Abstract
A new algorithm for automatic extraction of interesting objects is proposed in this paper. The proposed algorithm can be summarized in two steps. First, segmentation of color image discriminating interesting objects and backgrounds is performed. According to the research stating, 'humans perceive things by contracting them into three to four essential colors,' a color image is segmented into three regions utilizing k-mean algorithm, followed by the merger of the regions performed when their similarities exceeds the critical value that is drawn from the calculation of the histogram similarity. Second, identifying an interesting object out of the segmented image, generated upon the image composition theory, is performed. To have a good picture, it is important to adjust positions of interesting objects as the picture composition theory. Extracting objects is a retro-deduction process using a weighted mask based on the triangular composition of picture. To show merits of the proposed method, experiments are conducted over 400 images in comparison with recently proposed k-means connectivity constraint and graph-based image segmentation methods.
| Original language | English |
|---|---|
| Pages (from-to) | 7210-7218 |
| Number of pages | 9 |
| Journal | Expert Systems with Applications |
| Volume | 36 |
| Issue number | 3 PART 2 |
| DOIs | |
| Publication status | Published - 2009 Apr 1 |
Fingerprint
Keywords
- Extracting object of interest
- Image composition
- Positions of objects
- Segmentation
- Similarity
- Weighted mask
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Engineering(all)
Cite this
Development of expert system for extraction of the objects of interest. / Kang, Seon D.; Park, Sang Sung; Yoo, Hun W.; Shin, Young Geun; Jang, Dong Sik.
In: Expert Systems with Applications, Vol. 36, No. 3 PART 2, 01.04.2009, p. 7210-7218.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Development of expert system for extraction of the objects of interest
AU - Kang, Seon D.
AU - Park, Sang Sung
AU - Yoo, Hun W.
AU - Shin, Young Geun
AU - Jang, Dong Sik
PY - 2009/4/1
Y1 - 2009/4/1
N2 - A new algorithm for automatic extraction of interesting objects is proposed in this paper. The proposed algorithm can be summarized in two steps. First, segmentation of color image discriminating interesting objects and backgrounds is performed. According to the research stating, 'humans perceive things by contracting them into three to four essential colors,' a color image is segmented into three regions utilizing k-mean algorithm, followed by the merger of the regions performed when their similarities exceeds the critical value that is drawn from the calculation of the histogram similarity. Second, identifying an interesting object out of the segmented image, generated upon the image composition theory, is performed. To have a good picture, it is important to adjust positions of interesting objects as the picture composition theory. Extracting objects is a retro-deduction process using a weighted mask based on the triangular composition of picture. To show merits of the proposed method, experiments are conducted over 400 images in comparison with recently proposed k-means connectivity constraint and graph-based image segmentation methods.
AB - A new algorithm for automatic extraction of interesting objects is proposed in this paper. The proposed algorithm can be summarized in two steps. First, segmentation of color image discriminating interesting objects and backgrounds is performed. According to the research stating, 'humans perceive things by contracting them into three to four essential colors,' a color image is segmented into three regions utilizing k-mean algorithm, followed by the merger of the regions performed when their similarities exceeds the critical value that is drawn from the calculation of the histogram similarity. Second, identifying an interesting object out of the segmented image, generated upon the image composition theory, is performed. To have a good picture, it is important to adjust positions of interesting objects as the picture composition theory. Extracting objects is a retro-deduction process using a weighted mask based on the triangular composition of picture. To show merits of the proposed method, experiments are conducted over 400 images in comparison with recently proposed k-means connectivity constraint and graph-based image segmentation methods.
KW - Extracting object of interest
KW - Image composition
KW - Positions of objects
KW - Segmentation
KW - Similarity
KW - Weighted mask
UR - http://www.scopus.com/inward/record.url?scp=58349120999&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=58349120999&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2008.09.062
DO - 10.1016/j.eswa.2008.09.062
M3 - Article
AN - SCOPUS:58349120999
VL - 36
SP - 7210
EP - 7218
JO - Expert Systems with Applications
JF - Expert Systems with Applications
SN - 0957-4174
IS - 3 PART 2
ER -