PCNN pre-processor stage for the optical broadcast neural network processor

Lamela, Horacio; Ruiz-Llata, Marta; Jiménez, Matías; González, Manuel González; Gimeno, Jesús; Warde, Cardinal

doi:10.1117/12.668370

Cited by 2 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be achieved by placing a resistor between the neurons we want to connect [2]. Figure 17 shows a PCNN composed by 4×4 neurons, whose input/output nodes are connected by resistors.…”

Section: Pulse Coupled Neural Networkmentioning

confidence: 99%

“…A central neuron, i.e. neuron22, is connected to its nearest neighbour neurons, that is, the four located up, down, left and right positions [2]. A PCNN composed by N×N neurons can be used to process images with size N×N pixels.…”

Section: Pulse Coupled Neural Networkmentioning

confidence: 99%

“…In the study of different configurations determined by interconnections, simplifications have been demonstrated: 4/8 connections per neuron, (conditioning its activation or inhibition) [2] or 5/9, where 4/8 acts as activators and the rest act as inhibitors under the action of a global element designed for this purpose [3]. In order to simulate the high level of connectivity, and inspired by the success of temporal multiplexing in communications and computational networks, many investigators have adopted this method to solve the problems mentioned.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, the main problem is not only the number of connections which are in the network, but also if any configuration is to be created it is required that a hardware structure is developed with a fixed number of connections and elements [2] [3]. Where the aforementioned connections define the size of the image at the input.…”

Section: Introductionmentioning

confidence: 99%

“…Where the aforementioned connections define the size of the image at the input. The use of commercial sensors is not always possible, thus their development is also necessary [2].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Hardware implementation of a neural vision system based on a neural network using integrated and fire neurons

et al. 2007

View full text Add to dashboard Cite

In this paper we present the scheme for a control circuit used in an image processing system which is to be implemented in a neural network which has a high level of connectivity and reconfiguration of neurons for integration and trigger based on the Address-Event Representation. This scheme will be employed as a pre-processing stage for a vision system which employs as its core processing an Optical Broadcast Neural Network (OBNN). [Optical Engineering letters 42 (9), 2488]. The proposed vision system allows the possibility to introduce patterns from any acquisition system of images, for posterior processing.

show abstract

Section: Pulse Coupled Neural Networkmentioning

confidence: 99%

Section: Pulse Coupled Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Where the aforementioned connections define the size of the image at the input. The use of commercial sensors is not always possible, thus their development is also necessary [2].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Hardware implementation of a neural vision system based on a neural network using integrated and fire neurons

et al. 2007

View full text Add to dashboard Cite

show abstract

Optimization of a hardware implementation for pulse coupled neural networks for image applications

2010

Self Cite

View full text Add to dashboard Cite

Pulse Coupled Neural Networks are a very useful tool for image processing and visual applications, since it has the advantages of being invariant to image changes as rotation, scale, or certain distortion. Among other characteristics, the PCNN changes a given image input into a temporal representation which can be easily later analyzed for pattern recognition. The structure of a PCNN though, makes it necessary to determine all of its parameters very carefully in order to function optimally, so that the responses to the kind of inputs it will be subjected are clearly discriminated allowing for an easy and fast post-processing yielding useful results. This tweaking of the system is a taxing process.In this paper we analyze and compare two methods for modeling PCNNs. A purely mathematical model is programmed and a similar circuital model is also designed. Both are then used to determine the optimal values of the several parameters of a PCNN: gain, threshold, time constants for feed-in and threshold and linking leading to an optimal design for image recognition. The results are compared for usefulness, accuracy and speed, as well as the performance and time requirements for fast and easy design, thus providing a tool for future ease of management of a PCNN for different tasks.

show abstract

PCNN pre-processor stage for the optical broadcast neural network processor

Cited by 2 publications

References 11 publications

Hardware implementation of a neural vision system based on a neural network using integrated and fire neurons

Hardware implementation of a neural vision system based on a neural network using integrated and fire neurons

Optimization of a hardware implementation for pulse coupled neural networks for image applications

Contact Info

Product

Resources

About