基于Surf和改进颜色矩的服装图像检索算法研究  

Research on Garment Image Retrieval Algorithm Based on Surf and Improved Color Moment

作　　者：施怡澄 刘洞波[1] 陈玉婷 SHI Yi-cheng;LIU Dong-bo;CHEN Yu-ting(College of Computer and Communication,Hunan Institute of Engineering,Xiangtan 411104,China)

机构地区：[1]湖南工程学院计算机与通信学院,湘潭411104

出　　处：《湖南工程学院学报（自然科学版）》2021年第3期53-58,共6页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：湖南省自然科学基金项目(2020JJ6022).

摘　　要：针对单一算法检索效率不高的问题,提出一种新的基于Surf和改进颜色矩的服装图像检索算法,采用改进的目标颜色矩进行服装图像特征筛选,对目标进行预定位,进而采用Surf算法进行特征点匹配检索出目标图像,仿真结果表明,该算法图像检索时间比单一算法缩短了62.5%,效率提高了166%,比基于单一Surf或者颜色矩的检索算法更具准确性和检索效率,增强了算法的便捷性及实用性.A new clothing image retrieval algorithm based on Surf and improved color moments is proposed.The target color moments are used to screen clothing images and roughly locate the target.And Surf algo-rithm is used to match the feature points in the filtered data set.The code is based on MATLAB program-ming.Simulation results show that this CM-SURF algorithm is more accurate than traditional SINGLE Surf or color moment,can find more expected targets and ensure the normal recognition of the whole system,great-ly enhancing the convenience and practicability of the algorithm.

关 键 词：SURF特征 颜色矩 特征提取 特征匹配 图像检索 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]