A kind of acne automatic detection method

Abstract

The invention discloses an automatic pimple detection method. The method comprises steps that S100, an original image is acquired; S200, skin color filtering and face key point positioning of the original image are carried out, a binary skin color graph of the original image is acquired; S300, the binary skin color graph is utilized to extract a connected pimple zone; S400, according to the connected pimple zone, pimple zones of the original image are coarsely detected; and S500, the pimple zones are screened, and the accurate pimple zones are acquired through screening according to local pimple characteristics. The method is advantaged in that the pimples, moles and relatively obvious speckles on a face can be automatically and accurately detected, the method is simple and reliable, computational complexity is low, and the beauty effect can be realized in combination with a subsequent pimple removal method.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to an automatic detection method for acne. Background technique [0002] In recent years, with the advancement of technology, mobile devices such as smartphones and tablets have become indispensable digital entertainment tools for people. With the rise of smart devices, the demand for beautifying selfies is also increasing. Many users hope to remove some acne and moles on their faces. [0003] However, many existing applications need to manually click on the acne area to achieve the effect of removing acne, and the process is cumbersome; even if there is an automatic method for removing acne, it still cannot remove obvious acne and relatively large moles. . [0004] Moreover, in the prior art, LOG, DOG, etc. are often used to detect spots, and the amount of calculation is usually relatively large, and there will be many false detections for acne on the face. Contents of...

AI Technical Summary

Problems solved by technology

[0003] However, many existing applications need to manually click on the acne area to achieve the effect of removing acne, and the process is cumbersome; even if there is an automatic method for removing acne, it still cannot remove obvious acne and relatively large moles.

[0004] Moreover, in the prior art, LOG, DOG, etc. are often used to detect spots, and the amount of calculation is usually relatively large, and there will be many false detections for acne on the face.

Images