Saliency-Based Image Object Indexing and Retrieval

Automatic classification and interpretation of objects present in 2D images is a key issue for various computer vision applications. In particular, when considering image/video, indexing, and retrieval applications, automatically labeling in a semantically pertinent manner/huge multimedia databases still remains a challenge. This paper examines the issue of still image object categorization. The objective is to associate semantic labels to the 2D objects present in natural images. The principle of the proposed approach consists of exploiting categorized 3D model repositories to identify unknown 2D objects, based on 2D/3D matching techniques. The authors use 2D/3D shape indexing methods, where 3D models are described through a set of 2D views. Experimental results, carried out on both MPEG-7 and Princeton 3D models databases, show recognition rates of up to 89.2%.

Download Full-text

A NEW APPROACH TO SHAPE-BASED IMAGE RETRIEVAL

International Journal of Computing ◽

10.47839/ijc.7.3.530 ◽

2014 ◽

pp. 99-106

Author(s):

Mehdi Chehel Amirani ◽

Zahra Sadeghi Gol ◽

Ali Asghar Beheshti Shirazi

Keyword(s):

Image Retrieval ◽

Curvature Function ◽

Feature Points ◽

Retrieval Performance ◽

New Approach ◽

Large Databases ◽

Indexing And Retrieval ◽

Active Research ◽

Low Dimensional ◽

Object Indexing

Content-based image retrieval (CBIR) is very active research topic in recent years. This paper introduces a new approach to shape-based image retrieval. At first, feature points are determined at the boundary of the shape as the extremums of a new version of the curvature function and the initial features are calculated at these points. The proposed method utilizes a supervised system for nonlinear combination of initial features for extraction of efficient and low dimensional feature vector for each shape. The retrieval performance of the approach is illustrated using the MPEG-7 shape database. Our experiments show that the proposed method is well suited for object indexing and retrieval in large databases.

Download Full-text

Efficient Object Indexing and Retrieval Using Partial Dominant Orientation Descriptor

2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV) ◽

10.1109/cgiv.2016.62 ◽

2016 ◽

Cited By ~ 1

Author(s):

Abdessamad Elboushaki ◽

Rachida Hannane ◽

Karim Afdel ◽

Lahcen Koutti

Keyword(s):

Dominant Orientation ◽

Indexing And Retrieval ◽

Object Indexing

Download Full-text

A New Partial 3D Object Indexing and Retrieval Approach Combining 2D slices and Apriori Algorithm

Scientific Visualization ◽

10.26583/sv.12.2.09 ◽

2020 ◽

Vol 12 (2) ◽

Author(s):

I.O. Taybi ◽

T. Gadi ◽

R. Alaoui

Keyword(s):

Apriori Algorithm ◽

3D Object ◽

Indexing And Retrieval ◽

Object Indexing

Download Full-text

Delaunay triangulation for image object indexing: a novel method for shape representation

10.1117/12.333884 ◽

1998 ◽

Cited By ~ 12

Author(s):

Yi Tao ◽

William I. Grosky

Keyword(s):

Delaunay Triangulation ◽

Shape Representation ◽

Novel Method ◽

Object Indexing ◽

Image Object

Download Full-text

3D Model-Based Semantic Categorization of Still Image 2D Objects

Multimedia Data Engineering Applications and Processing ◽

10.4018/978-1-4666-2940-0.ch008 ◽

2013 ◽

pp. 151-169

Author(s):

Raluca-Diana Petre ◽

Titus Zaharia

Keyword(s):

3D Model ◽

3D Models ◽

Multimedia Databases ◽

Still Image ◽

Shape Indexing ◽

Indexing And Retrieval ◽

Video Indexing And Retrieval ◽

Computer Vision Applications ◽

Matching Techniques ◽

Image Object

Automatic classification and interpretation of objects present in 2D images is a key issue for various computer vision applications. In particular, when considering image/video, indexing, and retrieval applications, automatically labeling in a semantically pertinent manner/huge multimedia databases still remains a challenge. This paper examines the issue of still image object categorization. The objective is to associate semantic labels to the 2D objects present in natural images. The principle of the proposed approach consists of exploiting categorized 3D model repositories to identify unknown 2D objects, based on 2D/3D matching techniques. The authors use 2D/3D shape indexing methods, where 3D models are described through a set of 2D views. Experimental results, carried out on both MPEG-7 and Princeton 3D models databases, show recognition rates of up to 89.2%.

Download Full-text