基于分層差分表達(dá)理論的圖像視覺增強(qiáng)
doi: 10.11999/JEIT161070 cstr: 32379.14.JEIT161070
-
2.
(長春理工大學(xué) 長春 130022) ②(中國科學(xué)院長春光學(xué)精密機(jī)械與物理研究所 長春 130033)
基金項(xiàng)目:
國家自然科學(xué)基金(61205143)，吉林省科技廳重點(diǎn)項(xiàng)目(20110329)
Image Visual Enhancement Based on Layered Difference Representation
-
2.
(Changchun University of Science and Technplogy, Changchun 130022, China)
Funds:
The National Natural Science Foundation of China (61205143), The Science and Technology Department of Jilin Province Research Funding (20110329)
-
摘要: 視覺注意機(jī)制表明人眼趨向于關(guān)注感興趣區(qū)域。為了實(shí)現(xiàn)圖像視覺增強(qiáng)，該文提出基于2維直方圖分層差分表達(dá)理論的圖像增強(qiáng)方法。該算法首先檢測圖像的顯著性區(qū)域，并對該區(qū)域進(jìn)行分割，得到更適合人眼觀測的顯著圖。然后統(tǒng)計(jì)原圖中顯著圖對應(yīng)區(qū)域的2維差分直方圖，依據(jù)分層差分表達(dá)理論和考慮各層之間的內(nèi)在聯(lián)系，通過解線性優(yōu)化問題得到顯著性區(qū)域差分向量。定義原始差分向量代表原圖特征，將兩個(gè)向量加權(quán)相加后得到全局變換函數(shù)，重建得到視覺增強(qiáng)圖像。實(shí)驗(yàn)結(jié)果表明：該方法有效地增強(qiáng)圖像中人眼感興趣區(qū)域?qū)Ρ榷?，提升?xì)節(jié)信息。客觀評價(jià)指標(biāo)表明：與其他5種方法比較，該方法處理結(jié)果在3組實(shí)驗(yàn)中在保持全局亮度、提升峰值信噪比及人眼視覺系統(tǒng)敏感度信噪比指標(biāo)優(yōu)勢明顯。該方法增強(qiáng)后圖像顯著性區(qū)域的EME值適中，有利于視覺觀測?？陀^指標(biāo)與主觀觀察結(jié)果一致，表明該方法能有效改善圖像視覺效果。
-
關(guān)鍵詞:
- 圖像處理 /
- 人眼視覺增強(qiáng) /
- 顯著性檢測 /
- 分層差分表達(dá) /
- 2維直方圖
Abstract: Human vision pays more attention to the interesting region than other areas. A method based on salient region detection for layered difference representation of 2D histogram is proposed to achieve visual enhancement. The algorithm detects the salient region by salient filtering and cuts salient region with a threshold for visual perception firstly. Then, 2D histogram is calculated for related region in original image of salient region, and statistical information in different layers is converted to layer 2 according to the inner relationship of each layer. Following a difference vector is gained though solving a constrained optimization problem of layered difference representation at a specified layer. To preserve the character of non-salient region, an origin difference vector is defined. Finally, output image is reconstructed by a transformation function, which is the result of two difference vectors for salient region and non-salient region. Experimental results show that the proposed method enhances contrast and details in salient region efficiently while protecting non-salient region in origin image. The objective evaluation parameters in three group experiments illustrate that the proposed algorithm can get better scores in protecting global mean lighting in non-salient region, increasing PSNR and HSNR of the whole image compared to other five algorithms. The EME value of images enhanced by the proposed method is moderate. The objective evaluation parameters are consistent with the subject observation, and it demonstrates the proposed method can achieve visual enhancement effectively. -
JI Tingting and WANG Guoyu. An approach to underwater image enhancement based on image structural decomposition [J]. Journal of Ocean University of China, 2015, 14(2): 255-260. doi: 10.1007/s11802-015-2426-2. SUN Wei, GUO Baolong, LI Dajian, et al. Fast single image dehazing method for visible-light systems[J]. Optical Engineering, 2013, 52(9): 093103. doi: 10.1117/1.OE.52.9. 093103. 劉海波, 楊杰, 吳正平, 等. 改進(jìn)的基于霧氣理論的視頻去霧[J]. 光學(xué)精密工程, 2016, 24(7): 1789-1798. doi: 10.3788/OPE. 20162407.1789. LIU Haibo, YANG Jie, WU Zhengping, et al. Improved video defogging based on fog theory[J]. Optics and Precision Engineering, 2016, 24(7): 1789-1798. doi: 10.3788/OPE. 20162407.1789. MOHAN Shelda and RAVISHANKAR M. Modified contrast limited adaptive histogram equalization based on local contrast enhancement for mammogram images[J]. Communications in Computer Information Science, 2013, 296: 397-403. doi: 10.1007/978-3-642-35864-7_60. GAUTAM C and TIWARI N. Efficient color image contrast enhancement using range limited bi-histogram equalization with adaptive gamma correction[C]. 2015 International Conference on Industrial Instrumentation and Control (ICIC), Pune, India, 2015: 175-180. doi: 10.1109/IIC.2015. 7150733. 盧彥飛, 張濤, 章程. 應(yīng)用log-Gabor韋伯特征的圖像質(zhì)量評價(jià)[J]. 光學(xué)精密工程, 2015, 23(11): 3259-3269. doi: 10.3788/ OPE.20152311.3259. LU Yanfei, ZHANG Tao, and ZHANG Cheng. Image quality assessment using log-Gabor Weber feature[J]. Optics and Precision Engineering, 2015, 23(11): 3259-3269. doi: 10.3788/ OPE.20152311.3259. YANG Guocheng, LI Meiling, CHEN Leiting, et al. The nonsubsampled contourlet transform based statistical medical image fusion using generalized Gaussian density[J]. Computational Mathematical Methods in Medicine, 2015, 13(11): 1-13. doi: 10.1155/2015/262819. DEMIREL H and ANBARIJAFARI FG. Discrete wavelet transform-based satellite image resolution enhancement[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(6): 706-717. doi: 10.1109/TGRS.2010.2100401. 吳一全, 殷駿, 戴一冕. 基于人工蜂群優(yōu)化的NSCT域圖像模糊集增強(qiáng)方法[J]. 華南理工大學(xué)學(xué)報(bào):自然科學(xué)版, 2015, 43(1): 59-65. doi: 10.3969/j.issn.1000-565X.2015.01.010. WU Yiquan, YIN Jun, and DAI Yimian. Image enhancement in NSCT domain based on fuzzy sets and artificial bee colony optimization[J]. Journal of South China University of Technology (Natural Science Edition), 2015, 43(1): 59-65. doi: 10.3969/j.issn.1000-565X.2015.01.010. 張?bào)@雷, 胡曉婷, 溫顯斌, 等. 基于Shearlet變換與區(qū)域分割的遙感圖像融合[J]. 光電子激光, 2015, 26(12): 2393-2399. doi: 10.16136/j.joel.2015.12.0526. ZHANG Jinglei, HU Xiaoting, WEN Xianbing, et al. Remote sensing image fusion algorithm based on Shearlet transform and region segmentation[J]. Journal of OptoelectronicsLaser, 2015, 26(12): 2393-2399. doi: 10.16136/j.joel.2015.12.0526. LEE C L, LEE C, and KIM C S. Contrast enhancement based on layered difference representation of 2D histograms[J]. IEEE Transactions on Image Processing, 2013, 20(12): 5372-5384. doi: 10.1109/TIP.2013.2284059. PERAZZI F, KRAHENBUHL P, and PRITCH Y. Salency filters: Contrast based filtering for salient region detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2012: 733-740. doi: 10.1109/CVPR.2012. 6247743. KE W M, CHEN C R, and CHIU C T. BiTA/SWCE: Image enhancement with bilateral tone adjustment and saliency weighted contrast enhancement[J]. IEEE Transactions on Circuits and System for Video Technology, 2011, 21(3): 360-364. doi: 0.1109/TCSVT.2010.2087475. LI Yi, ZHANG Yunfeng, CAO Lihua, et al. Visual enhancement based on salient region detection and layered difference representation[J]. Optical Review, 2016, 23(1): 1-7. doi: 10.1007/s10043-015-0163-9. ZHANG X Y, CHAN K L, and CONSTABLE M. Atmospheric perspective effect enhancement of landscape photographs through depth-aware contrast manipulation[J]. IEEE Transactions on Multimedia, 2014, 16(3): 653-667. doi: 10.1109/TMM.2014.2299511. OOI C H, KONG NSP, and IBRAHIM H. Bi-histogram equalization with a plateau limit for digital image enhancement[J]. IEEE Transactions on Consumer Electronics, 2009, 55(4): 2072-2080. doi: 10.1109/TCE.2009. 5373771. AGAIAN S S, SILVER B, and PANETTA K A. Transform coefficient histogram-based image enhancement algorithms using contrast entropy[J]. IEEE Transactions on Image Processing, 2007, 16(3): 741-758. doi: 10.1109/TIP.2006.888338. SIM K S, TSO C P, and TAN Y Y. Recursive sub-image histogram equalization applied to gray scale images[J]. Pattern Recognition Letters, 2007, 1209(28): 1209-1221. doi: 10.1016/j.patrec.2007.02.003. 安雪晶, 田媛. 無參考圖像質(zhì)量評價(jià)方法的設(shè)計(jì)原則[J]. 中國光學(xué)與應(yīng)用光學(xué), 2009, 2(2): 140-144. doi: 1674-2915(2009) 02-0140-05 AN Xuejing and TIAN Yuan. Design principle of no-reference image quality evaluation[J]. Chinese Journal of Optics and Applied Optics, 2009, 2(2): 140-144. doi: 1674-2915(2009)02- 0140-05. USC SIPI圖像庫. ftp://sipi.usc.edu/pub/database/misc.zip 2015.12. -
計(jì)量
- 文章訪問數(shù): 1829
- HTML全文瀏覽量: 156
- PDF下載量: 317
- 被引次數(shù): 0
下載:
