افزایش وضوح تصویر با استفاده از برجستگی بصری
محورهای موضوعی : مهندسی برق و کامپیوترمینا وفایی جهان 1 , عباس ابراهیمی مقدم 2 , مرتضی خادمی 3
1 - دانشکده مهندسی برق، دانشگاه فردوسی مشهد
2 - دانشکده مهندسی برق، دانشگاه فردوسی مشهد
3 - دانشکده مهندسی برق، دانشگاه فردوسی مشهد
کلید واژه: افزایش وضوح در لبه‌ها, برجستگی بصری (VS) , توجه بصری (VA) ,
چکیده مقاله :
افزایش وضوح تصویر در بسیاری موارد به تقویت مؤلفه‌های فرکانس بالای آن و افزایش وضوح در لبه‌ها اطلاق می‌شود. در مدل‌های موجود افزایش وضوح فرض می‌شود که حساسیت سیستم بینایی انسان(HVS) در تمام صحنه یکسان است و تأثیرات توجه بصری (VA) ناشی از برجستگی بصری (VS) در این مدل‌ها لحاظ نشده است. مطالعات مختلف نشان داده‌اند که حساسیت بصری در نقاطی که توجه بیشتری را جلب می‌کند بالاتر است؛ بنابراین افزایش وضوح تصویر مبتنی بر توجه بصری می‌تواند باعث وضوح بیشتر درک‌شده در تصویر گردد. در این مقاله، مدلی برای افزایش وضوح تصویر پیشنهاد شده که از رابطه بین نقشه مؤلفه‌های فرکانس بالای تصویر و برجستگی بصری برای تعیین مقدار بهینه وضوح تصویر استفاده می‌کند. مدل پیشنهادی با به‌کارگیری یک تابع غیرخطی، مقدار وضوح بهینه برای یک تصویر را با توجه به برجستگی بصری آن بیان می‌کند. تعیین پارامترهای تابع غیرخطی در قالب یک مسأله بهینه‌سازی مدل‌سازی شده که حل آن منجر به یافتن مقدار وضوح بهینه به طور خودکار می‌شود. جهت ارزیابی روش پیشنهادی و نشان‌دادن کارایی آن، آزمایش‌های ذهنی و عینی انجام شده که نتایج نشان می‌دهند روش پیشنهادی در صورت انتخاب مقادیر مناسب پارامترهای کنترلی، نسبت به دیگر روش‌های مورد مقایسه عملکرد مؤثرتری دارد.
Increasing the sharpness of the image, in many cases, refers to strengthening its high frequency components and increasing the sharpness at the edges. In the existing models of increasing clarity, it is assumed that the sensitivity of the human visual system is the same in the whole scene, and the effects of visual attention caused by visual salience are not included in these models. Various studies have shown that visual sensitivity is higher in places that attract more attention. Therefore, increasing image clarity based on visual attention can cause greater perceived clarity in the image. In this article, a model for increasing image sharpness is proposed, which uses the relationship between the map of high frequency image components and visual salience to determine the optimal value of image sharpness. By using a non-linear function, the proposed model expresses the optimal sharpness value for an image according to its visual prominence. Determining the parameters of the nonlinear function in the form of a modeled optimization problem, the solution of which leads to finding the optimal sharpness value automatically. The results show that the proposed method has a more effective performance than the other compared methods if the appropriate values of the control parameters are selected.
[1] Tutorials:Sharpness.http://www.cambridgeincolour.com/tutorials/sharpness.htm. [Online] (visited on June 11, 2016).
[2] M. Reichmann, Understanding sharpness, https://luminous landscape.com/rediscover-understanding-sharpness/.[Online] (visited on June 27. 2018).
[3] N. Strobel and S. K. Mitra, "Quadratic filters for image contrast enhancement," in Proc. of 28th Asilomar Conf. on Signals, Systems and Computers, vol. 1, pp. 208-212, Pacific Grove, CA, USA, 31 Oct-Nov. 1994.
[4] C. Yin, Y. Zhou, S. Agaian, and C. L. Philip Chen, "Parametric rational unsharp masking for image enhancement," SPIE 9019, Image Processing: Algorithms and Systems XII, vol. 90190, 8 pp., Feb. 2014.
[5] K. Kaur, N. Jindal, and K. Singh, "Fractional derivative based unsharp masking approach for enhancement of digital images," Multimedia Tools and Applications, vol. 80, pp. 3645-3679, Aug. 2021.
[6] A. Polesel, G. Ramponi, and V. J. Mathews, "Image enhancement via adaptive unsharp masking," IEEE Trans. on Image Processing, vol. 9, no. 3, pp. 505-510, Mar. 2000.
[7] W. Ye and K. K. Ma, "Blurriness-guided unsharp masking," IEEE Trans. on Image Processing, vol. 27, no. 9, pp. 4465-4477, Jan. 2018.
[8] T. Kobayashi and J. Tajima, "Content-adaptive automatic image sharpening," in Proc. 20th Int. Conf. on Pattern Recognition, pp. 2214-2217, Istanbul, Turkey, 23-26 Aug. 2010.
[9] L. Krasula, P. L. Callet, K. Fliegel, and M. Klíma, "Quality assessment of sharpened images: challenges, methodology, and objective metrics," IEEE Trans. on Image Processing, vol. 26, no. 3, pp. 1496-1508, Mar. 2017.
[10] X. Duan, et al., "A multiscale contrast enhancement for mammogram using dynamic unsharp masking in laplacian pyramid," IEEE Trans. on Radiation and Plasma Medical Sciences, vol. 3, no. 5, pp. 557-564, Sep. 2019.
[11] B. J. Borah and C. K. Sun, "A GPU-accelerated modified unsharp-masking method for high-frequency background-noise suppression," IEEE Access, vol. 9, pp. 68746-68757, 2021.
[12] I. Draganov and V. Gancheva, "Unsharp masking with local adaptive contrast enhancement of medical images," In Su, R., Zhang, YD., Liu, H. (eds) Proc. of 2021 Int. Conf. on Medical Imaging and Computer-Aided Diagnosis, Lecture Notes in Electrical Engineering, Springer, Singapore, vol. 784, pp. 354-363, Jan. 2021.
[13] C. C. Pham and J. W. Jeon, "Efficient image sharpening and denoising using adaptive guided image filtering," IET Image Processing, vol. 9, no. 1, pp. 71-79, Jan. 2014.
[14] R. R. Kumar, A. Kumar, and S. Srivastava, "Anisotropic diffusion based unsharp masking and crispening for denoising and enhancement of MRI images," in Proc. Int. Conf. on Emerging Frontiers in Electrical and Electronic Technologies, ICEFEET'20, 6 pp., Patna, India, 10-11Jul. 2020.
[15] Z. Alameen, A. Muttar, and G. Albadrani, "Improving the sharpness of digital image using an amended unsharp mask filter," International J. of Image, Graphics and Signal Processing, vol. 11, no. 3, pp. 1-9, Mar. 2019.
[16] S. H. Majeed and N. A. M. Isa, "Adaptive entropy index histogram equalization for poor contrast images," IEEE Access, vol. 9, pp. 6402-6437, 2021.
[17] R. C. Gonzalez and R. E. Woods, Digital Image Processing Using MATLAB, 2nd Ed. New Delhi India: Pearson, 2004.
[18] Y. T. Kim, "Contrast enhancement using brightness preserving bi-histogram equalization," IEEE Trans. on Consumer Electronics, vol. 43, no. 1, pp. 1-8, Feb. 1997.
[19] S. D. Chen and A. R. Ramli, "Contrast enhancement using recursive meanseparate histogram equalization for scalable brightness preservation," IEEE Trans. Consum. Electron., vol. 49, no. 4, pp. 1301-1309, Nov. 2003.
[20] Q. Wang and R. Ward, "Fast image/video contrast enhancement based on weighted thresholded histogram equalization," IEEE Trans. Consum. Electron., vol. 53, no. 2, pp. 757-764, Jun. 2007.
[21] J. Y. Kim, L. S. Kim, and S. H. Hwang, "An advanced contrast enhancement using partially overlapped sub-block histogram equalization," IEEE Trans. Circuits Syst. Video Technol., vol. 11, no. 4, pp. 475-484, Apr. 2001.
[22] S. F. Tan and N. A. M. Isa, "Exposure based multi-histogram equalization contrast enhancement for non-uniform illumination images," IEEE Access, vol. 7, pp. 70842-70861, 2019.
[23] Z. Shi, Y. Chen, E. Gavves, P. Mettes, and C. G. M. Snoek, "Unsharp mask guided filtering," IEEE Trans. on Image Processing, vol. 30, pp. 7472-74852021.
[24] J. Li, M. D. Levine, X. An, X. Xu, and H. He, "Visual saliency based on scale-space analysis in the frequency domain," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 35, no. 4, pp. 996-1010, Nov. 2013.
[25] L. Itti, C. Koch, and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, no. 11, pp. 1254-1259, Nov. 1998.
[26] L. Itti and C. Koch, "A saliency-based search mechanism for overt and covert shifts of visual attention," IEEE Trans. Image Process, vol. 13, no. 10, pp. 1304-1318, Jan. 2004.
[27] A. Borji, M. M. Cheng, H. Jiang, and J. Li, "Salient object detection: a benchmark," IEEE Trans. on Image Process, vol. 24, no. 12, pp. 5706-5722, Jan. 2015.
[28] B. Zhang, J. P. Allebach, and Z. Pizlo, "An investigation of perceived sharpness and sharpness metrics," Proc. SPIE, Image Quality and System Performance II, vol. 5668, pp. 98-110, Jan. 2005.
[29] T. Judd, K. Ehinger, F. Durand, and A. Torralba, "Learning to predict where humans look," in Proc. IEEE 12th Int. Conf. on Computer Vision, pp. 2106-2113, Kyoto, Japan, 29 Sept.-2 Oct. 2009.
[30 ف. نعمتی خلیل‌آباد، ﻫ. هادی‌زاده، ع. ابراهیمی‌مقدم و م. خادمی درح، "تخمین کمترین تفاوت قابل درک با استفاده از برجستگی بصری در تصاویر،" فصل‌نامه پردازش علائم و داده‌ها، جلد 17، شماره 2، صص. 71-84، 1399.
[31] K. Zuiderveld, Contrast Limited Adaptive Histogram Equalization, Chapter VIII.5, Graphics Gems IV. P. S. Heckbert (Eds.), Cambridge, MA, Academic Press, Feb. 1994.
[32] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," IEEE Trans. on Image Processing, vol. 13, no. 4, pp. 600-612, Apr. 2004.
[33] G. Deng, F. Galetto, M. Alnasrawi, and W. Waheed, "A guided edge-aware smoothing-sharpening filter based on patch interpolation model and generalized gamma distribution," IEEE Open J. of Signal Processing, vol. 2, pp. 119-135, Mar. 2021.
[34] D. Ngo, S. Lee, and B. Kang, "Nonlinear unsharp masking algorithm," in Proc. Int. Conf. on Electronics, Information, and Communication, ICEIC'20, 6 pp., Barcelona, Spain, 19-22 Jan. 2020.
[35] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th Ed. New York, NY: Pearson, pp. 138-140, 2018.
[36] K. Singh and R. Kapoor, "Image enhancement via median-mean based sub-image-clipped histogram equalization," Optik-International J. for Light and Electron Optics. vol. 125, no. 17, pp. 4646-4651, Sept. 2014.
[37] T. Judd, K. Ehinger, F. Durand, and A. Torralba, "Learning to predict where humans look," in Proc.IEEE 12th Int. Conf. on Computer Vision, pp. 2106-2113, Kyoto, Japan, 29 Sept.- 2 Oct. 2009.
