Image Fusion Algorithm Based on Contourlet Transform and PCNN for Detecting Obstacles in Forests

Abstract In this paper the image fusion algorithm based on Contourlet transform and Pulse Coupled Neural Network (PCNN) was proposed to improve the performance of the image fusion in the detection accuracy of obstacles in forests. At the same time, the wavelet transform and the Principal Component Analysis (PCA) were simulated for comparison with the proposed algorithm. Then visible and infrared thermal images were collected in a forest. The experimental results have shown that the fused images using the method proposed provided a better understanding of the reality, enhanced images’ clarity and eliminated factors which provided shelters for targets.

Download Full-text

Study on Image Fusion Model Based on HIS Transform and Nonsubsampled Contourlet Transform

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.500.659 ◽

2012 ◽

Vol 500 ◽

pp. 659-665

Author(s):

Min Cao ◽

Shan Shan Tan ◽

Quan Fei Shen

Keyword(s):

Principal Component Analysis ◽

Wavelet Transform ◽

Image Fusion ◽

Principal Component ◽

Component Analysis ◽

Contourlet Transform ◽

Fusion Method ◽

Nonsubsampled Contourlet Transform ◽

Fusion Model ◽

His Transform

After analysising the principle of nonsubsampled contourlet transform, the image fusion model based on HIS transform and nonsubsampled contourlet transform is proposed. By taking of ALOS image as an example, the image fusion of multi-spectral band and panchromatic band at the same time is carried out by different fusion methods such as the method combining HIS transform and nonsubsampled contourlet transform (NSCT), HIS transform fusion method, principal component analysis (PCA), Brovey and static wavelet transform (SWT). By calculating the quantitative evaluation indicators of the different fused image, it is conclued that the fusion effection of static wavelet transform fusion method and nonsubsampled contourlet transform fusion method is better than the common methods such as HIS transform, principal component analysis and Brovey. In particular, the image fusion effection of nonsubsampled contourlet transform method, which betterly maintains the image spectral information while improving image spatial resolution at the same time, is superior than the fusion evaluation of static wavelet transform fusion method.

Download Full-text

Detecting Shilling Attacks with Automatic Features from Multiple Views

Security and Communication Networks ◽

10.1155/2019/6523183 ◽

2019 ◽

Vol 2019 ◽

pp. 1-13 ◽

Cited By ~ 2

Author(s):

Yaojun Hao ◽

Fuzhi Zhang ◽

Jian Wang ◽

Qingshan Zhao ◽

Jianfang Cao

Keyword(s):

Principal Component Analysis ◽

Recommender Systems ◽

Detection Method ◽

Principal Component ◽

Component Analysis ◽

Experimental Results ◽

Detection Methods ◽

Detection Accuracy ◽

Multiple Views ◽

Fine Grained

Due to the openness of the recommender systems, the attackers are likely to inject a large number of fake profiles to bias the prediction of such systems. The traditional detection methods mainly rely on the artificial features, which are often extracted from one kind of user-generated information. In these methods, fine-grained interactions between users and items cannot be captured comprehensively, leading to the degradation of detection accuracy under various types of attacks. In this paper, we propose an ensemble detection method based on the automatic features extracted from multiple views. Firstly, to collaboratively discover the shilling profiles, the users’ behaviors are analyzed from multiple views including ratings, item popularity, and user-user graph. Secondly, based on the data preprocessed from multiple views, the stacked denoising autoencoders are used to automatically extract user features with different corruption rates. Moreover, the features extracted from multiple views are effectively combined based on principal component analysis. Finally, according to the features extracted with different corruption rates, the weak classifiers are generated and then integrated to detect attacks. The experimental results on the MovieLens, Netflix, and Amazon datasets indicate that the proposed method can effectively detect various attacks.

Download Full-text

Multi-focus image fusion based on robust principal component analysis and pulse-coupled neural network

Optik ◽

10.1016/j.ijleo.2014.04.002 ◽

2014 ◽

Vol 125 (17) ◽

pp. 5002-5006 ◽

Cited By ~ 23

Author(s):

Yongxin Zhang ◽

Li Chen ◽

Zhihua Zhao ◽

Jian Jia ◽

Jie Liu

Keyword(s):

Neural Network ◽

Principal Component Analysis ◽

Image Fusion ◽

Principal Component ◽

Component Analysis ◽

Robust Principal Component Analysis ◽

Pulse Coupled Neural Network ◽

Focus Image

Download Full-text

Image Fusion Algorithm Based on Wavelet Transform and Laplacian Pyramid

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.860-863.2846 ◽

2013 ◽

Vol 860-863 ◽

pp. 2846-2849

Author(s):

Ming Jing Li ◽

Yu Bing Dong ◽

Xiao Li Wang

Keyword(s):

Wavelet Transform ◽

Image Fusion ◽

Relevant Information ◽

Experimental Results ◽

Improve Quality ◽

Laplacian Pyramid ◽

Single Image ◽

Fusion Algorithm ◽

Fused Image

Image fusion is process which combine relevant information from two or more images into a single image. The aim of fusion is to extract relevant information for research. According to different application and characteristic of algorithm, image fusion algorithm could be used to improve quality of image. This paper complete compare analyze of image fusion algorithm based on wavelet transform and Laplacian pyramid. In this paper, principle, operation, steps and characteristic of fusion algorithm are summarized, advantage and disadvantage of different algorithm are compared. The fusion effects of different fusion algorithm are given by MATLAB. Experimental results shows that quality of fused image would be improve obviously.

Download Full-text