In today's computer networks, the amount of digital images increases rapidly and enormously. However, images may be distorted through di erent types of processing such as histogram equalization, quantization, smoothing, compression, noise corruption, geometric transformation, and changing of illumination. It is imperative to develop an e ective method to retrieve the original images from very large image databases because only the original images are stored for economy. In this study, a new image normalization method is ΓΏrst proposed to solve the problem with illumination varying. A complementary retrieval method is then proposed to resist various types of processing. According to the type of distortion, all processing are classiΓΏed into three distortion categories, low frequency, high frequency and geometric transformation. In addition, di erent features are resistant to di erent distortion categories. However, the distortion by which a query image is corrupted is usually unknown. Hence, a complementary analysis is proposed to determine the distortion category for each query image and the feature resistant to the estimated category is used to retrieve the desired original image. As a result, an e ective retrieval method is achieved. The feasibility and e ectiveness of our method are demonstrated by experimental results.