Block-based apple image segmentation method based on gray center color space
A grayscale center, color space technology, applied in the field of image processing, can solve the problem of low accuracy and achieve the effect of high accuracy
Pending Publication Date: 2021-09-07
NORTHWEST A & F UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The invention aims to solve the problem that the accuracy of apple target recognition is low under the influence of complex conditions such as sunlight irradiation and shadows after the light is blocked. Aiming at the accuracy of apple image recognition and classification, a method based on the gray center color space is proposed. Block-based apple image segmentation method, the research is based on the gray center RGB color space, and a "block-based" K-means clustering segmentation algorithm is proposed to identify ripe apples in natural scenes
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
example
[0042] The test experiment hardware and software environment of the present embodiment is as follows:
[0043] Hardware environment:
[0044] CPU: i9-9880H CPU@2.30GHz;
[0045] Memory: 8.00GB;
[0046] System type: 64-bit Windows 10 operating system.
[0047] Software environment: IDE: Matlab 2018b;
[0048] Dataset: collected at 8:00 am and 5:00 pm with weak atmospheric light, and at 12:00 noon with strong sunlight. A total of 300 apple images taken under natural light conditions were collected in the experiment, and 180 images were randomly selected to test the performance of the algorithm. Among them, there were only 60 apples with different degrees of shadow image data, and only different degrees of light image data (with 60 pieces of apple image data with different degrees of light and shadow coexisting.
[0049] Such as figure 1 The present invention is aimed at the apple image segmentation algorithm under the influence of complex conditions such as sunlight irrad...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a block-based apple image segmentation method based on a gray center color space, and belongs to the technical field of image processing. The method comprises the following steps: firstly, decomposing an apple image in a gray center color space in parallel and vertical directions by using quaternion; secondly, taking an image formed by a vector constructed by pointing to all pixels from a gray center and pixels within an included angle range of 30 degrees with the selected interested color vector (red) as a feature map of the apple; and then, in combination with pixel field information, providing a block-based apple image segmentation method based on a gray center color space. According to the method, changes in the field of apple images can be better described, the accuracy of apple target recognition of the apple picking robot under the influence of complex conditions such as sunlight irradiation and shadow generated after light shielding is improved, and the method has important significance in target image segmentation of other fruits and vegetables such as bananas and grapes.
Description
technical field [0001] The invention belongs to the technical field of image processing, and relates to image processing of an apple picking robot vision system, in particular to a block-based apple image segmentation method based on a gray center color space. Background technique [0002] Apple picking is a labor-intensive and time-intensive job. It is an inevitable trend of agricultural development to replace manual fruit picking with apple picking robots. In a natural unstructured environment, when the sun shines directly or is blocked by branches and leaves, light spots and shadows will be produced on the apple surface. In the existing fruit harvesting robot vision system, the influence of sunlight is reduced by changing the imaging conditions before collection or optimizing the image after collection. Another solution is to optimize the algorithm of the captured image to reduce or eliminate the impact of light (with shadows) on the target area of the image. Aiming a...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T7/11G06K9/62
CPCG06T7/11G06T2207/10004G06T2207/10024G06T2207/20081G06F18/23
Inventor 杨福增王美茸樊攀
Owner NORTHWEST A & F UNIV