- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 International Conference on Communication and Signal Processing (ICCSP) - Chennai (2018.4.3-2018.4.5)] 2018 International Conference on Communication and Signal Processing (ICCSP) - A Comparative Analysis of Total Variation and Least Square Based Hyperspectral Image Denoising Methods
摘要： Hyperspectral image (HSI) with high spectral resolution will be always degraded by the noise accumulation. Therefore, image denoising is a fundamental preprocessing technique which improves the precision of successive processes like image classification, unmixing etc. In this paper, we compare least square (LS) weighted regularization in spectral domain with spatial least square and total variation (TV) denoising techniques. These methods are experimented on real, and noise simulated hyperspectral image datasets. The contrast and edges of the image are well preserved in the spectral LS. The image contrast varies in spatial LS, and edge informations are lost in TV. The experimental results show that, the spectral LS is superior to other two techniques in terms of visual interpretation, Signal-to-Noise Ratio (SNR) and Structural Similarity (SSIM) Index.
关键词： IBBC,SNR,Least Square,Hyperspectral Image,Denoising,Spectral domain,Total Variation,SSIM
更新于2025-09-23 15:22:29
-
[IEEE 2019 18th International Conference on Optical Communications and Networks (ICOCN) - Huangshan, China (2019.8.5-2019.8.8)] 2019 18th International Conference on Optical Communications and Networks (ICOCN) - Image Registration SIFT Algorithm Based on Adaptive Adjustment of Grayscale Weight
摘要： In view of the low color contrast of the foreground in the image of aero-engine blades, this paper optimizes the SIFT algorithm which was commonly used in image registration. The SSIM index and FSIM index in the image similarity evaluation standard are added to calculate. Using the ESFS index as the judgment standard for analysing the similarity between the color image and the corresponding grayscale image. To calculate a weight ratio which is better than the traditional algorithm. Experiments show that the proposed algorithm outperforms traditional algorithm in saving the blade images’ information, and can acquire more feature point pairs in the subsequent SIFT registration process.
关键词： Edge Structure and Feature Similarity (ESFS),Scale-invariant Feature Transform(SIFT),Feature Similarity(FSIM),Structural Similarity(SSIM)
更新于2025-09-23 15:21:01
-
[IEEE 2018 20th International Conference on Transparent Optical Networks (ICTON) - Bucharest (2018.7.1-2018.7.5)] 2018 20th International Conference on Transparent Optical Networks (ICTON) - Measurement of IPTV Services on a Hybrid Access Network
摘要： Future telecommunication networks will be formed by means of different types of telecommunication systems that were used in the past. Considering expanding options of today’s smart mobile phones there is increasing pressure on telecommunication operators, who face a challenge how to cooperate across different telecommunication systems within their networks. The work focuses on the expansion of IPTV data flow on a hybrid network that is formed by the EPON and ADSL technologies. Along with the hybrid topology we focus on comparing multicast and unicast expansion of IPTV data traffic within this work.
关键词： EPON,MSE,ADSL,hybrid network,PSNR,SSIM,IPTV
更新于2025-09-10 09:29:36