Method for selecting a light source for illuminating defects, electronic device, and non-transitory storage medium
A method for selecting a light source for illuminating defects, an electronic device, and a non-transitory storage medium are provided. The method includes acquire grayscale images of an object with a known defect and generates a pseudo-hyperspectral image cube based on the grayscale images, so that algorithms related to hyperspectral images can analyze the grayscale images collected under different light sources. A most effective or target light source can be automatically and quickly determined from the plurality of light sources, improving an efficiency of light source selection.
1. A method for selecting a light source for illuminating defects, the method comprising:
acquiring a plurality of grayscale images of an object with a known defect, one grayscale image corresponding to one light source;
generating a pseudo-hyperspectral image cube according to the plurality of grayscale images, comprising: obtaining the pseudo-hyperspectral image cube by performing a three-dimensional fusion of the plurality of grayscale images, wherein a width of the pseudo-hyperspectral image cube is a width of the grayscale image, and a length of the pseudo-hyperspectral image cube is a length of the grayscale image, and a height of the pseudo-hyperspectral image cube is a number of the plurality of grayscale images;
acquiring defect information of the known defect, and acquiring a spectrum wavelength of the defect information from the pseudo-hyperspectral image cube;
generating a characteristic spectrum curve according to the defect information and the spectrum wavelength; and
applying a hyperspectral image analysis algorithm to analyze the characteristic spectrum curve to obtain an analyze result and obtaining a target light source according to the analyze result.
2. The method according to claim 1 , wherein acquiring the plurality of grayscale images of an object with a known defect comprises:
acquiring an image of the object under each of a plurality of light sources; and
converting each of the acquired image through a gray scale conversion algorithm to obtain the plurality of grayscale images.
3. The method according to claim 2 , wherein the gray scale conversion algorithm comprises any one of a floating-point algorithm, an integer algorithm, a shift algorithm, an average value algorithm, and a green-only algorithm.
4. The method according to claim 1 , the method further comprising:
performing hyperspectral image analysis on the pseudo-hyperspectral image cube according to a preset analysis algorithm to obtain data, after generating the pseudo-hyperspectral image cube according to the plurality of grayscale images; and
saving the data in a database.
5. The method according to claim 4 , wherein the preset analysis algorithm comprises any one of a waveband selection algorithm and an orthogonal subspace projection algorithm.
6. The method according to claim 5 , the method further comprising:
acquiring an image of a target object to be detect under the target light source, after obtaining a target light source according to the analyze result;
performing an optical detection on the image of the target object to obtain a result of detection or non-detection of a defect, wherein the result is used to determine whether the target object has the known defect.
7. An electronic device comprising a memory and a processor, the memory stores at least one computer-readable instruction, which when executed by the processor causes the processor to:
acquire a plurality of grayscale images of an object with a known defect, one grayscale image corresponding to one light source, comprising: obtaining the pseudo-hyperspectral image cube by performing a three-dimensional fusion of the plurality of grayscale images, wherein a width of the pseudo-hyperspectral image cube is a width of the grayscale image, and a length of the pseudo-hyperspectral image cube is a length of the grayscale image, and a height of the pseudo-hyperspectral image cube is a number of the plurality of grayscale images;
generate a pseudo-hyperspectral image cube according to the plurality of grayscale images;
acquire defect information of the known defect, and acquire a spectrum wavelength of the defect information from the pseudo-hyperspectral image cube;
generate a characteristic spectrum curve according to the defect information and the spectrum wavelength; and
apply a hyperspectral image analysis algorithm to analyze the characteristic spectrum curve to obtain an analyze result and obtain a target light source according to the analyze result.
8. The device for selecting a light source according to claim 7 , wherein the processor acquires the plurality of grayscale images of an object with a known defect by:
acquiring an image of the object under each of a plurality of light sources; and
converting each of the acquired image through a gray scale conversion algorithm to obtain the plurality of grayscale images.
9. The device for selecting a light source according to claim 8 , wherein the gray scale conversion algorithm comprises any one of a floating-point algorithm, an integer algorithm, a shift algorithm, an average value algorithm, and a green-only algorithm.
10. The device for selecting a light source according to claim 7 , wherein the processor is further caused to:
perform hyperspectral image analysis on the pseudo-hyperspectral image cube according to a preset analysis algorithm to obtain data, after generating the pseudo-hyperspectral image cube according to the plurality of grayscale images; and
save the data in a database.
11. The device for selecting a light source according to claim 9 , wherein the preset analysis algorithm comprises any one of a waveband selection algorithm and an orthogonal subspace projection algorithm.
12. The device for selecting a light source according to claim 11 , wherein the processor is further caused to:
acquire an image of a target object to be detect under the target light source, after obtaining a target light source according to the analyze result;
perform an optical detection on the image of the target object to obtain a result of detection or non-detection of a defect, wherein the result is used to determine whether the target object has the known defect.
13. A non-transitory storage medium having stored thereon at least one computer-readable instructions that, when the at least one computer-readable instructions are executed by a processor to implement a method for selecting a light source for illuminating defects, which comprises:
acquiring a plurality of grayscale images of an object with a known defect, one grayscale image corresponding to one light source;
generating a pseudo-hyperspectral image cube according to the plurality of grayscale images, comprising: obtaining the pseudo-hyperspectral image cube by performing a three-dimensional fusion of the plurality of grayscale images, wherein a width of the pseudo-hyperspectral image cube is a width of the grayscale image, and a length of the pseudo-hyperspectral image cube is a length of the grayscale image, and a height of the pseudo-hyperspectral image cube is a number of the plurality of grayscale images;
acquiring defect information of the known defect, and acquiring a spectrum wavelength of the defect information from the pseudo-hyperspectral image cube;
generating a characteristic spectrum curve according to the defect information and the spectrum wavelength; and
applying a hyperspectral image analysis algorithm to analyze the characteristic spectrum curve to obtain an analyze result and obtaining a target light source according to the analyze result.
14. The non-transitory storage medium according to claim 13 , wherein acquiring the plurality of grayscale images of an object with a known defect comprises:
acquiring an image of the object under each of a plurality of light sources;
converting each of the acquired image through a gray scale conversion algorithm to obtain the plurality of grayscale images.
15. The non-transitory storage medium according to claim 14 , wherein the gray scale conversion algorithm comprises any one of a floating-point algorithm, an integer algorithm, a shift algorithm, an average value algorithm, and a green-only algorithm.
16. The non-transitory storage medium according to claim 13 , the method further comprising:
performing hyperspectral image analysis on the pseudo-hyperspectral image cube according to a preset analysis algorithm to obtain data, after generating the pseudo-hyperspectral image cube according to the plurality of grayscale images; and
saving the data in a database.
17. The non-transitory storage medium according to claim 16 , the method further comprising:
acquiring an image of a target object to be detect under the target light source, after obtaining a target light source according to the analyze result;
performing an optical detection on the image of the target object to obtain a result of detection or non-detection of a defect, wherein the result is used to determine whether the target object has the known defect.