비네팅효과 감소와 가변학습률로 보완한 신경망 구조의 불균일 보정
Scene-based Nonuniformity Correction for Neural Network Complemented by Reducing Lense Vignetting Effect and Adaptive Learning rate
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, reducing lense Vignetting effect and adaptive learning rate method are proposed to complement Scribner’s neural network for nuc algorithm which is the effective algorithm in statistic SBNUC algorithm. Proposed reducing vignetting effect method is updated weight and bias each differently using different cost function. Proposed adaptive learning rate for updating weight and bias is using sobel edge detection method, which has good result for boundary condition of image. The ordinary statistic SBNUC algorithm has problem to compensate lense vignetting effect, because statistic algorithm is updated weight and bias by using gradient descent method, so it should not be effective for global weight problem same like, lense vignetting effect. We employ the proposed methods to Scribner’s neural network method(NNM) and Torres’s reducing ghosting correction for neural network nuc algorithm(improved NNM), and apply it to real-infrared detector image stream. The result of proposed algorithm shows that it has 10dB higher PSNR and 1.5 times faster convergence speed then the improved NNM Algorithm
Abstract
In this paper, reducing lense Vignetting effect and adaptive learning rate method are proposed to complement Scribner’s neural network for nuc algorithm which is the effective algorithm in statistic SBNUC algorithm. Proposed reducing vignetting effect method is updated weight and bias each differently using different cost function. Proposed adaptive learning rate for updating weight and bias is using sobel edge detection method, which has good result for boundary condition of image. The ordinary statistic SBNUC algorithm has problem to compensate lense vignetting effect, because statistic algorithm is updated weight and bias by using gradient descent method, so it should not be effective for global weight problem same like, lense vignetting effect. We employ the proposed methods to Scribner’s neural network method(NNM) and Torres’s reducing ghosting correction for neural network nuc algorithm(improved NNM), and apply it to real-infrared detector image stream. The result of proposed algorithm shows that it has 10dB higher PSNR and 1.5 times faster convergence speed then the improved NNM Algorithm
참고문헌 (17)
- D.A. Scribner, "Infrared focal plane array technology", Proceedings of the IEEE, 79(1), pp.66~85 (1991), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Abraham Friedenberg, "Nonuniformity two-point linear correction errors in infrared focal plane arrays", Optical Engineering, 37(4), pp.1251~ (1998), SPIE-Intl Soc Optical Eng[DOI]
- Meng Sheng, "Calibration-based NUC Method in Real time Based on IRFPA", 2011 International Conference on Physics Science and Technology, 22, pp.372~380 (2011)
- D.A.Scribner, "Adaptive retina-like preprocessing for imaging detector arrays", Proceedings of the IEEE International Conference on Neural Network (Institute of Electrical and Electronics Engineers, pp.1955~1960 (1993)
- In-Seob Song, "Digital implementation of scene-based non-uniformity correction for microscan-mode infrared cameras", Electronics Letters, 35(13), pp.1068~ (1999), Institution of Engineering and Technology (IET)[DOI]
- Yang Chunling, "Researches on New Non-uniformity Correction Algorithm for Resistor Array", IEEE Confernece Publications, pp.235~238 (2010)
- Chao Zuo, "Scene-based nonuniformity correction method using multiscale constant statistics", Proc. SPIE (2011)
- J. Harris., "Minimizing the 'ghosting' artifact in scene-based nonuniformity correction", Proc. SPIE, 3377, pp.106~113 (1998)
- Chao Zuo, "Improved interframe registration based nonuniformity correction for focal plane arrays", Infrared Physics & Technology, 55(4), pp.263~269 (2012), Elsevier BV[DOI]
- Sergio N. Torres, "A Neural Network for Nonuniformity and Ghosting Correction of Infrared Image Sequences", International Conference Image Analysis and Recognition, pp.1208~1216 (2005)
- Sergio N. Torres, "Adaptive Scene-Based Non-Uniformity Correction Method for Infrared-Focal Plane Arrays", Proc. SPIE (2003)
- Kobi Cohen, "On Projected Stochastic Gradient Descent Algorithm with Weighted Averaging for Least Squares Regression", IEEE Transactions on Automatic Control, 62(11), pp.5974~5981 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Rong Sheng-Hui, "Guided filter and adaptive learning rate based non-uniformity correction algorithm for infrared focal plane array", Infrared Physics & Technology, 76, pp.691~697 (2016), Elsevier BV[DOI]
- Lee Jongho, "Improvement on a optimi zation algorithm for non-uniformity correction of infrared videos", pp.2013
- Shupeng Wang, "Kalman Filter for Stripe Non-uniformity Correction in Infrared Focal Plane Arrays", IS3C, pp.124~127 (2016)
- Chao Zuo, "Improved interframe registration based nonuniformity correction for focal plane arrays", Infrared Physics & Technology, 55(4), pp.263~269 (2012), Elsevier BV[DOI]
- Nicolas Celedon, "FPGA-based Neural Network for Nonuniformity Correction on Infrared Focal Plane Arrays", Euromicro Conference on Digital Systelm Design, pp.193~200 (2012)