In order to achieve robust dim and small target detection in a infrared cloud clutter,a new approach based on fuzzy classification is proposed. Different kinds of class regions are extracted from the query image to get several classification models to describe different classifications in the image exactly.The classification based on such models will classify the image effectively and achieve robust dim and small target detection. Firstly,the dim and small infrared target image are analyzed and eleven kinds of class regions are proposed to describe the sky,cloud and the target in the image. Then,class feature vectors and class kernels are defined,and the class kernels of eleven class regions are extracted from the query image. Finally,the class similar coefficient and class similarity degree are defined according to the fuzzy classification theory. The target detection is achieved by reserving a dim and small target class,after image classification and class merge are performed. Experimental results show that the proposed method can classifly different kinds of regions in the dim and small infrared target image with a Signal Noise Ratio(SNR) larger than 1.0 exactly and can realize the robust dim and small infrared target detection in heavy background clutter.