Image classification and retrieval using optimized Pulse-Coupled Neural Network

Mohammed, Mona Mahrous; Badr, Amr; Abdelhalim, M. B.

doi:10.1016/j.eswa.2015.02.019

Cited by 40 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By studying the cerebral cortex of mammals, Eckhorn et al (1990) established a neuronal conduction characteristics model for the visual area, which eventually developed into PCNN (Lindblad and Kinser, 2013; Mohammed et al, 2015). PCNN is a single-layer artificial neural network model that does not need training on sample data as the network implementation is dominated by an iterative algorithm.…”

Section: Pseudo-anchor Points Discriminant Methods Based On Pcnnmentioning

confidence: 99%

Underwater Terrain Positioning Method Using Maximum a Posteriori Estimation and PCNN Model

Chen

Zhang

et al. 2019

J. Navigation

View full text Add to dashboard Cite

Conventional underwater navigation and positioning methods for Autonomous Underwater Vehicles (AUVs) either require the installation of acoustic arrays, which make AUVs less independent, or result in cumulative errors. This paper proposes an Underwater Terrain Positioning Method (UTPM) using Maximum a Posteriori (MAP) estimation and a Pulse Coupled Neural Network (PCNN) model for highly accurate navigation by AUVs. The PCNN model is used as a secondary discriminant to effectively identify pseudo-anchor points in flat terrain feature areas and to find the true positioning point, which significantly improves the matching positioning accuracy in these areas. Simulation results show that the proposed method effectively corrects Inertial Navigation System (INS) cumulative errors and has high matching positioning accuracy, which satisfy the requirements of AUV underwater navigation and positioning.

show abstract

Section: Pseudo-anchor Points Discriminant Methods Based On Pcnnmentioning

confidence: 99%

Underwater Terrain Positioning Method Using Maximum a Posteriori Estimation and PCNN Model

Chen

Zhang

et al. 2019

J. Navigation

View full text Add to dashboard Cite

show abstract

“…Dual Channel PCNN algorithm has been developed for the fusion of multimodality brain images [4]. Optimised PCNN in along with K-Nearest Neighbor (K-NN) is used for classification and retrieval of images by extracting visual features known as image signature [5]. Quantum based Particle Swarm Optimization along with adaptive PCNN fuses multimodal medical images [6].…”

Section: G Kalaiarasi K K Thyagharajanmentioning

confidence: 99%

A New Retrieval Algorithm Based on Pulse Coupled Neural Network for Biomedical Images

2019

IJITEE

View full text Add to dashboard Cite

The rapid expansion and improvement in medical science and technology lead to the generation of more image data in its regular activity such as computed tomography (CT), X-ray, magnetic resonance imaging (MRI) etc. To manage the medical images properly for clinical decision making, content-based medical image retrieval (CBMIR) system emerged. In this paper, Pulse Coupled Neural Network (PCNN) based feature descriptor is proposed for retrieval of biomedical images. Time series is used as an image feature which contains the entire information of the feature, based on which the similar biomedical images are retrieved in our work. Here, the physician can point out the disorder present in the patient report by retrieving the most similar report from related reference reports. Open Access Series of Imaging Studies (OASIS) magnetic resonance imaging dataset is used for the evaluation of the proposed approach. The experimental result of the proposed system shows that the retrieval efficiency is better than the other existing systems.

show abstract

“…In general, content-based image retrieval (CBIR) [20], [21] is using image content features to retrieve images from a large image database or the Internet. The core technique of CBIR is how to extract the image invariant feature effectively.…”

Section: A Content Based Image Retrievalmentioning

confidence: 99%

Color Image Invariant Feature Extraction by a Topological Property Motivated PCNN Model

Kou

Yue

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Topological invariant features take priority over other vision features in early visual perception stage, which is the core idea of topological perception theory. In order to improve the robustness and distinguishability of the invariant features extracted by pulse coupled neural network (PCNN), the topological properties are integrated into PCNN. The improved PCNN model is called as topological property motivated PCNN (TPCNN), which adopts the saliency map calculated by the spectral residual approach as the important topological properties (the connectivity, and the number of holes in target). In TPCNN, firstly, the normalized saliency map is used as a linking coefficient to enhance the importance of saliency object when we calculating the invariant features. Secondly, the entropy signature of the saliency map is treated as an additional new feature and merged into original features calculated by PCNN, then the final invariant feature is obtained. The proposed TPCNN is used to calculate the invariant feature of different kinds of fish in the paper. Experimental results show that TPCNN outperforms the state-of-art models on invariant features extraction.INDEX TERMS Pulse coupled neural network, invariant feature extraction, topological perception theory, saliency map, spectral residual approach.

show abstract

Image classification and retrieval using optimized Pulse-Coupled Neural Network

Cited by 40 publications

References 27 publications

Underwater Terrain Positioning Method Using Maximum a Posteriori Estimation and PCNN Model

Underwater Terrain Positioning Method Using Maximum a Posteriori Estimation and PCNN Model

A New Retrieval Algorithm Based on Pulse Coupled Neural Network for Biomedical Images

Color Image Invariant Feature Extraction by a Topological Property Motivated PCNN Model

Contact Info

Product

Resources

About