Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

A multipurpose neural processor for machine vision systems.

G K Knopf¹, M M Gupta

¹Dept. of Mech. Eng., Univ. of Western Ontario, London, Ont.

IEEE Transactions on Neural Networks

|January 1, 1993

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Endophytes of Withania somnifera modulate in planta content and the site of withanolide biosynthesis.

Scientific reports·2018

Same author

Microbial modulation of bacoside A biosynthetic pathway and systemic defense mechanism in Bacopa monnieri under Meloidogyne incognita stress.

Scientific reports·2017

Same author

Cumulative role of bioinoculants on growth, antioxidant potential and artemisinin content in Artemisia annua L. under organic field conditions.

World journal of microbiology & biotechnology·2016

Same author

Microbial secondary metabolites ameliorate growth, in planta contents and lignification in Withania somnifera (L.) Dunal.

Physiology and molecular biology of plants : an international journal of functional plant biology·2016

Same author

Fast Disintegrating Combination Tablet of Taste Masked Levocetrizine Dihydrochloride and Montelukast Sodium: Formulation Design, Development, and Characterization.

Journal of pharmaceutics·2015

Same author

Acacetin 7-O-α-l-rhamnopyranosyl (1-2) β-D-xylopyranoside Elicits Life-span Extension and Stress Resistance in Caenorhabditis elegans.

The journals of gerontology. Series A, Biological sciences and medical sciences·2015

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

A novel positive-negative (PN) neural processor is introduced for real-time visual processing. This multitask neural network architecture effectively processes early vision information, demonstrating versatility in machine vision applications.

Area of Science:

Computer Science
Neuroscience
Artificial Intelligence

Background:

The human visual system processes complex spatiotemporal information in real-time.
Existing machine vision systems require efficient computational models to emulate early visual processing stages.

Purpose of the Study:

To propose a novel multitask neural network, the positive-negative (PN) neural processor, for early vision processing.
To emulate the spatiotemporal information processing capabilities of neural activity fields in the human visual pathway.
To demonstrate the versatility of the PN neural processor architecture for machine vision.

Main Methods:

Developed a state-space model of the PN neural processor.
The model features a bilayered, two-dimensional array of interconnected nonlinear processing elements (PEs).

Related Experiment Videos

Simulated gray-level image processing to evaluate the architecture's performance.

Main Results:

The PN neural processor architecture effectively extracts information from external input data via a feedforward subnet.
A feedback subnet generates transient and steady-state activities for diverse processing roles.
Simulations confirmed the processor's applicability to gray-level, edge, texture, and color information.

Conclusions:

The proposed PN neural processor is a viable computational model for early visual information processing.
The architecture's design supports multitask operations relevant to machine vision.
The study highlights the potential of this neural network for advanced machine vision systems.