Analysis distances for similarity estimation by Fuzzy C-Mean algorithm

Similarity judgments are considered to be a valuable tool in the study of human perception and cognition, and play a central role in theories of human knowledge representation. Generally, a multidimensional vector is treated as a point of the feature space, we calculate the distance between the points to measure the similarity. The most popular distance measures maybe Euclidean distance and Manhattan distance. In this paper, we present the character of different distances using the FCM clustering algorithm based on statistical analysis. Experiment results show that the traditional similarity estimation methods can NOT reflect the message of shape similarity, using Morphology similarity distance (MSD) for similarity measurement, both the size and the shape similarity of the objects are taken into account.