Method and system for semi-automatic marking of three-dimensional (3D) model based on fuzzy K-nearest neighbor

Abstract

The invention discloses a method for semi-automatic marking of a three-dimensional (3D) model based on fuzzy K-nearest neighbor. The method comprises the following steps of: firstly establishing a 3D model training base; then extracting characteristic vectors of the input model to be marked, and matching similarity of the model with the model in the training base to find k neighbor models; then classifying by using a fuzzy K-nearest neighbor classifier to obtain a fuzzy classification result; and finally calculating classification uncertainty, and marking the models which are uncertain in classification by a feedback and retraining studying method. The marked models are added into the 3D model training base to further expand the model base. In the method for semi-automatic marking of the 3D model, the fuzzy classification result comprising more information is used; classification labels of the models with uncertain classification are determined by aid of feedback so as to solve overlapping problem of feature clustering edges; and a mechanism for training study is used to further automatically mark.

Description

technical field [0001] The invention relates to a three-dimensional model labeling method, in particular to a semi-automatic labeling method for a three-dimensional model based on fuzzy K-nearest neighbors. Background technique [0002] With the improvement of computer software and hardware performance and the development of computer graphics, as well as the emergence of many excellent 3D model modeling software, 3D models are used more and more widely and play an increasingly important role in many fields. For example: virtual reality, architectural design, machinery manufacturing, 3D games, 3D movies, computer-aided design, archaeology, biology, medicine and other fields, 3D is becoming a popular trend. The increasingly developed Internet technology provides convenient conditions for people to share and process 3D models, and more and more 3D model libraries have emerged, such as Google 3D Warehouse, 3D Café, etc. How to quickly find the desired model has become another h...

AI Technical Summary

Problems solved by technology

[0005] The solution ideas of the above literature have the following deficiencies: 1) Samples near the edge of the clustering area are prone to misjudgment, and there are many reasons for misjudgment: the feature itself is not distinguishable enough, the meaning of the category itself is vague, etc.

In this case, if the definite classification results are used, the wrong category labels will often be obtained; 2) the automation of model annotation is not enough, and too much depends on human judgment; 3) the 3D model training database maps feature information for semantic vocabulary , and these features obtained by the average method cannot accurately describe the semantic vocabulary, and also lose a lot of content information of the model

Images