Method, apparatus and system for multimedia model retrieval

• US 8,082,263 B2
• Filed: 09/05/2008
• Issued: 12/20/2011
• Est. Priority Date: 09/06/2007
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: Zhang, Qinwei, Ma, Yanping
• Primary Examiner(s): MORRISON, JAY A
• Application Number:
  US12/205,792
• Publication Number:
  US 20090070329A1
• Time in Patent Office: 1,201 Days
• Field of Search: None
• US Class Current: 707/758
• CPC Class Codes: G06F 16/434 using image data, e.g. images, photos, pictures taken by a user
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

A method, apparatus and system for multimedia model retrieval are provided. The method includes: obtaining parameters of a multimedia model to be retrieved; performing a projection on the multimedia model according to the parameters of the multimedia model so as to obtain a projection image; performing a feature extraction on the projection image; matching a feature extraction result with stored model multimedia file information to obtain a retrieval result; training a support vector machine (SVM) with the multimedia model labeled by a user upon the retrieval result as a training sample set, performing a probability-based classification on the multimedia model by the SVM, and updating the retrieval result with a classification result. The system of the present invention illustrated by embodiments achieves favorable applicability and robustness, so that users may perform a rapid and precise retrieval on massive model data in these fields.

Claims

1. A method for multimedia model retrieval, comprising:

acquiring parameters of a first multimedia model to be retrieved;

performing a projection on the first multimedia model according to the parameters of the first multimedia model so as to obtain a projection image;

performing a feature extraction on the projection image to generate a first feature extraction result;

comparing the first feature extraction result with a plurality of feature extraction results corresponding to a plurality of multimedia models stored in a database so as to obtain a retrieval result, wherein the retrieval result comprises a number of multimedia models;

labeling by a user each of the multimedia models in the retrieval result with a probability value;

training a support vector machine with the labeled multimedia models;

performing a probability-based classification on the plurality of multimedia models stored in the database by using the support vector machine to obtain a classification result; and

updating the retrieval result with the classification result.

2. The method according to claim 1, wherein the performing the feature extraction on the projection image comprises:

performing the feature extraction on the first multimedia model by using a Zernike moment.

3. The method according to claim 1, further comprising:

performing a pre-processing on the parameters of the first multimedia model to be retrieved.

4. The method according to claim 2, further comprising:

performing a pre-processing on the parameters of the first multimedia model to be retrieved.

5. The method according to claim 3, wherein the pre-processing comprises:

performing an isotropic transformation on the first multimedia model; and

performing a vertex sampling according to the first multimedia model after the isotropic transformation.

6. The method according to claim 1, wherein the performing a probability-based classification on the plurality of multimedia models stored in a database by using the support vector machine to obtain a classification result comprises:

forecasting each of the multimedia models in the database, obtaining relevant or irrelevant probability values attributed to each of the multimedia models in the database and revising a similarity degree by the probability values.

7. The method according to claim 1, wherein the performing the projection on the first multimedia model according to the parameters of the first multimedia model comprises:

performing a spherical projection on a three-dimensional multimedia model and calculating a spherical projection image.

8. The method according to claim 1, further comprising:

sorting the retrieval result obtained by comparing or the retrieval result obtained after updating.

9. The method according to claim 1, wherein a file format of the parameters of the first multimedia model to be retrieved is a three-dimensional model file format .3ds or a text file format .txt.

10. The method according to claim 1, wherein the probability-based classification comprises a similarity classification which is based on posterior probability.

11. An apparatus for multimedia model retrieval, comprising:

at least one hardware processor operable to;

acquire parameters of a first multimedia model to be retrieved;

generate a projection image from the first multimedia model according to the parameters of the first multimedia model;

perform a feature extraction on the projection image to generate a first feature extraction result;

compare the first feature extraction result with a plurality of feature extraction results corresponding to a plurality of multimedia models stored in a database so as to obtain a retrieval result, wherein the retrieval result comprises a number of multimedia models; and

train a support vector machine with multimedia models labeled by a user upon the retrieval result with a probability value, and perform a probability-based classification on the plurality of multimedia models stored in a database by the support vector machine to obtain a classification result, and update the retrieval result with the classification result.

12. The apparatus according to claim 11, wherein the at least one hardware processor is further operable to perform a pre-processing on the parameters of the first multimedia model to be retrieved.

13. The apparatus according to claim 12,

wherein the at least one hardware processor is further operable to perform an isotropic transformation on the first multimedia model;

and

to perform a vertex sampling on the first multimedia model after the isotropic transformation.

14. The apparatus according to claim 11,

wherein the at least one hardware processor is further operable to employ the multimedia models manually labeled by a user upon the retrieval result with a probability value as a training sample and train according to the training sample to obtain the support vector machine;

and

to perform a probability-based classification on the plurality of multimedia models stored in a database by the support vector machine to obtain a classification result, and update the retrieval result with the classification result.

15. The apparatus according to claim 11, wherein the at least one hardware processor is further operable to sort the retrieval result obtained by comparing or the retrieval result obtained after updating.

16. A system for multimedia model retrieval, comprising:

a database management system adapted to store multimedia model file information;

a model retrieval apparatus adapted to acquire parameters of a first multimedia model to be retrieved, perform a projection on the first multimedia model according to the parameters of the first multimedia model so as to obtain a projection image, perform a feature extraction on the projection image to generate a first feature extraction result, comparing the first feature extraction result with a plurality of feature extraction results corresponding to a plurality of multimedia models stored in the database management system to obtain a retrieval result, wherein the retrieval result comprises a number of multimedia models, train a support vector machine with the multimedia models labeled by a user upon the retrieval result with a probability value, perform a probability-based classification on the plurality of multimedia models stored in a database by using the support vector machine to obtain a classification result and update the retrieval result with the classification result.