Image marking method and computing device implementing image marking method
An image marking method includes acquiring an image and at least one feature to be marked in the image, searching for at least one target area matching the at least one feature to be marked in the image, and marking the at least one target area with a preset graphic. The feature corresponds to the preset graphic.
1. An image marking method comprising:
acquiring an image of a product using a camera and acquiring at least one first feature to be marked in the image, wherein the camera is located on a production device that is used to produce the product;
searching for at least one first target area matching the at least one first feature to be marked in the image;
marking the at least one first target area with a first preset graphic, the at least one first feature corresponding to the first preset graphic;
taking the at least one first target area as a center, and searching whether there is a second target area within a preset step length matching the at least one first feature; and
in response that there is the second target area, marking the second target area with the first preset graphic;
in response that the at least one first target area overlaps the second target area, assigning a first weight to an overlapping area of the at least one first target area and the second target area, and assigning a second weight to a non-overlapping area, the first weight being greater than the second weight, wherein an area with a higher weight has a higher credibility;
identifying areas from the image based on credibility; and
improving recognition accuracy by performing multi-scale training based on the identified areas.
2. The image marking method of claim 1 ,
wherein the first weight is used to describe a credibility of the at least one first target area, and the second weight is used to describe a credibility of the second target area.
3. The image marking method of claim 2 , further comprising:
generating a prompt message when the at least one first target area is simultaneously marked by the first preset graphic and a second preset graphic; and
executing a solution provided according to the prompt message.
4. The image marking method of claim 3 , further comprising:
when the image comprises a combination of the at least one first target area, the second target area, and the overlapping area of the at least one first target area and the second target area, sorting corresponding weights according to sizes, and generating a sorting result.
5. The image marking method of claim 3 ,
wherein the second preset graphic corresponds to a second feature, the second feature being different from the at least one first feature.
6. A computing device comprising:
a processor; and
a memory storing a plurality of instructions, which when executed by the processor, causes the processor to:
acquire an image of a product using a camera and acquiring at least one first feature to be marked in the image, wherein the camera is located on a production device that is used to produce the product;
search for at least one first target area matching the at least one first feature to be marked in the image;
mark the at least one first target area with a first preset graphic, the at least one first feature corresponding to the first preset graphic;
take the at least one first target area as a center, and search whether there is a second target area within a preset step length matching the at least one first feature; and
in response that there is the second target area, mark the second target area with the first preset graphic;
in response that the at least one first target area overlaps the second target area, assign a first weight to an overlapping area of the at least one first target area and the second target area, and assign a second weight to a non-overlapping area, the first weight being greater than the second weight, wherein an area with a higher weight has a higher credibility;
identify areas from the image based on credibility; and
improve recognition accuracy by performing multi-scale training based on the identified areas.
7. The computing device of claim 6 ,
wherein the first weight is used to describe a credibility of the at least one first target area, and the second weight is used to describe a credibility of the second target area.
8. The computing device of claim 7 , wherein the processor is further configured to:
generate a prompt message when the at least one first target area is simultaneously marked by the first preset graphic and a second preset graphic; and
execute a solution provided according to the prompt message.
9. The computing device of claim 7 , wherein the processor is further configured to:
when the image comprises a combination of the at least one first target area, the second target area, and the overlapping area of the at least one first target area and the second target area, sort corresponding weights according to sizes, and generate a sorting result.
10. The computing device of claim 6 ,
wherein the first preset graphic corresponds to a first feature, and the second preset graphic corresponding to a second feature, the second feature being different from the at least one first feature.
11. A non-transitory storage medium having stored thereon instructions that, when executed by at least one processor of a computing device, causes the at least one processor to execute instructions of an image marking method, the method comprising:
acquiring an image of a product using a camera and acquiring at least one first feature to be marked in the image, wherein the camera is located on a production device that is used to produce the product;
searching for at least one first target area matching the at least one first feature to be marked in the image;
marking the at least one first target area with a first preset graphic, the at least one first feature corresponding to the first preset graphic;
taking the at least one first target area as a center, and searching whether there is a second target area within a preset step length matching the at least one first feature; and
in response that there is the second target area, marking the second target area with the first preset graphic;
in response that the at least one first target area overlaps the second target area, assigning a first weight to an overlapping area of the at least one first target area and the second target area, and assigning a second weight to a non-overlapping area, the first weight being greater than the second weight, wherein an area with a higher weight has a higher credibility;
identifying areas from the image based on credibility; and
improving recognition accuracy by performing multi-scale training based on the identified areas.
12. The non-transitory storage medium of claim 11 ,
wherein the first weight is used to describe a credibility of the at least one first target area, and the second weight is used to describe a credibility of the second target area.
13. The non-transitory storage medium of claim 12 , wherein the method further comprises:
generating a prompt message when the at least one first target area is simultaneously marked by the first preset graphic and a second preset graphic; and
executing a solution provided according to the prompt message.
14. The non-transitory storage medium of claim 13 , wherein the method further comprises:
when the image comprises a combination of the at least one first target area, the second target area, and the overlapping area of the at least one first target area and the second target area, sorting corresponding weights according to sizes, and generating a sorting result.
15. The non-transitory storage medium of claim 13 ,
wherein the first preset graphic corresponds to a first feature, and the second preset graphic corresponds to a second feature, the second feature being different from the at least one first feature.