Fruit color grading method based on compressive sensing
A color grading and compression sensing technology, applied in color measurement devices, color/spectral characteristic measurement, sorting, etc., can solve the problems of limited promotion and application, complex processing process, long execution time, etc., to promote economic development, Fast and accurate grading
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0020] The present invention is an apple color grading method based on compressed sensing, which takes first-class fruit (apples whose red component coloring ratio is above 85%) as the tested object, and includes the following steps:
[0021] Step 1, obtain the main view and two left and right side views of the tested apple through the CCD camera;
[0022] Step 2, respectively extracting the R component images corresponding to the RGB images of the left and right side views, and adopting a color image space mean filter to smooth and filter the R component images of the left and right views respectively, so as to reduce the noise of the image;
[0023] Step 3: Take the 3*3 area in the upper left corner of the R component image after the filtering process as a reference template, and use the reference template to slide and scan the entire R component image pixel by pixel. For gray values greater than The area with the average value of the template above 10 is considered to con...
Embodiment 2
[0030] Taking the second-class fruit (apples whose red component coloring ratio is between 70% and 85%) as the tested object, the following steps are included:
[0031] Step 1, obtain the main view and two left and right side views of the tested apple through the CCD camera;
[0032] Step 2, respectively extracting the R component images corresponding to the RGB images of the left and right side views, and adopting a color image space mean filter to smooth and filter the R component images of the left and right views respectively, so as to reduce the noise of the image;
[0033] Step 3: Take the 3*3 area in the upper left corner of the R component image after the filtering process as a reference template, and use the reference template to slide and scan the entire R component image pixel by pixel. For gray values greater than The area with the average value of the template above 10 is considered to contain the apple area, and the original gray value is retained; on the contr...
Embodiment 3
[0040] Taking the third-class fruit (apples whose red component coloring ratio is below 70%) as the test object, the following steps are included:
[0041] Step 1, obtain the main view and two left and right side views of the tested apple through the CCD camera;
[0042] Step 2, respectively extracting the R component images corresponding to the RGB images of the left and right side views, and adopting a color image space mean filter to smooth and filter the R component images of the left and right views respectively, so as to reduce the noise of the image;
[0043]Step 3: Take the 3*3 area in the upper left corner of the R component image after the filtering process as a reference template, and use the reference template to slide and scan the entire R component image pixel by pixel. For gray values greater than The area with the average value of the template above 10 is considered to contain the apple area, and the original gray value is retained; on the contrary, the area ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
