Journal ArticleDOI
Multi-focus image fusion with a deep convolutional neural network
TLDR
A new multi-focus image fusion method is primarily proposed, aiming to learn a direct mapping between source images and focus map, using a deep convolutional neural network trained by high-quality image patches and their blurred versions to encode the mapping.About:
This article is published in Information Fusion.The article was published on 2017-07-01. It has received 826 citations till now. The article focuses on the topics: Image fusion & Convolutional neural network.read more
Citations
More filters
Journal ArticleDOI
Infrared and visible image fusion based on guided hybrid model and generative adversarial network
TL;DR: Wang et al. as discussed by the authors used a dual-path approach for feature extraction of the source image, and designed information exchange after the corresponding convolutional layer to retain more information, and proposed an end-to-end dual discriminators which can effiffifficiently guide the neural network training process.
Proceedings ArticleDOI
CSpA-DN: Channel and Spatial Attention Dense Network for Fusing PET and MRI Images
TL;DR: Zhang et al. as mentioned in this paper proposed a novel fusion framework based on a dense network with channel and spatial attention (CSpA-DN) for PET and MR images, where an encoder composed of the densely connected neural network is constructed to extract features from source images, and a decoder network is leveraged to yield the fused image from these features.
Posted Content
Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision
TL;DR: In this article, a shared architecture is proposed to exploit the relationship between depth and all-in-focus (AiF) estimation, which can be trained either supervisedly with ground truth depth, or unsupervisedly with AiF images as supervisory signals.
Journal ArticleDOI
A multi-focus image fusion framework based on multi-scale sparse representation in gradient domain
TL;DR: A novel multi-focus image fusion framework that performs focus region detection by a pixel-level focus measure that outperforms the conventional and state-of-the-art methods in terms of both visual perceptions and objective evaluations is proposed.
Journal ArticleDOI
Multi-focus image fusion for multiple images using adaptable size windows and parallel programming
TL;DR: The multi-focus image fusion with adaptable windows (MF-AW) algorithm for multiple images improves the results of the linear combination of images with variable windows (CLI-VV) algorithm, using a unique decision map and applying parallel programming.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
Image quality assessment: from error visibility to structural similarity
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Proceedings Article
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair,Geoffrey E. Hinton +1 more
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Related Papers (5)
A general framework for image fusion based on multi-scale transform and sparse representation
Yu Liu,Shuping Liu,Zengfu Wang +2 more