The synthetic aperture radar (SAR) auto target recognition (ATR) algorithm developed at Lincoln Laboratory is a standard algorithm for target detection/recognition. It has three main stages: a prescreener

a discriminator and a classifier. The clustering algorithm between the prescreener stage and the discriminator stage is significant for the performance of the detection algorithm. This letter introduces the steps of the common clustering algorithm and analyzes its disadvantages. We improve the common clustering algorithm from two aspects of the read sequence of image data and the calculation means of clustering quasicenter coordinates. The clustering results based on two actual images testify the efficiency of improved clustering algorithm.