Image confusion algorithm using adaptive threshold SSIM based on Contourlet transformation

ABSTRACT

Contourlet transformation has good characteristic in dealing with details in high frequency of the image information, and better directionality and sparsity. An improved algorithm using Structural similarity (SSIM) has been proposed to determine fusion rules adaptively. The improved algorithm calculates structural similarity of two images to be fused, takes the average of SSIM as a threshold value, and selects adaptively the high-frequency sub-band fusion method and low-frequency sub-band method to retain more profile information. The investigations show that the improved algorithm based on Contourlet transformation has richer details and sharper edges and gets better results of image quality index.

KEYWORDS:

• Image confusion
• Contourlet transformation
• SSIM
• self-adaption

Acknowledgments

This work is supported by the National Natural Science Foundation of China (31370565) and Technology Innovate Talents of Harbin (2015RAYXJ005).

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work is supported by the National Natural Science Foundation of China [grant number 31370565] and Technology Innovate Talents of Harbin [grant number 2015RAYXJ005].

Notes on contributors

Yan Zhancai

Yan Zhancai, professor, doctoral supervisor, Ph. D. in Navigation, Guidance and Control, Harbin Institute of Technology, research interests: information control and high performance computing, email: yaqiuliu @126.com

Liu Yaqiu

Liu Yaqiu, male, Youth League Committee of Heihe University, associate researcher, 35 years old, research interest: image processing, email: yanzhancai [email protected]