Journal ArticleDOI
A new approach to image segmentation based on simplified region growing PCNN
Reads0
Chats0
TLDR
In this paper, a region growing pulse coupled neural network (PCNN) algorithm is proposed for multi-value image segmentation, which improves the region growing PCNN model by modifying the linking channel function and decreases the complexity of adjusting parameters.About:
This article is published in Applied Mathematics and Computation.The article was published on 2008-11-15. It has received 34 citations till now. The article focuses on the topics: Image segmentation & Region growing.read more
Citations
More filters
Journal ArticleDOI
A New Automatic Parameter Setting Method of a Simplified PCNN for Image Segmentation
TL;DR: The experimental segmentation results of the gray natural images from the Berkeley Segmentation Dataset, rather than synthetic images, prove the validity and efficiency of the proposed automatic parameter setting method of SPCNN.
Journal ArticleDOI
Computational Mechanisms of Pulse-Coupled Neural Networks: A Comprehensive Review
TL;DR: Insight into the internal operations and behaviors of PCNN is provided, and the way how PCNN achieves good performance in digital image processing is revealed.
Journal ArticleDOI
Region growing for image segmentation using an extended PCNN model
Dongguo Zhou,Yanhua Shao +1 more
TL;DR: This study proposes an extended PCNN model by using a strategy of the decision tree, and establishes links between the parameters and image characteristics, and can be considered as a region growing approach for multilevel image segmentation, thus named as an extendedPCNN model.
Journal ArticleDOI
An Overview of Image Segmentation Based on Pulse-Coupled Neural Network
Jing Lian,Jing Lian,Zhen Yang,Zhen Yang,Jizhao Liu,Wenhao Sun,Wenhao Sun,Li Zheng,Du Xiaogang,Zetong Yi,Bin Shi,Yide Ma +11 more
TL;DR: This paper elaborates internal behaviors of the pulse-coupled neural network to exhibit its image segmentation abilities, and systematically provides the related segmentation contents of the PCNN to help researchers to understand suitable segmentation applications of PCNN models.
Journal ArticleDOI
An Overview of PCNN Model’s Development and Its Application in Image Processing
TL;DR: In this paper, recent pulse coupled neural networks (PCNN) model’s development, especially in the fields related to the image processing, were surveyed and underlying difficulties, limitations, merits and disadvantages were discussed in applying these models.
References
More filters
Journal ArticleDOI
Image Segmentation Techniques
TL;DR: There are several image segmentation techniques, some considered general purpose and some designed for specific classes of images as discussed by the authors, some of which can be classified as: measurement space guided spatial clustering, single linkage region growing schemes, hybrid link growing scheme, centroid region growing scheme and split-and-merge scheme.
Journal ArticleDOI
Feature linking via synchronization among distributed assemblies: Simulations of results from cat visual cortex
TL;DR: It is proposed that synchronization is a general principle for the coding of associations in and among sensory systems and that at least two distinct types of synchronization do exist: stimulus-forced (event-locked) synchronization support crude instantaneous associations and stimulus-induced (oscillatory) synchronizations support more complex iterative association processes.
Proceedings ArticleDOI
Image Segmentation Techniques
TL;DR: Each of the major classes of image segmentation techniques is defined and several specific examples of each class of algorithm are described, illustrated with examples of segmentations performed on real images.
Journal ArticleDOI
PCNN models and applications
John L. Johnson,Mary Lou Padgett +1 more
TL;DR: The linking field modulation term is shown to be a universal feature of any biologically grounded dendritic model and the PCNN image decomposition (factoring) model is described in new detail.
Journal ArticleDOI
Perfect image segmentation using pulse coupled neural networks
G. Kuntimad,Heggere S. Ranganath +1 more
TL;DR: Conditions for perfect image segmentation are derived and it is shown that addition of an inhibition receptive field to the neuron model increases the possibility of perfect segmentation.
Related Papers (5)
Perfect image segmentation using pulse coupled neural networks
G. Kuntimad,Heggere S. Ranganath +1 more
Feature linking via synchronization among distributed assemblies: Simulations of results from cat visual cortex
Region growing with pulse-coupled neural networks: an alternative to seeded region growing
R.D. Stewart,I. Fermin,M. Opper +2 more