Fabric Image Retrieval Algorithm Based on Zernike Moment and Collage Error
In order to improve the efficiency of fabric image retrieval in textile enterprises,a fabric image retrieval algorithm based on Zernike moment and collage error was proposed.Firstly,the best match fractal parameters and Zernike moments are selected by calculation.Secondly,collage error was calculated based on the similarity between the range block and the best matching domain block.Finally,the method of combining Zernike moment and collage error was used for feature extraction of the feature quantity of cloth pattern retrieval as the fabric image retrieval characteristic.The experimental results show that the average accuracy,recall and retrieval time of the algorithm are 88.6%,53.4%and 0.207 s,respectively,which are significantly better than the basic fractal algorithm(BFC),single collage error algorithm(SCE),the joint orthogonal fractal parameters and the improved Hu moment invariant algorithm(OFH).In addition,the average accuracy and recall of ZMCE algorithm are better than algorithms in literature[4].Therefore,this algorithm has a good application value in fabric image retrieval of textile industry.
万方数据
维普
