The invention relates to an imaging method for virtual fitting. The imaging method comprises the following steps of: 1, establishing a
human body AI model by utilizing
label information of a clothingmeasurement rule and training the model on the basis of a
Mask-RCNN; 2, obtaining a clothing data picture according to the
label information of the clothing measurement rule and string the clothing data picture into a
database; 3, obtaining a customer
human body data picture according to the
label information of the clothing measurement rule; and 4, carrying out
data analysis and human-clothing matching: substituting the customer
human body data picture obtained in the step 3 into the human body AI model in the step 1 to
train, taking a human
body position and a key point output by the AI model as the label information, estimating a size of each area of the customer human body, retrieving clothing with proper sizes and carrying out fitting according to the estimated size information of each area of the customer human body, and displaying a fitting success result between the clothing and the human body through an image engine. The method is capable of improving the fitting efficiency, displaying the effect of bodily form and fit clothing, and really displaying whether the clothing is matched with the
skin color, head style and temperament or not.