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
Multi-focus image fusion based on fully convolutional networks
TL;DR: To obtain more precise focus detection maps, it is proposed to add skip layers in the network to make both detailed and abstract visual information available when using FD-FCN to generate maps.
Journal ArticleDOI
A scheme for edge-based multi-focus Color image fusion
Manali Roy,Susanta Mukhopadhyay +1 more
TL;DR: A novel region-based multi-focus color image fusion method, which employs the focused edges extracted from the source images to obtain a fused image with better focus, which has a competitive performance with respect to the recent fusion methods in terms of subjective and objective evaluation.
Journal ArticleDOI
A Survey of Multi-Focus Image Fusion Methods
Youyong Zhou,Lingjie Yu,Chao Zhi,Chuwen Huang,Shuai Wang,Mengqiu Zhu,Zhenxia Ke,Zhong-Yuan Gao,Yuming Zhang,Sida Fu +9 more
TL;DR: A novel classification method of image fusion algorithms is proposed: transform domain methods, boundary segmentation methods, deep learning methods, and combination fusion methods, which can effectively solve the problem of optical lens depth of field.
Subject evaluation criteria for image fusion used in paper Image Fusion Algorithm Based on Spatial Frequency-Motivated Pulse Coupled Neural Networks in Nonsubsampled Contourlet Transform Domain
TL;DR: In this article, the authors proposed a method for navigation system with the assistance of the Navigation Science Foundation of P. R. China (05F07001) and National Natural Science Foundation (NNSF) of China (60472081).
Journal ArticleDOI
Infrared and visible image fusion via octave Gaussian pyramid framework.
TL;DR: Zhang et al. as mentioned in this paper proposed an octave Gaussian pyramid based image fusion method, which decomposes an image into two scale spaces (octave and interval spaces) and retains high and low-frequency information from the original image.
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