Advanced 3D Model Retrieval System

Summary of the technology

This invention presents a novel method for document retrieval using three-dimensional (3D) models reconstructed from physical objects. By converting images of objects into 3D point clouds, the system generates feature vector representations that capture both local and global geometric properties. These representations enable effective retrieval and classification of documents related to the objects. For example, a multi-view image of a mechanical part can be transformed into a 3D model, allowing for precise searches in engineering databases.

Georgetown University

Details of the Technology Offer

BACKGROUND

The field of document retrieval often relies on two-dimensional images, which can inadequately represent the complexity of three-dimensional objects. Current systems struggle with accurately retrieving similar objects due to the limitations of multi-view images. This innovation addresses these challenges by utilizing 3D models, enhancing the accuracy and effectiveness of object identification and classification in various databases, including patents and industrial designs.

Benefit

  • Increases retrieval accuracy by using comprehensive 3D models instead of limited 2D images.
  • Enhances classification capabilities through advanced geometric analysis.
  • Reduces time spent on document searches by providing more relevant results.
  • Facilitates better organization and management of engineering and patent databases.
  • Supports various applications in industries requiring precise object identification.

Market Application

  • Potential use in engineering databases for parts and components retrieval.
  • Possible application in patent offices for identifying similar designs.
  • Can be implemented in governmental document repositories for improved access to physical models.
  • Suitable for educational institutions needing accurate representations of physical objects.
  • Applicable in museums or archives for digital preservation and retrieval of artifacts.

Intellectual property status

Granted Patent

Patent number : Patent No. 12,073,646

Where : USA

Related Keywords

  • Archivistics/Documentation/Technical Documentation
  • Engineering
  • point cloud processing
  • neural networks
  • 3d model retrieval
  • document search
  • feature vectors

About Georgetown University

Our mission is to advance GU’s innovations through strategic alliances and new venture creation, to facilitate the translation of research breakthroughs into tangible solutions, and to cultivate a dynamic and inclusive environment for entrepreneurship. We advance this mission in support of the GU community and for the benefit of society.

Georgetown University

Never miss an update from Georgetown University

Create your free account to connect with Georgetown University and thousands of other innovative organizations and professionals worldwide

Georgetown University

Send a request for information
to Georgetown University

About Technology Offers

Technology Offers on Innoget are directly posted
and managed by its members as well as evaluation of requests for information. Innoget is the trusted open innovation and science network aimed at directly connect industry needs with professionals online.

Help

Need help requesting additional information or have questions regarding this Technology Offer?
Contact Innoget support