Abstract: Intuitionistic fuzzy c-means (IFCM) clustering segmentation algorithm is sensitive to noise and initialization of cluster centroid, which leads to the problem of low accuracy and huge iterations. A novel intuitionistic kernel-based fuzzy C-means clustering algorithm which takes into account local information is proposed for image segmentation. Firstly, in order to solve the problem that centroid of cluster is sensitive to the initial values, a histogram based approach is used to determine the cluster centroid. Secondly, to improve the linear separability of image data, the test data is mapped the high dimensional nonlinear space by introducing kernel function. At the same time, through incorporating the local gray information and spatial information in the objective function and calculating the intuitionistic fuzzy membership degree, which can improve the classification accuracy of the intuitionistic fuzzy clustering. The experiments demonstrate that the proposed algorithm can reduce the number of iterations, improve the classification accuracy, and segment the image effectively. Both in image segmentation and the effectiveness of clustering, the performance of the proposed algorithm is superior to conventional fuzzy clustering methods, include fuzzy c-means (FCM), kernel-based fuzzy c-means(KFCM), intuitionistic fuzzy c-means with spatial constraints(IFCM-S), fuzzy local information c-means (FLICM) and intuitionistic kernel-based fuzzy c-means(IKFCM) algorithms.