In order to improve the efficiency of image retrieval, an adaptive texture image retrieval algorithm based on transform domain is proposed. The algorithm uses two-dimensional discrete wavelet transform to reduce the size of the test image and the trained image, and further applies the LL component of the 2-level decomposition image in the gray level co-occurrence matrix to train and test to extract the texture features of the image, and finally combine shape features and color features retrieve similar images by fusing different distance classifiers. In order to improve the adaptive ability of the algorithm, an interactive genetic algorithm is introduced to dynamically adjust the parameters. The experimental results show that the accuracy of the proposed algorithm is above 67% when the number of training iterations is 30, 60, and 100. The algorithm has high application value in the field of image retrieval, and has the advantages of stable and reliable performance and high precision.