基于視覺顯著失真度的圖像質(zhì)量自適應(yīng)評(píng)價(jià)方法
doi: 10.11999/JEIT141641
-
2.
(南京郵電大學(xué)信號(hào)處理與傳輸研究所 南京 210003) ②(浙江科技學(xué)院信息與電子工程學(xué)院 杭州 310023)
Image Quality Self-adaptive Assessment Based on Visual Salience Distortion
-
2.
(Institute of Signal Processing and Transmission, Nanjing University of Posts and Telecommunications,
-
摘要: 針對(duì)結(jié)構(gòu)相似(SSIM)圖像質(zhì)量評(píng)價(jià)算法沒有考慮人眼視覺多通道性和對(duì)圖像高失真評(píng)價(jià)的不穩(wěn)定性,提出一種基于視覺顯著失真度的圖像質(zhì)量自適應(yīng)融合(VSAP)評(píng)價(jià)方法。該方法首先采用log-Gabor濾波提取圖像的高頻、中頻及低頻3層視覺特征,基于log-Gabor變換尺度和方向權(quán)重系數(shù)計(jì)算特征值的相似度;然后基于視覺閾值多分辨性迭加計(jì)算出特征值的失真度;最后,根據(jù)視覺失真度自適應(yīng)融合相似度評(píng)價(jià)與失真度評(píng)價(jià)獲得圖像質(zhì)量的最終客觀評(píng)價(jià)。實(shí)驗(yàn)結(jié)果表明,VSAP方法不但對(duì)圖像不同類型失真的客觀評(píng)價(jià)與主觀感知具有更高的相關(guān)性,而且3個(gè)主要指標(biāo)斯皮爾曼等級(jí)相關(guān)系數(shù)(SROCC)、曲線擬合相關(guān)系數(shù)(CC)和均方根誤差(RMSE)對(duì)圖像不同水平失真的整體評(píng)價(jià)性能更穩(wěn)定,明顯優(yōu)于其它評(píng)價(jià)方法。
-
關(guān)鍵詞:
- 圖像質(zhì)量評(píng)價(jià) /
- 計(jì)算機(jī)視覺 /
- log-Gabor濾波器 /
- 視覺顯著 /
- 自適應(yīng)融合
Abstract: The Structural SIMilarity (SSIM) algorithm of image quality assessment does not take into account the characteristics of multi-channel resolutions of human vision, it is also not consistent with subjective human evaluation for high level distortions. A Visual Salience Adaptive Pooling (VSAP) strategy of image quality assessment is proposed based on visual multi-scale and multi-orientation of log-Gabor transformation. Firstly, the visual characteristics of image on the high, medium, and low frequency are extracted by the log-Gabor transformation. Then the visual similarity scores based on visual scales and visual orientations of log-Gabor are calculated, accordingly, the visual distortion levels of image are calculated iteratively with the visual multi- resolution threshold. Finally, a strategy of image quality assessment is proposed with adaptive pooling similarity scores to distortion scores. The experimental results show that objective assessments of VSAP for different types of distortion hold higher correlation with subjective assessment. More importantly, the overall assessment performance of the Spearman Rank-Order Correlation Coefficient (SROCC), Correlation Coefficient (CC) and Root Mean Square Error (RMSE) for different levels of distortion is more consistent with subjective scores and superior to other methods.-
Key words:
- Image quality assessment /
- Computer vision /
- log-Gabor filter /
- Visual salience /
- Adaptive pooling
-
蔣剛毅, 黃大江, 王旭, 等. 圖像質(zhì)量評(píng)價(jià)方法研究進(jìn)展[J]. 電子與信息學(xué)報(bào), 2010, 32(1): 219-226. Jiang Gang-yi, Huang Da-jiang, Wang Xu, et al.. Overview on image quality assessment methods[J]. Journal of Electronics Information Technology, 2010, 32(1): 219-226. 張飛艷, 謝偉, 陳榮元, 等. 基于視覺加權(quán)的奇異值分解壓縮圖像質(zhì)量評(píng)價(jià)測(cè)度[J]. 電子與信息學(xué)報(bào), 2010, 32(5): 1061-1065. Zhang Fei-yan, Xie Wei, Chen Rong-yuan, et al.. Compression image quality assessment based on human visual weight and singular value decomposition[J]. Journal of Electronics Information Technology, 2010, 32(5): 1061-1065. 王翔, 丁勇. 基于Gabor濾波器的全參考圖像質(zhì)量評(píng)價(jià)方法[J]. 浙江大學(xué)學(xué)報(bào)(工學(xué)版), 2013, 47(3): 422-430. Wang Xiang and Ding Yong. Full reference image quality assessment based on Gabor filter[J]. Journal of Zhejiang University(Engineering Science), 2013, 47(3): 422-430. 米曾真. 小波域中CSF頻率與方向加權(quán)的圖像質(zhì)量評(píng)價(jià)方法[J]. 電子學(xué)報(bào), 2014, 42(7): 1273-1276. Mi Zeng-zhen. Image quality evaluation method based on frequency and direction weighted to CSF in wavelet domain[J]. Acta Electronica Sinica, 2014, 42(7): 1273-1276. Yalman Y. Histogram based perceptual quality assessment method for color images[J]. Computer Standards Interfaces, 2014, 36(6): 899-908. Daly S. The visible different predictor: an algorithm for the assessment of images fidelity[C]. Digital Images and Human Vision Conference, Cambridge, England, 1993: 179-206. Lubin J. A visual discrimination model for images system design and evaluation[C]. Proceedings of the Conference on Visual Models for Target Detection and Recognition, Singapore City, Singapore, 1995: 207-220. Safranek R J and Johnston J D. A perceptually tuned sub-band image coder with image dependent quantization and post-quantization data compression[C]. Proceedings of the IEEE International Conference on Acoust, Speech and Signal Processing, Glasgow, UK, 1989: 1945-1948. Watson A B. DCT quantization matrices visually optimized for individual images[C]. Proceedings of the SPIE Human vision, Visual Processing, and Digital Display IV, Washington, USA, 1993: 202-216. Teo P C and Heeger D J. Perceptual image distortion[C]. SPIE International Conference on Image Processing, Texas, USA, 1994: 982-986. Wang Zhou, Bovik A C, Sheikh H R, et al.. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612. Sheikh H R, Bovik A C, and Veciana G D. An information fidelity criterion for image quality assessment using natural scene statistics[J]. IEEE Transactions on Image Processing, 2005, 14(12): 2117-2128. Aleksandr S D, Alexander G, and Eskicioglu A M. An SVD-based grayscale image quality measure for local and global assessment[J]. IEEE Transactions on Image Processing, 2006, 15(2): 422-429. Venkata N D, Kite T D, Bovik A C, et al.. Image quality assessment based on degradation model[J]. IEEE Transactions on Image Processing, 2000, 9(4): 636-650. Wang Zhou, Simoncelli E P, and Bovik A C. Multi-scale structural similarity for image quality assessment[C]. Proceedings of the 37th IEEE Asilomar Conference on Signals, Systems and Computers, Pacific Grove, Canada, 2002(2): 1398-1402. Zhang Lin, Zhang Lei, Mou Xuanqin, et al.. FSIM: a feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(8): 2378-2386. Ding Yong, Wang Shao-ze, and Zhang Dong. Full-reference image quality assessment using statistical local correlation [J]. Electronics Letters, 2014, 50(2): 79-81. Hu An-zhou, Zhang Rong, Yin Dong, et al.. Image quality assessment using a SVD-based structural projection[J]. Signal Processing: Image Communication, 2014, 29(3): 293-302. Zhang Lin, Shen Ying, and Li Hong-yu. VSI: a visual saliency-induced index for perceptual image quality assessment[J]. IEEE Transactions on Image Processing, 2014, 23(10): 4270-4281. Chang Hua-wen, Yang Hua, Gan Yong, et al.. Sparse feature fidelity for perceptual image quality assessment[J]. IEEE Transactions on Image Processing, 2013, 22(10): 4007-4018. Larson E C and Chandler D M. Most apparent distortion: full-reference image quality assessment and the role of strategy[J]. Journal of Electronic Imaging, 2010, 19(1): 011006-1-011006-21. Wandell B A. Foundations of Vision[M]. Stanford: Sinauer Associates, 1995: 277-284. Wang Zhou, Lu L G, and Bovik A C. Foveation scalablevideo coding with automatic fixation selection[J]. IEEE Transactions on Image Processing, 2003, 12(2): 243-254. -
計(jì)量
- 文章訪問數(shù): 1560
- HTML全文瀏覽量: 149
- PDF下載量: 1055
- 被引次數(shù): 0