Effective Multifocus Image Fusion Based on HVS and BP Neural Network

The aim of multifocus image fusion is to fuse the images taken from the same scene with different focuses to obtain a resultant image with all objects in focus. In this paper, a novel multifocus image fusion method based on human visual system (HVS) and back propagation (BP) neural network is presented. Three features which reflect the clarity of a pixel are firstly extracted and used to train a BP neural network to determine which pixel is clearer. The clearer pixels are then used to construct the initial fused image. Thirdly, the focused regions are detected by measuring the similarity between the source images and the initial fused image followed by morphological opening and closing operations. Finally, the final fused image is obtained by a fusion rule for those focused regions. Experimental results show that the proposed method can provide better performance and outperform several existing popular fusion methods in terms of both objective and subjective evaluations.

[1]  Gonzalo Pajares,et al.  A wavelet-based image fusion tutorial , 2004, Pattern Recognit..

[2]  Luciano Alparone,et al.  Remote sensing image fusion using the curvelet transform , 2007, Inf. Fusion.

[3]  Jason Jianjun Gu,et al.  Multi-focus image fusion using PCNN , 2010, Pattern Recognit..

[4]  Dheeraj Agrawal,et al.  Multifocus image fusion using modified pulse coupled neural network for improved image quality , 2010 .

[5]  Veysel Aslantas,et al.  Fusion of multi-focus images using differential evolution algorithm , 2010, Expert Syst. Appl..

[6]  Alexander Toet,et al.  Image fusion by a ration of low-pass pyramid , 1989, Pattern Recognit. Lett..

[7]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[8]  Yufeng Zheng,et al.  A new metric based on extended spatial frequency and its application to DWT based fusion algorithms , 2007, Inf. Fusion.

[9]  Chai Yi,et al.  Multifocus image fusion algorithm based on multiscale products and property of human visual system , 2012 .

[10]  Gwanggil Jeon,et al.  A multifocus image fusion method by using hidden Markov model , 2013 .

[11]  Jirí Mekyska,et al.  Multi-focus thermal image fusion , 2013, Pattern Recognit. Lett..

[12]  Shutao Li,et al.  Multifocus Image Fusion and Restoration With Sparse Representation , 2010, IEEE Transactions on Instrumentation and Measurement.

[13]  Michael Unser,et al.  Texture classification and segmentation using wavelet frames , 1995, IEEE Trans. Image Process..

[14]  Uday B. Desai,et al.  Multifocus and multispectral image fusion based on pixel significance using multiresolution decomposition , 2013, Signal Image Video Process..

[15]  Zhang Feng and Chang Huiyou Employing BP Neural Networks to Alleviate the Sparsity Issue in Collaborative Filtering Recommendation Algorithms , 2006 .

[16]  Shutao Li,et al.  Hybrid Multiresolution Method for Multisensor Multimodal Image Fusion , 2010, IEEE Sensors Journal.

[17]  Zhongliang Jing,et al.  Evaluation of focus measures in multi-focus image fusion , 2007, Pattern Recognit. Lett..

[18]  Qiang Zhang,et al.  Multifocus image fusion using the nonsubsampled contourlet transform , 2009, Signal Process..

[19]  Shutao Li,et al.  Performance comparison of different multi-resolution transforms for image fusion , 2011, Inf. Fusion.

[20]  Hadi Seyedarabi,et al.  Multi-focus image fusion for visual sensor networks in DCT domain , 2011, Comput. Electr. Eng..

[21]  Shi Zhan Log-Gabor and 2D semi-supervised discriminant analysis based face image retrieval , 2012 .

[22]  Dong Sun Park,et al.  Medical Image Fusion via an Effective Wavelet-Based Approach , 2010, EURASIP J. Adv. Signal Process..

[23]  L. Yang,et al.  Multimodality medical image fusion based on multiscale geometric analysis of contourlet transform , 2008, Neurocomputing.

[24]  Dafang Zhuang,et al.  Advances in Multi-Sensor Data Fusion: Algorithms and Applications , 2009, Sensors.

[25]  Yi Chai,et al.  Multifocus image fusion scheme using focused region detection and multiresolution , 2011 .

[26]  Yaonan Wang,et al.  Multifocus image fusion using artificial neural networks , 2002, Pattern Recognit. Lett..