Research on clothing style online design subsystem of Oracle database based on J2EE and UML technology

This paper focuses on the detailed design and development of clothing style online design subsystem of Oracle database based on J2EE technology and UML technology. Fabric image shape analysis can be realized by extracting SURF features from fabric images. However, due to the high SURF feature dimension and the feature extraction is based on grayscale images, the matching speed is slow and the matching results are not consistent with human visual characteristics. The SURF adaptive feature extraction algorithm based on wavelet and the K-Means clustering algorithm for automatic clothing color segmentation are studied. The purpose of quickly and accurately identifying clothing fabrics is achieved. At last, this paper has carried on the experiment to 8 pictures of clothing fabric. The experimental results show that the proposed method has a more accurate recognition rate compared with SIFT, SURF and other methods. The development of this software is of great significance to improve the scientific and technological level and economic benefit of domestic garment industry.