摘要： 提出了一种基于交互式遗传算法的图像检索模型。该模型首先将图像划分成一定的特征区间，结合区间的颜色特征和信息熵对图像进行编码，通过对用户评价后的图像进行遗传操作选出接近用户需要的图像，同时在遗传操作的过程中使用保护策略，保证在选择过程中用户不会丢失最适合的图像。实验证明该方法是实用有效的。

关键词: 图像检索；交互式遗传算法；信息熵；保护策略

Abstract: This paper proposes an image retrieval system based on IGA. First it divides the image into small feature spaces and construcs image chromosome using both color feature and image information entropy. The user decides the fitness of the image and the fittest image is used as the parent of genetic algorithm. Elitist strategy is used during the genetic operation to make sure the user does not lost the fittest result. Experiments prove that the method is practical and useful

Key words: Image retrieval; Interactive genetic algorithm (IGA); Information entropy; Elitist strategy