The composite insulator surface hydrophobicity detection is one of the primary means to determine its anti flashover performance. This paper introduces the sparse representation classification algorithm to classify composite insulator's hydrophobic image. It uses the smallest normal method to calculate the coefficient of sparse representation and searches the training sample image that best matches the test image by calculating the minimum residual image, therefore the test image's hydrophobic HC level is accurately identified. The algorithm has successfully avoided complicated feature extraction in general pattern recognition algorithms, thus providing a new way for composite insulator's hydrophobic image recognition and detection. The experimental results show that the method can be effectively applied in the composite insulator's hydrophobic image classification.