Fabric image retrieval method based on fine texture representation

Abstract

The invention belongs to the field of fabric retrieval methods, and relates to a fabric image retrieval method based on fine texture representation. The method comprises the following steps: preprocessing an image to be inquired and an image in an image library, enhancing the contrast ratio of a fabric image, and highlighting the texture characteristics of the image; for the preprocessed image, processing the image by adopting a low-order feature extraction method, and carrying out feature description on the image to be inquired and the image in the image library; carrying out similarity measurement on the feature description of the to-be-queried image and the feature description of the image in the image library, and sorting according to the similarity from large to small; displaying thecorresponding images in sequence according to the similarity; and calling out process parameters corresponding to the image to guide production. According to the method, the fine texture features of the fabric are considered, the retrieval fineness and accuracy are high, the advantages of the two features are synthesized by proposing the product form for the first time, and the method has great potential in the field of image fine retrieval.

Description

technical field [0001] The invention belongs to the field of fabric retrieval methods, and relates to a fabric image retrieval method based on fine texture representation. Background technique [0002] With the improvement of people's consumption level, consumers' demand for clothing products is no longer limited to their wearing performance, but tends to be more beautiful and diversified. The styles of fabrics are changing with each passing day, and the patterns of patterns are constantly changing. Therefore, small batches and multiple varieties have increasingly become a new production method in the textile and garment industry. When textile enterprises imitate the samples received by consumers, they need to analyze the fabric first, obtain the process parameters of the fabric, adjust the parameters repeatedly, and try weaving and proofing until the needs of consumers are met. Therefore, the management and retrieval of fabrics has become an urgent problem for textile ente...

AI Technical Summary

Problems solved by technology

This method improves the efficiency of fabric retrieval, but manual labeling is also time-consuming and laborious. Labeling varies from person to person, has strong subjectivity, and the retrieval results are unstable, making it difficult to meet the requirements of enterprises.

[0003]Currently, image-based fabric retrieval methods only focus on the overall appearance of the fabric, without considering the fine texture information such as fabric structure and density

Images