Skin color detection method, skin color detection apparatus, and storage medium

A skin color detection apparatus, comprising a processor, a memory and at least one program code stored on the memory and executable by the processor;

• wherein the processor, when executing the at least one program code, is configured to:
• determine chrominance signal values in a luminance chrominance YUV domain of a pixel value corresponding to each pixel point in a target image under skin color detection;
• acquire images carrying the skin color points under various illumination conditions;
• generate a binary image based on the chrominance signal values in the YUV domain of a pixel value of each skin color point in the acquired images carrying the skin color points;
• obtain a distance matrix through distance transformation based on the pixel value of each pixel point in the binary image;
• determine the skin color index matrix based on the distance matrix;
• search for a skin color probability corresponding to the chrominance signal values in the skin color index matrix based on the chrominance signal values in the YUV domain of the pixel value corresponding to the pixel point, wherein the skin color index matrix is generated through processing skin color images under various illumination conditions, and the skin color probability is a probability that the pixel point is a skin color point;
• and
• perform skin color detection based on the skin color probability corresponding to the chrominance signal values of each pixel point in the target image.

A computer-readable storage medium having at least one instruction stored thereon;

• wherein the at least one instruction, when being executed by a processor, the processor is configured to:
• determine chrominance signal values in a luminance chrominance YUV domain of a pixel value corresponding to each pixel point in a target image under skin color detection;
• acquire images carrying the skin color points under various illumination conditions;
• generate a binary image based on the chrominance signal values in the YUV domain of a pixel value of each skin color point in the acquired images carrying the skin color points;
• obtain a distance matrix through distance transformation based on the pixel value of each pixel point in the binary image;
• determine the skin color index matrix based on the distance matrix;
• search for a skin color probability corresponding to the chrominance signal values in the skin color index matrix based on the chrominance signal values in the YUV domain of the pixel value corresponding to the pixel point, wherein the skin color index matrix is generated through processing skin color images under various illumination conditions, and the skin color probability is a probability that the pixel point is a skin color point;
• and
• perform skin color detection based on the skin color probability corresponding to the chrominance signal values of each pixel point in the target image.