Proceedings ArticleDOI
Hybrid neural networks for automatic target recognition
J. Waldemark,Vlatko Becanovic,Th. Lindblad,Clark S. Lindsey +3 more
- Vol. 4, pp 4016-4021
TLDR
The paper presents a hybrid neural network system for automatic target recognition, or ATR, that uses a hybrid of a biological inspired neural net called the Pulse Coupled Neural Net, PCNN, and traditional feedforward neural nets.Abstract:
The paper presents a hybrid neural network system for automatic target recognition, or ATR. The ATR system uses a hybrid of a biological inspired neural net called the Pulse Coupled Neural Net, PCNN, and traditional feedforward neural nets. The PCNN is an iterative neural network in which, for example, a grey scale input image results in a 1D time signal invariant to rotation, scale and translation alternations. The PCNN can also extract edges, perform object segmentation and extract texture information. The PCNN pre-processor generates a 1D time signal that is input to a feedforward pattern recognition net.read more
Citations
More filters
Journal ArticleDOI
Image object classification using saccadic search, spatio-temporal pattern encoding and self-organisation
TL;DR: A strategy using multiple self-organising feature maps (SOM) in a hierarchical manner is used, using a certain degree of user selection, a database of sub-images is grouped according to similarities in signature space.
Journal ArticleDOI
Image classification using the frequencies of simple features
TL;DR: The p-gram encoding scheme provides invariance to translation of the objects within the image and tolerance to scale variations as well and is successful for this limited image domain.
Journal ArticleDOI
Image Recognition Technology in Texture Identification of Marine Sediment Sonar Image
TL;DR: Zhang et al. as mentioned in this paper used transfer learning to improve the performance of bottom sonar image image texture classification using K-means clustering and transfer learning was used to reset the prior frame parameters to improve speed and accuracy.
Proceedings ArticleDOI
Generic VHDL implementation of a PCNN with loadable coefficients
TL;DR: This paper presents a general VHDL implementation of a Pulse Coupled Neural Network targeted for FPGA but can also be used with advantage for ASIC implementations.
Generic VHDL Implementation of a PCNN with Loadable Coefficients
TL;DR: In this article, a general VHDL implementation of a Pulse Coupled Neural Network (PCNN) is presented, targeted for FPGA but can also be used with advantage for ASIC implementations.
References
More filters
Journal ArticleDOI
Fast learning in networks of locally-tuned processing units
John Moody,Christian J. Darken +1 more
TL;DR: This work proposes a network architecture which uses a single internal layer of locally-tuned processing units to learn both classification tasks and real-valued function approximations (Moody and Darken 1988).
Journal ArticleDOI
A general regression neural network
TL;DR: The general regression neural network (GRNN) is a one-pass learning algorithm with a highly parallel structure that provides smooth transitions from one observed value to another.
Journal ArticleDOI
Probabilistic neural networks
TL;DR: A probabilistic neural network that can compute nonlinear decision boundaries which approach the Bayes optimal is formed, and a fourlayer neural network of the type proposed can map any input pattern to any number of classifications.
Journal ArticleDOI
A resource-allocating network for function interpolation
TL;DR: A network that allocates a new computational unit whenever an unusual pattern is presented to the network, which learns much faster than do those using backpropagation networks and uses a comparable number of synapses.
Journal ArticleDOI
The ART of adaptive pattern recognition by a self-organizing neural network
TL;DR: Art architectures are discussed that are neural networks that self-organize stable recognition codes in real time in response to arbitrary sequences of input patterns, which opens up the possibility of applying ART systems to more general problems of adaptively processing large abstract information sources and databases.