Clothing sketch input cloth material identification simulation method based on deep learning

Abstract

The invention relates to a clothes sketch input cloth material identification simulation method based on deep learning, and the method comprises the steps: obtaining a clothes sketch as a training image, and obtaining a preprocessed clothes sketch image and a corresponding cloth material image through data filtering; adopting a hand-drawn sketch identification method fusing a convolutional neuralnetwork and a Fisher vector to train a collected clothing sketch; inputting the obtained preprocessed clothing sketch image serving as training data into a convolutional neural network and Fisher vector hand-drawn sketch recognition method to obtain a clothing sketch image classification result of the cloth material image; after an obtained clothing sketch image classification result is obtained,selecting the closest real cloth according to a cloth matching algorithm to perform simulation; according to the method, the corresponding real cloth material is obtained in a simple sketch mode, andthe dynamic effect of the material cloth matched with the sketch after human body try-on is simulated in a three-dimensional mode.

Description

technical field [0001] The invention relates to a method for identifying and simulating cloth material based on deep learning of clothing sketch input, and belongs to the technical field of service design. Background technique [0002] In fashion design, sketches are an important carrier to reflect the designer's thinking. They can quickly and accurately display the designer's design thinking intuitively, and can communicate with customers more conveniently. The simplicity of the sketch allows the designer to spend more time focusing on the most essential part of the shape and improve the efficiency of the design. The clothing design sketch expresses the designer's intention, the details of the clothing and the style of the clothing when it is drawn. In the design process, fashion designers usually have similarities in the process of making clothing sketches. Cloths of different materials are skillfully combined to produce a harmonious and varied texture contrast effect, th...

AI Technical Summary

Problems solved by technology

[0006] The technical solution of the present invention is to overcome the existing difficulties in selecting clothing materials in the design stage, and provide a method for identifying and simulating cloth materials based on deep learning based on sketch input, so as to obtain corresponding cloth materials through simple sketches, and use three-dimensional methods To simulate the effect of the human body wearing clothing, solve the difficulty in the selection of fabric materials, and intuitively reflect the performance of the fabric material in the final design of clothing

Images