Date of Award

2019

Publisher

North Dakota State University

Document Type

Master's Paper

Degree Awarded

Master of Science (MS)

Program

Software Engineering

Department

Computer Science

College

Engineering

Faculty Advisor

Nygard, Kendall

Description

A Content-Based Image Retrieval (CBIR) system can help in detecting trademark infringement. This paper describes an improvement and extension of previous work for the existing Universal Model for a CBIR system, which only uses texture along with color to produce a reliable and capable system. To enhance the security and efficiency of the CBIR based Universal Model, the extension is a Multi Feature CBIR Model that can utilize many parameters including color, texture, and shape with the facility of choosing a suitable and flexible set of features. The supported selection techniques give priority to individual features and help increase the efficiency of the system. I am going to provide write-ups with the proven computational work over the existing feature methods of the Universal Model, which becomes the foundation for the Multi-Feature CBIR Model. In comparison to the Universal Model, the Multi-Feature CBIR Model can obtain higher recall and precision values.

Rights

NDSU Policy 190.6.2

Rights Link

https://www.ndsu.edu/fileadmin/policy/190.pdf

Handle Identifier

https://hdl.handle.net/10365/29757

Download

Share

COinS