Abstract—This paper presents the development of soft clustering and learning vector quantization (LVQ) algorithms that rely on a weighted norm to measure the distance between the feature vectors and their prototypes. The development of LVQ and clustering algorithms is based on the minimization of a reformulation function under the constraint that the generalized mean of the norm weights be constant. According to the proposed formulation, the norm weights can be computed from the data in an iterative fashion together with the prototypes. An error analysis provides some guidelines for selecting the parameter involved in the definition of the generalized mean in terms of the feature variances. The algorithms produced from this formulation are easy to implement and they are almost as fast as clustering algorithms relying on the Euclidean norm. An experimental evaluation on four data sets indicates that the proposed algorithms outperform consistently clustering algorithms relying on the Euclidean norm and they are strong competitors to non-Euclidean algorithms which are computationally more demanding. Index Terms—Clustering, generator function, learning vector quantization (LVQ), non-Euclidean norm, reformulation, reformulation function, weight matrix, weighted norm. I.

Abstract--- Fuzzy c-means clustering (FCM) with spatial constraints (FCM_S) is an effective algorithm suitable for image segmentation. Its effectiveness contributes not only to introduction of fuzziness for belongingness of each pixel but also to exploitation of spatial contextual information. Although the contextual information can raise its insensitivity to noise to some extent, FCM_S (1) still lacks enough robustness to noise and outliers and (2) is not suitable for revealing non-Euclidean structure of the input data due to the use of Euclidean distance (L2 norm). In this paper, to overcome the above problems, we first propose two variants, FCM_S1 and FCM_S2, of FCM_S to aim at simplifying its computation and then extend them, including

Abstract — Fuzzy c-means (FCM) algorithms with spatial constraints (FCM_S) have been proven effective for image segmentation. However, they still have the following disadvantages: 1) Although the introduction of local spatial information to the corresponding objective functions enhances their insensitiveness to noise to some extent, they still lack enough robustness to noise and outliers, especially in absence of prior knowledge of the noise; 2) In their objective functions, there exists a crucial parameter α used to balance between robustness to noise and effectiveness of preserving the details of the image, it is selected generally through experience; 3) The time of segmenting an image is dependent on the image size, and hence the larger the size of the image, the more the segmentation time. In this paper, by incorporating local spatial and gray information together, a novel fast and robust FCM framework for image segmentation, i.e. Fast Generalized Fuzzy c-means clustering algorithms (FGFCM), is proposed. FGFCM can mitigate the disadvantages of FCM_S and at the same time enhances the clustering performance. Furthermore, FGFCM not only includes many existing algorithms, such as fast FCM and Enhanced FCM as its special cases, but also can derive other new algorithms such as FGFCM_S1 and FGFCM_S2 proposed in the rest of this paper. The major characteristics of FGFCM are: 1) to use a new factor Sij as a local (both spatial and gray) similarity measure aiming to guarantee both noise-immunity and

Distances in the well known fuzzy c-means algorithm of Bezdek (1973) are measured by the squared Euclidean distance. Other distances have been used as well in fuzzy clustering. For example, Jajuga (1991) proposed to use the L1-distance and Bobrowski and Bezdek (1991) also used the L∞-distance. For the more general case of Minkowski distance and the case of using a root of the squared Minkowski distance, Groenen and Jajuga (2001) introduced a majorization algorithm to minimize the error. One of the advantages of iterative majorization is that it is a guaranteed descent algorithm, so that every iteration reduces the error until convergence is reached. However, their algorithm was limited to the case of Minkowski parameter between 1 and 2, that is, between the L1-distance and the Euclidean distance. Here, we extend their majorization algorithm to any Minkowski distance with Minkowski parameter greater than (or equal to) 1. This extension also includes the case of the L∞-distance. We also investigate how well this algorithm performs and present an empirical application.