Clustering method and related device

Abstract

The embodiment of the present disclosure discloses a clustering method and a related device. The clustering method uses the Rank-Order distance between the classes to merge the qualified classes, thereby reducing the number of classes; and then, using each object in the class Calculate the degree of intra-class aggregation by calculating the distance between them, and split the objects whose distance between objects in the class is smaller than the degree of aggregation within the class into new classes until all the classes are split. Then, the split classes are iteratively merged and split again until each class can no longer be split, and the clusters containing multiple objects and the class containing a single object are determined, so as to realize the comparison of the dissimilarity in the clustering process Large objects are eliminated to improve the accuracy of clustering results. In particular, when there are many objects in the data set but few objects belonging to the same class, the accuracy of the clustering result is relatively high.

Description

technical field [0001] The present disclosure relates to the field of computer technology, in particular to a clustering method and a related device. Background technique [0002] Clustering is the process of dividing a collection of physical or abstract objects into multiple classes composed of similar objects, that is, the process of classifying objects into different classes (clusters). Objects in the same class have great similarity and different Objects between classes have great dissimilarity. The concept of "class" is used below, and it should be noted that the meaning of "class" and "cluster" in this article are the same. [0003] For example, when the clustering method is used for the classification of face pictures, the pictures belonging to the same person are divided into one category, and the related clustering method uses the Rank-Order distance to measure the similarity between two faces, which can classify the same person pictures clustered together. Howev...

AI Technical Summary

Problems solved by technology

However, when the number of faces contained in a push picture is relatively large, and the pictures of each person are relatively small, the accuracy rate of the clustering result of this clustering method is very low

Images