Abstract: Image retrieval method based on genetic fuzzy c-means algorithm and support vector machines relevance feedback is proposed.First of all，the color feature and texture feature of image library is extracted，and genetic FCM clustering algorithm is used to cluster image，each cluster center of image class is obtained.The similarity between the sample image and the corresponding categories is calculated，according to the size of the similarity to return to retrieval results.At last，a relevance feedback method based on support vector machines is proposed to further improve the accuracy of the retrieval.The experiments show that the proposed method has a good image retrieval performance.

Key words: image retrieval, genetic algorithm, Fuzzy C-means Clustering algorithm, Support Vector Machines（SVM）, relevance feedback

摘要： 提出基于遗传FCM聚类算法和SVM相关反馈的图像检索方法。首先对图像库提取颜色和纹理特征，采用遗传FCM聚类算法对图像进行聚类，得到每个图像类的聚类中心；最后计算查询示例图像和对应图像类的图像之间的相似度，按照相似度的大小返回检索结果。为了进一步提高检索精度，提出基于SVM的相关反馈算法。实验结果表明，提出的方法具有优良的检索性能。

关键词: 图像检索, 遗传算法, 模糊C均值聚类算法, 支持向量机, 相关反馈