Pixel-based and region-based image fusion schemes using ICA bases

By N. Mitianoudis, Tania Stathaki. Information Fusion, 2007

356 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4f9a50ea5933410aed61bd953512f1a0d0f2c19c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yu Liu
2. Xun Chen
3. Jiayi Ma
4. Hui Li
5. Zengfu Wang
6. Leyuan Fang
7. Hu Peng
8. Shutao Li

In Media Technology

1. Yu Liu
2. Xun Chen
3. Hui Li
4. Jiayi Ma
5. Zengfu Wang
6. Leyuan Fang
7. Shutao Li
8. Hu Peng

In Signal Processing

1. Y. Liu
2. Haitao Yin
3. Shutao Li
4. Bin Yang
5. Yu Liu
6. Xudong Kang
7. Leyuan Fang
8. Jianwen Hu

Citations in the corpus

• Pixel-level image fusion: A survey of the state of the art (2017, methodology): “N For example, in [81], the multi-focus images are fused in the independent component analysis (ICA) 285 transform domain using pixel-based and region-based fusion rules.”
• Performance comparison of different multi-resolution transforms for image fusion (2011, methodology): “Generally, these algorithms can be categorized into spatial domain fusion and transform domain fusion [3].”
• Image Fusion With Convolutional Sparse Representation (2016, neutral): “gated in image fusion include Laplacian pyramid [11], discrete wavelet transform [12], discrete cosine transform [13], nonsubsampled contourlet transform (NSCT) [14], independent component analysis [15], sparse representation (SR) [16], etc.”
• Multi-focus image fusion with a deep convolutional neural network (2017, background): “In recent years, a new kind of transform domain fusion methods [12–16] has emerged as an attractive branch in this field.”
• DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer (2023, methodology): “Conventional image fusion methods mainly involve transform domain-based methods [9], [10], sparse representation (SR)-based meth-ods [11], subspace-based methods [12], hybrid methods [13], and others [14].”
• Pixel-level image fusion with simultaneous orthogonal matching pursuit (2012, background): “Compared to feature or decision-level fusion, pixellevel fusion can preserve more original information [7].”
• AttentionFGAN: Infrared and Visible Image Fusion Using Attention-Based Generative Adversarial Networks (2021, methodology): “Subspace methods include the principal component analysis based methods [19], independent component analysis based methods [20] and non-negative matrix factorization based methods [21].”