scispace - formally typeset
Search or ask a question
Author

Xiaoliu Luo

Bio: Xiaoliu Luo is an academic researcher from Chongqing University. The author has contributed to research in topics: Pixel & Segmentation. The author has an hindex of 1, co-authored 8 publications receiving 4 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: In this paper, a novel multi-focus image fusion algorithm based on Geometrical Sparse Representation (GSR) over single images is proposed, which does not need to train an overcomplete dictionary and vectorize the signal.
Abstract: Multi-focus image fusion aims to generate an image with all objects in focus by integrating multiple partially focused images. It is challenging to find an effective focus measure to evaluate the clarity of source images. In this paper, a novel multi-focus image fusion algorithm based on Geometrical Sparse Representation (GSR) over single images is proposed. The main novelty of this work is that it shows the potential of GSR coefficients used for image fusion. Unlike the traditional sparse representation-based (SR) methods, the proposed algorithm does not need to train an overcomplete dictionary and vectorize the signal. In our algorithm, using a single dictionary image, the source images are first represented by geometrical sparse coefficients. Specifically, we employ a weighted GSR model in the sparse coding phase, ensuring the importance of the center pixel. Then, the weighted GSR coefficient is used to measure the activity level of the source image and an average pooling strategy is applied to obtain an initial decision map. Third, the decision map is refined with a simple post-processing. Finally, the fused all-in-focus image is constructed with the refined decision map. Experimental results demonstrate that the proposed method can be competitive with or even superior to the state-of-the-art fusion methods in both subjective and objective comparisons.

12 citations

Journal ArticleDOI
TL;DR: A novel parameter estimation algorithm called TDAVBEM is introduced, which combines the Tsallis entropy and a deterministic annealing (DA) algorithm on the basis of the variational bayesian expected maximum (VBEM) to simultaneously implement the parameter estimation and select the optimal components of GMM.

6 citations

Journal ArticleDOI
TL;DR: A novel deep network architecture for multi-focus image fusion that is based on a non-local image model that outperforms the state-of-the-art methods, both qualitatively and quantitatively.
Abstract: Previous Convolutional Neural Networks (CNNs) based multi-focus image fusion methods rely primarily on local information of images. In this paper, we propose a novel deep network architecture for multi-focus image fusion that is based on a non-local image model. The motivation of this paper stems from local and non-local self-similarity widely shown in nature images. We build on this concept and introduce a recurrent neural network (RNN) that performs non-local processing. The RNN captures global and local information by retrieving long distant dependencies, hence augmenting the representation of each pixel with contextual representations. The augmented representation is beneficial to detect accurately focused and defocused pixels. In addition, we design a regression loss to address the influences of texture information. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods, both qualitatively and quantitatively.

6 citations

Journal ArticleDOI
TL;DR: Extensive experiments on popular multi-focus images show that the proposed dynamic convolutional kernel network without any post-processing algorithms is comparable to state-of-the-art approaches, and the unsupervised model obtains high fusion quality.

4 citations

Journal ArticleDOI
TL;DR: A novel geometrical sparse representation (GSR) model with single image is introduced in this paper that solves a model to measure the similarity between the input image and the single dictionary image.

3 citations


Cited by
More filters
Christopher M. Bishop1
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

10,141 citations

Journal ArticleDOI
TL;DR: In this paper , a new hierarchical Gaussian mixture model (HGMM) was proposed to construct minimum trajectory spanning trees via recursive clustering to model the multi-granular spatial structure and extract BIs.
Abstract: Mining the browsing behavior on the web map service platforms (WMSPs) can help to understand the users’ access intentions and provide recommendations. Although WMSPs are popular, the research on browsing behavior is in its infancy. The zoom-in indicates interest increasing whereas the zoom-out indicates interest decreasing. We defined the micro process of the users’ browsing behavior as the trajectory on the WMSP (WMSP trajectory) reflecting the change of interest. Modeling the WMSP trajectory and extracting its maximum browsing interest (BI) are our objectives. WMSP trajectory has multi-dimensional and multi-granular attributes due to the pyramid model of tiles organization making it challenging to achieve that. We constructed a space–time cube to scan the WMSP trajectory and reduce dimensionality. A new hierarchical Gaussian mixture model (HGMM) was proposed to construct minimum trajectory spanning trees via recursive clustering to model the multi-granular spatial structure and extract BIs. The Random Forest model was used to improve the BIs extraction accuracy. We evaluated the effectiveness of the proposed model using real-world data from Tianditu and proved the HGMM is superior to the GMM. This article will help to make WMSPs intelligent.

4 citations

Journal ArticleDOI
TL;DR: Wang et al. as mentioned in this paper proposed an end-to-end multimodal brain image fusion framework, MMI-fuse, which first applies an autoencoder to extract the features of source images, then an information preservation weighted channel spatial attention model is proposed to fuse the image features.
Abstract: Medical imaging plays a pivotal role in the clinical diagnosis of brain disease. There are many imaging methods to detect the state of tissues in the brain. While these imaging methods have advantages, they also have shortcomings. For example, magnetic resonance imaging (MRI) contains structural information but no functional characteristics of tissue, while positron emission tomography (PET) possesses functional characteristics but no structural information. The attention mechanism has been widely used in image fusion tasks, such as fusion of infrared and visible images and medical images. However, those attention models lack a balance mechanism for multimodal image features, affecting the final fusion performance. This paper proposes an end-to-end multimodal brain image fusion framework, MMI-fuse. Specifically, we first apply an autoencoder to extract the features of source images. Then, an information preservation weighted channel spatial attention model (ICS) is proposed to fuse the image features. We set an adaptive weight according to the information preservation degree of features. Finally, we use a decoder model to restructure the fused medical image. The proposed method increased the quality of fused images and decreased the fusion time effectively by the help of the improved attention model and encoder-decoder structure. To validate the performance of the proposed method, we collected 1590 pairs of multimodal brain images from the Harvard dataset and performed extensive experiments. Seven methods and five metrics were selected for the comparison experiments. The results demonstrate that the proposed method achieved notable performance on both the visual quality and objective metric score among these seven approaches. Moreover, the proposed method takes the least time among all compared methods.

3 citations

Journal ArticleDOI
TL;DR: In this paper , a dual-branch UNet fusion network based on pyramidal attention and cross-convolution (PACCDU) is proposed to obtain fused images with high contrast, rich information, and clear contours.
Abstract: Infrared and visible image fusion is an important branch in the field of information fusion, which aims to integrate effective information from different sensors and enhance the integrity of image information. Therefore, how to fully extract and retain the structural information and texture details in the source images is a pressing problem at present. In this article, a dual-branch UNet fusion network based on pyramidal attention and cross-convolution (PACCDU) is proposed to obtain fused images with high contrast, rich information, and clear contours. The network encoder uses cross-encoding blocks and pyramidal attention blocks to extract contextual features and cross-scale correlation features in different directions. The fusion block uses parallel spatial attention and channel attention to fuse feature information at different scales. The decoding stage uses large kernel convolution blocks and pyramidal attention to reconstruct the fused features. Ablation experiments and comparison experiments are conducted on the public datasets TNO, RoadScene, and NIR, and the results show that the algorithm in this article is superior in both subjective visual and objective evaluation.

2 citations