Image processing with neural networks - a review

By Michael Egmont-Petersen, D. de Ridder, Heinz Handels. 2002

1,224 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

N4-Fields: Neural Network Nearest Neighbor Fields for Image Transforms (2014, background): “cessing systems. Here, we only review several works that are arguably most related to ours. Neural networks for image processing. The use of neural networks for image processing goes back for decades [7]. Several recent works have investigated large-scale training of deep architectures for complex s”
A review of neural networks in plant disease detection using hyperspectral data (2018, background): “The advanced algorithms are for abstraction at pixel, feature, structure, object-set levels and scene characterization [98,132,133].”
eDoctor: machine learning and the future of medicine (2018, methodology): “To illustrate this, CNN, a type of feedforward NN that is designed to mimic neural processes in the brain, is frequently applied to image processing tasks [70, 71].”
Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment (2012, methodology): “Some examples where this technology is well described include ElMasry et al. (2008b), where a hyperspectral imaging system based on a spectrograph was used in the spectral region between 400 and 1,000 nm for the early detection of bruises on different background colours of apples cv.”
Supervised Learning of Image Restoration with Convolutional Networks (2007, methodology): “A convolutional network makes use of context to do image processing As mentioned in the introduction, our work is closely related to neural networks that operate on image patches, which have been studied extensively [7].”
Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections (2016, background): “Having this special structure, allows the network to learn long-term dependencies more easily (Gers et al. (2001)).”
A Review of Automated Microinjection Systems for Single Cells in the Embryogenesis Stage (2016, neutral): “image understanding [82].”