C22. Enhanced fusion for Infrared and visible images

An enhanced fusion technique for Infrared (IR) and visible images, which is based on the curvelet transform and homomorphic processing using the additive wavelet transform, is presented in this paper. The idea behind this technique is based on fusing the IR and visible images using the curvelet transform, and then decomposing the fused image into sub-bands in an additive fashion using the additive wavelet transform. The homomorphic enhancement is performed on each sub-band, separately. Finally, an inverse additive wavelet transform is performed on the homomorphic enhanced sub-bands to get an enhanced fused image with better visual details. The simulation results with real IR and visible images show that the proposed technique effectively enhances IR targets and preserves the details of visible images.

[1]  Yajie Wang,et al.  Image Fusion Based Concealed Weapon Detection , 2009, 2009 International Conference on Computational Intelligence and Software Engineering.

[2]  Guofan Jin,et al.  Infrared and visible image fusion based on NSCT and fuzzy logic , 2010, 2010 IEEE International Conference on Mechatronics and Automation.

[3]  Myeong-Ryong Nam,et al.  Fusion of multispectral and panchromatic Satellite images using the curvelet transform , 2005, IEEE Geoscience and Remote Sensing Letters.

[4]  Zhang Xiu-qiong,et al.  Dynamic Infrared and Visible Image Sequence Fusion Based on DT-CWT Using GGD , 2008, 2008 International Conference on Computer Science and Information Technology.

[5]  B. B. Saevarsson,et al.  Time invariant curvelet denoising , 2004, Proceedings of the 6th Nordic Signal Processing Symposium, 2004. NORSIG 2004..

[6]  Karen Panetta,et al.  Image fusion using the Parameterized Logarithmic Dual Tree Complex Wavelet Transform , 2010, 2010 IEEE International Conference on Technologies for Homeland Security (HST).

[7]  A. Wang,et al.  The Application of Wavelet Transform to Multi-modality Medical Image Fusion , 2006, 2006 IEEE International Conference on Networking, Sensing and Control.

[8]  F. El-Samie,et al.  HOMOMORPHIC ENHANCEMENT OF INFRARED IMAGES USING THE ADDITIVE WAVELET TRANSFORM , 2008 .

[9]  S. Udomhunsakul,et al.  Feature extraction in medical MRI images , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[10]  Myungjin Choi,et al.  THE CURVELET TRANSFORM FOR IMAGE FUSION , 2004 .

[11]  Nick Kingsbury,et al.  The dual-tree complex wavelet transform: a new technique for shift invariance and directional filters , 1998 .

[12]  Ibrahim M. Eldokany,et al.  CURVELET FUSION OF MR AND CT IMAGES , 2008 .

[13]  B. B. Saevarsson,et al.  Translation invariant combined denoising algorithm , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[14]  Vassilia Karathanassi,et al.  Investigation of the Dual-Tree Complex and Shift-Invariant Discrete Wavelet Transforms on Quickbird Image Fusion , 2007, IEEE Geoscience and Remote Sensing Letters.

[15]  Wei Lu,et al.  A new image fusion method based on curvelet transform , 2010, International Conference on Digital Image Processing.

[16]  Xiuqiong Zhang.  Infrared and Color Visible Image Sequence Fusion Based on Statistical Model and Image Enhancement , 2008, International Conference on Advanced Computer Theory and Engineering.

[17]  Guofan Jin,et al.  One color contrast enhanced infrared and visible image fusion method , 2010 .