TY - GEN
T1 - An improved technology for target detection in images
AU - Li, Gaoliang
AU - Zhao, Yan
AU - Wu, Falin
AU - Zhang, Shuo
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/11/14
Y1 - 2014/11/14
N2 - It is difficult to detect the target area of the image which has complex gray scale information in the field of industrial detection. So in order to improve the accuracy of detection, this paper proposed improved image segmentation method based on the region of interest. In the proposed method, the authors extracted regions of interest from the detected image that remove the effects of the complex environmental condition. In addition, dynamic threshold algorithm is used which is appropriate for extracting the target area from the region of interest. To make the algorithm more precise, the paper use mathematical morphology method to process the result which is segmented by dynamic threshold algorithm. The experimental results show that target area of the image can be extracted very accurately across a large number of test-cases. This method can overcome the limitations of traditional segmentation algorithm effectively, and it has advantages of fast detection speed, stable robustness and high efficiency.
AB - It is difficult to detect the target area of the image which has complex gray scale information in the field of industrial detection. So in order to improve the accuracy of detection, this paper proposed improved image segmentation method based on the region of interest. In the proposed method, the authors extracted regions of interest from the detected image that remove the effects of the complex environmental condition. In addition, dynamic threshold algorithm is used which is appropriate for extracting the target area from the region of interest. To make the algorithm more precise, the paper use mathematical morphology method to process the result which is segmented by dynamic threshold algorithm. The experimental results show that target area of the image can be extracted very accurately across a large number of test-cases. This method can overcome the limitations of traditional segmentation algorithm effectively, and it has advantages of fast detection speed, stable robustness and high efficiency.
KW - Dynamic Threshold
KW - Mathematical Morphology
KW - Object Detection
UR - https://www.scopus.com/pages/publications/84916594754
U2 - 10.1109/IST.2014.6958435
DO - 10.1109/IST.2014.6958435
M3 - 会议稿件
AN - SCOPUS:84916594754
T3 - IST 2014 - 2014 IEEE International Conference on Imaging Systems and Techniques, Proceedings
SP - 1
EP - 5
BT - IST 2014 - 2014 IEEE International Conference on Imaging Systems and Techniques, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE International Conference on Imaging Systems and Techniques, IST 2014
Y2 - 14 October 2014 through 17 October 2014
ER -