Random forest-based scheme using feature and decision levels information for multi-focus image fusion

详细信息    查看全文

• 作者：Nabeela Kausar ; Abdul Majid
• 关键词：Image fusion ; Multi ; focus ; Random forest ; Ensemble ; Machine learning
• 刊名：Pattern Analysis & Applications
• 出版年：2016
• 出版时间：February 2016
• 年：2016
• 卷：19
• 期：1
• 页码：221-236
• 全文大小：2,921 KB
• 参考文献：1.Mitianoudis N, Stathaki T (2007) Joint fusion and blind restoration for multiple image scenarios with missing data. Comput J 50(6):660–673CrossRef
  2.Susperregi L, Arruti A, Jauregi E, Sierrac B, Martínez-Otzetaa JM, Lazkanoc E, Ansuategui A (2013) Fusing multipleIimage transformations and a thermal sensor with Kinect to improve person detection ability. Eng Appl Artif Intell 26(8):1980–1991CrossRef
  3.Zhu H, Liu M, Ji H, Li Y (2010) Combined invariants to blur and rotation using Zernike moment descriptors. Pattern Anal Appl. doi:10.​1007/​s10044-009-0159-9:​309-319
  4.Dai X, Zhang H, Liu T, Shu H, Luo L (2014) Legendre moment invariants to blur and affine transformation and their use in image recognition. Pattern Anal Appl 17(2):311–326MathSciNet CrossRef
  5.Naidu VPS, Raol JR (2008) Pixel-level image fusion using wavelets and principal component analysis. Def Sci J 58(3):338–352CrossRef
  6.Hamzaa AB, Heb Y, Krimc H, Willskyd A (2005) A multiscale approach to pixel-level image fusion. Integr Comput Aided Eng 12:135–146
  7.Burt PJ, Adelson EH (1983) The Laplacian pyramid as a compact image code. IEEE Trans Commun 31(4):532–540CrossRef
  8.Matsopoulos GK, Marshall S, Brunt JNH (1994) Multiresolution morphological fusion of MR and CT images of the human brain. IEE Proc Vision Image Signal Proc 141(3):137–142CrossRef
  9.Burt PJ, Kolczynski RJ (1993) Enhanced image capture through fusion. In: Fourth international conference on computer vision 1993, pp 173–182
  10.Mumtaz A, Choi TS, Majid A, Mumtaz A (2010) Image fusion algorithm based on dual tree complex wavelet transform and support vector machine. In: International Bhurban conference on applied sciences & technology, Islamabad, Pakistan, pp 197–202
  11.Lan Y, Ren H, Zhang Y (2013) Multi-band vector wavelet transformation based multi-focus image fusion algorithm. J Softw 8(1):208–217
  12.Goodman TNT, Lee SL, Tang WS (1993) Wavelets in wandering subspaces. Trans Am Math Soc 338(2):639–654MathSciNet CrossRef
  13.Piella G (2003) A general framework for multiresolution image fusion: from pixels to regions. Inf Fusion 4:259–280CrossRef
  14.S-h Zhao, Xue-zhi F, Kang G-d, Ramadan E (2002) Multi-source remote sensing image fusion based on support vector machine. Chin Geogr Sci 12:244–248CrossRef
  15.Mamatha SG, Rahim SA, Raj CP (2012) Feature-level multi-focus image fusion using neural network and image enhancement. Global J Comput Sci Technol Graph Vis 12(10):16–23
  16.Pagidimarry M, Babu KA (2011) An all approach for multi-focus image fusion using neural network. Int J Comput Sci Telecommun 2(8):23–29
  17.Li S, Kwok JT, Wang Y (2002) Multifocus image fusion using artificial neural networks. Pattern Recogn Lett 23:985–997CrossRef
  18.Li S, Kwok JT, Wang Y (2004) Fusing images with multiple focuses using support vector machines. IEEE Trans Neural Netw 15(6):1555–1561CrossRef
  19.Wang X-Y, Zhang B-B, Yang H-Y (2012) Active SVM-based relevance feedback using multiple Classifiers ensemble and features reweighting. Eng Appl Artif Intell 26(2013):368–381
  20.Ali S, Majid A, Khan A (2014) IDM-PhyChm-Ens: intelligent decision-making ensemble methodology for classification of human breast cancer using physicochemical properties of amino acids. Amino Acids 46(4):977–993CrossRef
  21.Breiman L (1996) Bagging predictors. Mach Learn 26:123–140
  22.Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRef
  23.Jiwu H, Shi YQ, Xianhua D (1999) A segmentation-based image coding algorithm using the features of human vision system. J Image Graph 4(5):400–404
  24.Eskicioglu AM, Fisher PS (1993) Image quality measures and their performance. IEEE Trans Commun 43(12):2959–2965CrossRef
  25.Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698CrossRef
  26.Zhang Y, Ge L (2009) Efficient fusion scheme for multi-focus images by using blurring measure. Digit Signal Proc 19(2):186–193CrossRef
  27.Naidu VPS, Raol JR (2008) Pixel-level Image fusion using wavelets and principal component analysis. Defen Sci J 58(3):338–352CrossRef
  28.Klonus S, Ehlers M (2009) Performance of evaluation methods in image fusion. In: 12th International conference on information fusion, Seattle, WA, USA, July 6–9 2009
  29.Heng C, LI Jie, Weile Z (2006) A novel support vector machine-based multifocus image fusion algorithm. In: International conference on communications, circuits and systems proceedings, 2006, pp 500–504
  
• 作者单位：Nabeela Kausar (1)
  Abdul Majid (1)
  
  1. Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, Islamabad, 45650, Pakistan
  
• 刊物类别：Computer Science
• 刊物主题：Pattern Recognition
  
• 出版者：Springer London
• ISSN：1433-755X

文摘

Often captured images are not focussed everywhere. Many applications of pattern recognition and computer vision require all parts of the image to be well-focussed. The all-in-focus image obtained, through the improved image fusion scheme, is useful for downstream tasks of image processing such as image enhancement, image segmentation, and edge detection. Mostly, fusion techniques have used feature-level information extracted from spatial or transform domain. In contrast, we have proposed a random forest (RF)-based novel scheme that has incorporated feature and decision levels information. In the proposed scheme, useful features are extracted from both spatial and transform domains. These features are used to train randomly generated trees of RF algorithm. The predicted information of trees is aggregated to construct more accurate decision map for fusion. Our proposed scheme has yielded better-fused image than the fused image produced by principal component analysis and Wavelet transform-based previous approaches that use simple feature-level information. Moreover, our approach has generated better-fused images than Support Vector Machine and Probabilistic Neural Network-based individual Machine Learning approaches. The performance of proposed scheme is evaluated using various qualitative and quantitative measures. The proposed scheme has reported 98.83, 97.29, 98.97, 97.78, and 98.14 % accuracy for standard images of Elaine, Barbara, Boat, Lena, and Cameraman, respectively. Further, this scheme has yielded 97.94, 98.84, 97.55, and 98.09 % accuracy for the real blurred images of Calendar, Leaf, Tree, and Lab, respectively. Keywords Image fusion Multi-focus Random forest Ensemble Machine learning