Method and apparatus for detecting specific external human body parts from texture energy maps of images by performing convolution

An apparatus for detecting one or more specific external human body parts in an image, the apparatus comprising:

• a processor;
• and
• a memory comprising code that, when executed by the processor, causes the processor to:
• analyze energy distribution in the image and generate texture energy maps;
• extract those regions having energy values higher than or equal to a threshold from a given texture energy map as one or more candidate regions-of-interest, the given texture energy map being selected from among the texture energy maps;
• perform convolution between one or more candidate masks for the one or more specific external human body parts and the one or more candidate regions-of-interest, and select one or more candidate external human body parts based on one or more results of the convolution;
• and
• detect the one or more specific external human body parts in the image by performing verification using one or more machine-learning models for the one or more specific external human body parts on the one or more candidate external human body parts,
• wherein the one or more specific external human body parts comprise at least one of a breast or genitals,
• wherein the one or more candidate masks comprise at least one candidate face mask, at least one candidate breast mask, at least one candidate genitals mask, or at least one combination of two or more of said at least one candidate face mask, said at least one candidate breast mask, and said at least one candidate genitals mask, and
• wherein said at least one candidate face mask and said at least one candidate genitals mask are configured to be used in eight-directional masking, and said at least one candidate breast mask is configured to be used in nine-directional masking.