Laser & Optoelectronics Progress, Volume. 55, Issue 12, 121003(2018)
Image Salient Object Detection Combined with Deep Learning
Figures & Tables(7)
Fig. 2. Examples of image processing. (a) Initial image; (b) convolved images; (c) clustered images; (d) CRF optimized images; (e) truth value chart
Fig. 4. Comparison among P-R curves by several algorithms. (a) ECSSD; (b) DUT-ORMON
Fig. 5. Comparison among image salient detection results by several algorithms. (a) Initial images; (b) GT; (c) proposed algorithm; (d) DCL; (e) DRFI; (f) DS; (g) ELD; (h) FT; (i) MDF; (j) QCUT; (k) RC; (l) RFCN
Table 1. Comparison of F and MAE
View tableTable 1. Comparison of F and MAE
Algorithm ECSSD DUT-OMRON F MAE F MAE Proposed 0.877 0.046 0.689 0.048 DCL 0.863 0.047 0.681 0.053 DRFI 0.732 0.080 0.545 0.083 DS 0.824 0.075 0.598 0.062 ELD 0.814 0.050 0.609 0.059 FT 0.379 0.121 0.311 0.106 MDF 0.795 0.079 0.603 0.064 QCUT 0.743 0.121 0.495 0.072 RC 0.680 0.098 0.678 0.110 RFCN 0.873 0.047 0.681 0.057
Table 2. Comparison of time consuming
View tableTable 2. Comparison of time consuming
Algorithm Proposed DCL DS ELD MDF RFCN Time /s 0.3 1.5 1.1 0.5 8 4.6
Tools
Get Citation
Copy Citation Text
Heng Zhao, Weisheng An. Image Salient Object Detection Combined with Deep Learning[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121003
Paper Information
Category: Image Processing
Received: May. 14, 2018
Accepted: Jun. 8, 2018
Published Online: Aug. 1, 2019
The Author Email: Zhao Heng (zhlance@foxmail.com), An Weisheng (anweisheng@home.swjtu.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20