Fourier descriptor and BP neural network-based garment style identification method

Abstract

The invention relates to a Fourier descriptor and BP (Back Propagation) neural network-based garment style identification method. The method comprises the steps of preprocessing a garment image to obtain an outer contour of the garment; performing Fourier description of the outer contour of the garment, and performing data preprocessing; and performing BP neural network-based garment style identification. The preprocessing of the garment image refers to a process that the garment image is subjected to segmentation processing to obtain a garment region, and the garment image is subjected to edge detection to obtain a contour image of the garment; the Fourier description of the outer contour of the garment refers to a process that a standardized Fourier descriptor eigenvector of a contour shape of the garment is extracted, and the data preprocessing refers to normalization processing and principal component analysis performed on the standardized Fourier descriptor eigenvector; and the BP neural network-based garment style identification refers to garment style identification performed on a principal component matrix by using a three-layer BP neural network. The method can achieve the identification accuracy of 81%, is good in robustness and generalization ability, and can be suitable for identification of garment styles in garment images.

Description

technical field [0001] The invention belongs to the technical field of clothing style recognition, and relates to a clothing style recognition method based on a Fourier descriptor and a BP neural network, in particular to a clothing outline image obtained by edge detection after image segmentation processing and based on Fourier Clothing style recognition method based on descriptor and BP neural network. Background technique [0002] With the advent of the era of big data, merchants can use machine vision technology to analyze consumers' dressing styles, which will help merchants capture the consumption trends of various customer groups and formulate targeted product portfolios, marketing plans and business decisions. At the same time, with the popularization of face computer recognition technology, extracting face features and combining clothing style features will improve the accuracy of identity authentication. Clothing styles are composed of changes in the outer contour...

AI Technical Summary

Problems solved by technology

Since the similarity comparison method between WFD feature vectors is complex and depends on the complexity of the target object outline, WFD is not suitable for real-time classification of shapes

Although ELM can greatly improve the speed and generalization ability of network learning, it inevitably causes the hidden danger of over-fitting and reduces the classification effect.

At the same time, An recognizes the clothing design plan without the interference of color and texture, so the clothing outline is smoother and the recognition difficulty is slightly lower; its recognition method is not suitable for clothing with color and texture

Images