聯合多種邊緣檢測算子的無參考質量評價算法

沈麗麗; 杭寧

doi:10.13374/j.issn2095-9389.2018.08.014

聯合多種邊緣檢測算子的無參考質量評價算法

doi: 10.13374/j.issn2095-9389.2018.08.014

沈麗麗^,,
杭寧

天津大學電氣自動化與信息工程學院, 天津 300072

基金項目:

國家自然科學基金資助項目（61520106002，61471262）

詳細信息

中圖分類號: TN911.73
計量
- 文章訪問數: 656
- HTML全文瀏覽量: 277
- PDF下載量: 10
- 被引次數: 0
出版歷程
- 收稿日期: 2017-08-22

No-reference image quality assessment using joint multiple edge detection

SHEN Li-li^,,
HANG Ning

School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

摘要

摘要: 提出了一種聯合多種邊緣檢測算子的無參考質量評價算法，同時考慮一階和二階邊緣算子，避免了單一算子的局限性.該方法首先將彩色圖像轉換為灰度圖像，然后計算灰度圖像的梯度，相對梯度以及LOG特征.本文所使用的特征分為兩部分，一部分提取相對梯度方向的標準差，另一部分利用條件熵來量化不同特征之間的相似性和相互關系，并且考慮到人眼特性進行多尺度計算，最后使用自適應增強（AdaBoost）神經網絡進行訓練和預測.在公共數據庫LIVE和TID2008上進行實驗，結果表明新方法對失真圖像的預測評分與主觀評分有較高的一致性，能很好地反映圖像質量的視覺感知效果，僅使用10維特征，性能優于現有的主流無參考質量評價算法.
- 無參考圖像質量評價 /
- 梯度 /
- LOG特征 /
- 條件熵 /
- AdaBoost神經網絡
Abstract: Before digital images become available to consumers, they usually undergo several stages of processing, which include acquisition, compression, transmission, and presentation. Unfortunately, each stage introduces certain types of distortion, such as white noise, Gaussian blur, and compression distortion, which may degrade the perceptual quality of the final image. Therefore, it is important to design an effective and robust image quality assessment method to automatically evaluate distortions in image quality. Image quality assessment is widely used in image compression, image deblur, image enhancement, and other image processing domains. In general, no-reference image quality assessment methods have profound practical significance and broad application value; hence, it remains the main focus of many researchers. At present, many image quality assessment methods extract features and predict image quality using single edge detection operations such as gradient or local binary pattern. However, it is difficult for a single edge detection operation to represent the whole perceptual quality of distorted images, and hence, their predictions may not be satisfactory. To eliminate the limitations of single edge detection operation, this paper proposes a new no-reference image quality assessment method based on a multiple edge detection operation. The paper considers first-order and second-order derivative information and utilize their similarity to predict image quality. The proposed method first converted color images to grayscale images, and calculated the gradient magnitude (GM), relative gradient magnitude (RM), relative gradient orientation (RO), and Laplacian of Gaussian (LOG) of the grayscale images. The feature vectors extracted from the maps were divided into two parts, where one part was the standard deviation of RO, and the second part utilized conditional entropy to quantify the similarity and relationship of GM, RM, and LOG. The images were naturally multiscale, and distortions affected the image structures across scales. Hence, all features at two scales were extracted:the original image scale and at a reduced resolution (low-pass filtered and down sampled by a factor of 2). Lastly, an AdaBoost back-propagation network was used to train and establish a regression model to predict the image quality. The experiment of the proposed method was performed on two public databases, LIVE and TID2008, and the results show that the score predicted by this new method has a good correlation with the subjective quality score. Moreover, this method can reflect perceptual quality properly using only ten-dimensional feature vectors, and the performance of correlation coefficient can exceed some state-of-the-art no-reference image quality assessment algorithms.
- no-reference image quality assessment /
- gradient /
- Laplacian of Gaussian /
- conditional entropy /
- AdaBoost network

HTML全文

參考文獻(23)

[1]	Wang S Q, Gu K, Zhang X, et al. Subjective and objective quality assessment of compressed screen content images. IEEE J Emerging Sel Top Circuits Syst, 2016, 6(4):532
[2]	Zhang X F, Wang S Q, Gu K, et al. Just-noticeable difference-based perceptual optimization for JPEG compression. IEEE Signal Process Lett, 2017, 24(1):96
[3]	Li L D, Yan Y, Lu Z L, et al. No-reference quality assessment of deblurred images based on natural scene statistics. IEEE Access, 2017, 5:2163
[4]	Gu K, Zhai G T, Wang S Q, et al. A general histogram modification framework for efficient contrast enhancement//IEEE International Symposium on Circuits and Systems. Lisbon, 2015:2816
[5]	Ruderman D L. The statistics of natural images. Network Comput Neural Syst, 1994, 5(4):517
[6]	Saad M A, Bovik A C, Charrier C. Blind image quality assessment:a natural scene statistics approach in the DCT domain. IEEE Trans Image Process, 2012, 21(8):3339
[7]	Moorthy A K, Bovik A C. Blind image quality assessment:from natural scene statistics to perceptual quality. IEEE Trans Image Process, 2011, 20(12):3350
[8]	Mittal A, Moorthy A K, Bovik A C. No-reference image quality assessment in the spatial domain. IEEE Trans Image Process, 2012, 21(12):4695
[9]	Hubel D H, Wiesel T N. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. J Physiol, 1962, 160(1):106
[10]	Clark M, Bovik A C. Experiments in segmenting texton patterns using localized spatial filters. Pattern Recognit, 1989, 22(6):707
[11]	Marziliano P, Dufaux F, Winkler S, et al. A no-reference perceptual blur metric//IEEE International Conference on Image Processing (ICIP). Rochester, 2002:Ⅲ-57
[12]	Marziliano P, Dufaux F, Winkler S, et al. Perceptual blur and ringing metrics:application to JPEG2000. Signal Process:Image Commun, 2004, 19(2):163
[13]	Liu L X, Hua Y, Zhao Q J, et al. Blind image quality assessment by relative gradient statistics and adaboosting neural network. Signal Process:Image Commun, 2016, 40:1
[14]	Zhang M, Muramatsu C, Zhou X R, et al. Blind image quality assessment using the joint statistics of generalized local binary pattern. IEEE Signal Process Lett, 2014, 22(2):207
[15]	Li Q H, Lin W S, Fang Y M. No-reference quality assessment for multiply-distorted images in gradient domain. IEEE Signal Process Lett, 2016, 23(4):541
[16]	Yue G H, Hou C P, Gu K, et al. No reference image blurriness assessment with local binary patterns. J Visual Commun Image Representation, 2017, 49:382
[18]	Ponomarenko N, Lukin V, Zelensky A, et al. TID2008-a database for evaluation of full-reference visual quality assessment metrics. Adv Mod Radioelectron, 2009, 10(4):30
[19]	Ghosh K, Sarkar S, Bhaumik K. Understanding image structure from a new multi-scale representation of higher order derivative filters. Image Vision Comput, 2007, 25(8):1228
[20]	Gu K, Li L D, Lu H, et al. A fast reliable image quality predictor by fusing micro- and macro-structures. IEEE Trans Ind Electron, 2017, 64(5):3903
[21]	Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment:from error visibility to structural similarity. IEEE Trans Image Process, 2004, 13(4):600
[22]	Ye P, Kumar J, Kang L, et al. Unsupervised feature learning framework for no-reference image quality assessment//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, 2012:1098
[23]	Zhang M, Muramatsu C, Zhou X R, et al. Blind image quality assessment using the joint statistics of generalized local binary pattern. IEEE Signal Process Lett, 2014, 22(2):207
[24]	Gu K, Zhai G T, Yang X K, et al. Using free energy principle for blind image quality assessment. IEEE Trans Multimedia, 2015, 17(1):50