Abstract
In this paper the usage of multi-step segmentation for near-duplicate image recognition is investigated. The clustering of image pixels brightness is used for segmentation. The clustering is realized by means of a recurrent neural network. The search pattern based on the rank distributions of the brightness clusters cardinality is suggested. Experimental results on the near-duplicate image recognition based on the application of the suggested search pattern are given. It is shown that the use of a multi-step segmentation and rank distributions of the brightness clusters cardinality allows one to successfully recognize the duplicates, which are received by a considerable visual distortion of the original image or by the change of image scale.
| Original language | English |
|---|---|
| Pages (from-to) | 811-817 |
| Number of pages | 7 |
| Journal | Computer Optics |
| Volume | 38 |
| Issue number | 4 |
| Publication status | Published - 2014 |
Fingerprint
Keywords
- Clustering
- Image
- Image recognition
- Pixel
- Point mapping
- Ranking distribution
- Recurrent neural network
- Segmentation
ASJC Scopus subject areas
- Atomic and Molecular Physics, and Optics
- Electrical and Electronic Engineering
- Computer Science Applications
Cite this
Near-duplicate image recognition based on the rank distribution of the brightness clusters cardinality. / Nemirovskiy, V. B.; Stoyanov, A. K.
In: Computer Optics, Vol. 38, No. 4, 2014, p. 811-817.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Near-duplicate image recognition based on the rank distribution of the brightness clusters cardinality
AU - Nemirovskiy, V. B.
AU - Stoyanov, A. K.
PY - 2014
Y1 - 2014
N2 - In this paper the usage of multi-step segmentation for near-duplicate image recognition is investigated. The clustering of image pixels brightness is used for segmentation. The clustering is realized by means of a recurrent neural network. The search pattern based on the rank distributions of the brightness clusters cardinality is suggested. Experimental results on the near-duplicate image recognition based on the application of the suggested search pattern are given. It is shown that the use of a multi-step segmentation and rank distributions of the brightness clusters cardinality allows one to successfully recognize the duplicates, which are received by a considerable visual distortion of the original image or by the change of image scale.
AB - In this paper the usage of multi-step segmentation for near-duplicate image recognition is investigated. The clustering of image pixels brightness is used for segmentation. The clustering is realized by means of a recurrent neural network. The search pattern based on the rank distributions of the brightness clusters cardinality is suggested. Experimental results on the near-duplicate image recognition based on the application of the suggested search pattern are given. It is shown that the use of a multi-step segmentation and rank distributions of the brightness clusters cardinality allows one to successfully recognize the duplicates, which are received by a considerable visual distortion of the original image or by the change of image scale.
KW - Clustering
KW - Image
KW - Image recognition
KW - Pixel
KW - Point mapping
KW - Ranking distribution
KW - Recurrent neural network
KW - Segmentation
UR - http://www.scopus.com/inward/record.url?scp=84922545284&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84922545284&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:84922545284
VL - 38
SP - 811
EP - 817
JO - Computer Optics
JF - Computer Optics
SN - 0134-2452
IS - 4
ER -