TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region
DOI: 10.1109/tencon.2003.1273228
|View full text |Cite
|
Sign up to set email alerts
|

Comparison of similarity metrics for texture image retrieval

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
61
0
6

Publication Types

Select...
5
3
2

Relationship

0
10

Authors

Journals

citations
Cited by 122 publications
(67 citation statements)
references
References 9 publications
0
61
0
6
Order By: Relevance
“…Such approaches have involved using general multimedia processing techniques for internal representation of events in lifelogging such as using MPEG-7 visual features, Salembier and Sikora (2002), SIFT (Scalable Invariant Feature Transformations), Lowe (2004), SURF (Speeded up Robust Features), Bay et al (2006), search using a bag of visual words approach, Nistér and Stewnius (2006), and others. This work involves exploring image feature vector similarity options, Kokare et al (2003); Rubner et al (2000), and also merging different data sources together, Montague and Aslam (2001); Fox and Shaw (1993). All similar approaches generate signatures for a given image from an event.…”
Section: Annotating Lifelogs -Whatmentioning
confidence: 99%
“…Such approaches have involved using general multimedia processing techniques for internal representation of events in lifelogging such as using MPEG-7 visual features, Salembier and Sikora (2002), SIFT (Scalable Invariant Feature Transformations), Lowe (2004), SURF (Speeded up Robust Features), Bay et al (2006), search using a bag of visual words approach, Nistér and Stewnius (2006), and others. This work involves exploring image feature vector similarity options, Kokare et al (2003); Rubner et al (2000), and also merging different data sources together, Montague and Aslam (2001); Fox and Shaw (1993). All similar approaches generate signatures for a given image from an event.…”
Section: Annotating Lifelogs -Whatmentioning
confidence: 99%
“…where L 1 (, ), D can (, ) denotes the Manhattan and the Canberra distance [50] respectively, each one normalized to the [0,1] space. The overall similarity between two 3D objects is measured by computing the distance between the sets of features of the same aligned version and the comparison that gives the minimum distance between the two alignments, sets the final score.…”
Section: Features Weighing and Matchingmentioning
confidence: 99%
“…In order to validate the performance of the proposed method, the precision and recall measures [12] are used, which are given in equations (17) Where ⋅ returns the size of the set. The precision (P) represents the ratio of the number of images relevant to the query image among retrieved images to the number of retrieved images.…”
Section: Measure Of Performancementioning
confidence: 99%