14-09-2013, 01:58 PM
The Content-Based Image Retrieval using the Pulse Coupled Neural Network
Content-Based Image Retrieval.ppt (Size: 604 KB / Downloads: 26)
Pulse Coupled Neural Network
(PCNN)
Pulse-coupled networks or pulse-coupled neural networks (PCNNs) are neural models proposed by modeling a cat’s visual cortex and developed for high-performance biomimetic image processing.
A PCNN is a two-dimensional neural network. Each neuron in the network corresponds to one pixel in an input image, receiving its corresponding pixel’s color information (e.g. intensity) as an external stimulus.
THE CONTENT-BASED IMAGE RETRIEVAL SYSTEM
USING THE PULSE COUPLED NEURAL NETWORK
In this study, we apply the image matching technique using the PCNN to the CBIR system and evaluate its applicability.
The database in our system has image data, and each image data is annotated with its PCNN-Icon.
To retrieve the images, the system calculates the correlation among the PCNN-Icons of the images in the database and the query image.
The PCNN learning method for image matching is applied to this CBIR system to improve its performance.
Conclusion
In this system, an image matching technique using PCNN is applied to the CBIR system and we can evaluate the applicability and the performances of the system by the simulations.
In this system, the results of the image retrieval using our CBIR system, the images in relevant category were listed on top of the ranking.