Reference : Image classification using neural networks
Patent : Patent
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/226179
Image classification using neural networks
English
Van Droogenbroeck, Marc mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Deliège, Adrien mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Cioppa, Anthony mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
19-Dec-2019
2018-06-17
World Intellectual Property Organization
WO 2019/238976 A1
18178146.9
A
Switzerland
University of Liège
G06K 9/46, G06K9/62
Not released
Europe
BE
[en] Classification ; Neural network
[en] A computer-implemented method for training a neural network for classifying image data and a related computer program product are disclosed. A labelled input data set comprising a plurality of labelled image data samples is provided together with a neural network. The neural network comprises an input layer, at least one intermediate layer, and an output layer having one channel per label class. Each channel provides a mapping of labelled image data samples onto feature vectors. Furthermore, the input layer of a decoder network for reconstructing image data samples at its output is connecting the output layer of the neural network. A classifier predicts class labels as the labels of those channels for which a normed distance of its feature vector relative to a pre-determined reference point is smallest. A loss function for the neural network is suitable for steering, for each channel, the feature vectors onto which image data samples of the associated class are mapped, into a convex target region around the pre-determined reference point.
Montefiore Institute of Electrical Engineering and Computer Science - Montefiore Institute ; Telim
DeepSport
Researchers ; Professionals
http://hdl.handle.net/2268/226179

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
HitNet publication WO2019238976.pdfPublisher postprint4.62 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.