Abstract
A novel quality metric for binary edge maps, called the structural edge quality metric (SEQM), is proposed in this work. First, we define the matching cost between an edge pixel in a detected edge map and its candidate matching pixel in the ground-truth edge map. The matching cost includes a structural term, as well as a positional term, to measure the discrepancy between the local structures around the two pixels. Then, we determine the optimal matching pairs of pixels using the graph-cut optimization, in which a smoothness term is employed to take into account global edge structures in the matching. Finally, we sum up the matching costs of all edge pixels to determine the quality index of the detected edge map. Simulation results demonstrate that the proposed SEQM provides more faithful and reliable quality indices than conventional metrics.
| Original language | English |
|---|---|
| Title of host publication | 2012 IEEE Visual Communications and Image Processing, VCIP 2012 |
| DOIs | |
| Publication status | Published - 2012 Dec 1 |
| Event | 2012 IEEE Visual Communications and Image Processing, VCIP 2012 - San Diego, CA, United States Duration: 2012 Nov 27 → 2012 Nov 30 |
Other
| Other | 2012 IEEE Visual Communications and Image Processing, VCIP 2012 |
|---|---|
| Country | United States |
| City | San Diego, CA |
| Period | 12/11/27 → 12/11/30 |
Fingerprint
Keywords
- binary edge map
- edge quality assessment
- Image quality assessment
- pixel matching
- structural similarity
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
Cite this
SEQM : Edge quality assessment based on structural pixel matching. / Jang, Won Dong; Kim, Chang-Su.
2012 IEEE Visual Communications and Image Processing, VCIP 2012. 2012. 6410731.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - SEQM
T2 - Edge quality assessment based on structural pixel matching
AU - Jang, Won Dong
AU - Kim, Chang-Su
PY - 2012/12/1
Y1 - 2012/12/1
N2 - A novel quality metric for binary edge maps, called the structural edge quality metric (SEQM), is proposed in this work. First, we define the matching cost between an edge pixel in a detected edge map and its candidate matching pixel in the ground-truth edge map. The matching cost includes a structural term, as well as a positional term, to measure the discrepancy between the local structures around the two pixels. Then, we determine the optimal matching pairs of pixels using the graph-cut optimization, in which a smoothness term is employed to take into account global edge structures in the matching. Finally, we sum up the matching costs of all edge pixels to determine the quality index of the detected edge map. Simulation results demonstrate that the proposed SEQM provides more faithful and reliable quality indices than conventional metrics.
AB - A novel quality metric for binary edge maps, called the structural edge quality metric (SEQM), is proposed in this work. First, we define the matching cost between an edge pixel in a detected edge map and its candidate matching pixel in the ground-truth edge map. The matching cost includes a structural term, as well as a positional term, to measure the discrepancy between the local structures around the two pixels. Then, we determine the optimal matching pairs of pixels using the graph-cut optimization, in which a smoothness term is employed to take into account global edge structures in the matching. Finally, we sum up the matching costs of all edge pixels to determine the quality index of the detected edge map. Simulation results demonstrate that the proposed SEQM provides more faithful and reliable quality indices than conventional metrics.
KW - binary edge map
KW - edge quality assessment
KW - Image quality assessment
KW - pixel matching
KW - structural similarity
UR - http://www.scopus.com/inward/record.url?scp=84874026898&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84874026898&partnerID=8YFLogxK
U2 - 10.1109/VCIP.2012.6410731
DO - 10.1109/VCIP.2012.6410731
M3 - Conference contribution
SN - 9781467344050
BT - 2012 IEEE Visual Communications and Image Processing, VCIP 2012
ER -