Segmentation Tree Based Multiple Object Image Retrieval

2012 ◽  
Author(s):  
Wei-Bang Chen ◽  
Chengcui Zhang ◽  
Song Gao
Keyword(s):  
Image Retrieval ◽  
Object Image ◽  
Multiple Object

An Innovative Multiple-Object Image Retrieval Framework Using Hierarchical Region Tree

2013 ◽  
Vol 4 (3) ◽  
pp. 1-23 ◽  
Author(s):  
Wei-Bang Chen ◽  
Chengcui Zhang
Keyword(s):  
Image Segmentation ◽  
Image Retrieval ◽  
Negative Impact ◽  
Image Representation ◽  
Object Image ◽  
Object Retrieval ◽  
Hierarchical Tree ◽  
Multiple Object ◽  
Tree Construction ◽  
Object Based

Inaccurate image segmentation often has a negative impact on object-based image retrieval. Researchers have attempted to alleviate this problem by using hierarchical image representation. However, these attempts suffer from the inefficiency in building the hierarchical image representation and the high computational complexity in matching two hierarchically represented images. This paper presents an innovative multiple-object retrieval framework named Multiple-Object Image Retrieval (MOIR) on the basis of hierarchical image representation. This framework concurrently performs image segmentation and hierarchical tree construction, producing a hierarchical region tree to represent the image. In addition, an efficient hierarchical region tree matching algorithm is designed for multiple-object retrieval with a reasonably low time complexity. The experimental results demonstrate the efficacy and efficiency of the proposed approach.

scholarly journals A Comparative Analysis of the Zernike Moments for Single Object Retrieval

2019 ◽  
Vol 16 (2(SI)) ◽  
pp. 0504 ◽  
Author(s):  
Abu Bakar Et al.
Keyword(s):  
Image Retrieval ◽  
Shape Representation ◽  
Outer Boundary ◽  
Zernike Moments ◽  
Zernike Moment ◽  
Experimental Investigations ◽  
Object Image ◽  
Single Object ◽  
Object Retrieval ◽  
Object Shape

Zernike Moments has been popularly used in many shape-based image retrieval studies due to its powerful shape representation. However its strength and weaknesses have not been clearly highlighted in the previous studies. Thus, its powerful shape representation could not be fully utilized. In this paper, a method to fully capture the shape representation properties of Zernike Moments is implemented and tested on a single object for binary and grey level images. The proposed method works by determining the boundary of the shape object and then resizing the object shape to the boundary of the image. Three case studies were made. Case 1 is the Zernike Moments implementation on the original shape object image. In Case 2, the centroid of the shape object image in Case 1 is relocated to the center of the image. In Case 3, the proposed method first detect the outer boundary of the shape object and then resizing the object to the boundary of the image. Experimental investigations were made by using two benchmark shape image datasets showed that the proposed method in Case 3 had demonstrated to provide the most superior image retrieval performances as compared to both the Case 1 and Case 2. As a conlusion, to fully capture the powerful shape representation properties of the Zernike moment, a shape object should be resized to the boundary of the image.

Sign in / Sign up

Export Citation Format

Share Document