconstructio...

AI Technical Summary

Problems solved by technology

However, plant leaf images usually have the following characteristics: complex background, many leaves, easy to overlap, the surface of the leaves is not smooth enough, the color difference between the veins and the leaves is large, the gradient change is not obvious in some places on the edge of the leaves, the leaves and petioles are connected, and the branches overlap. It is difficult to separate the places, and some fruit tree leaf images show several areas of different brightness due to different lighting conditions, and the internal gradient changes are too obvious

The result of these features is that the continuity and closure of the edge cannot be guaranteed, and there are many broken edges and false edges in the high-detail area, so it is difficult to determine which edges are the real target edges

Images