Classification and Segmentation of Visual Patterns Based on Receptive and Inhibitory Fields

  title={Classification and Segmentation of Visual Patterns Based on Receptive and Inhibitory Fields},
  author={Bruno Jos{\'e} Torres Fernandes and George D. C. Cavalcanti and Ing Ren Tsang},
  journal={2008 Eighth International Conference on Hybrid Intelligent Systems},
This paper presents a new model to realize a supervised image segmentation task. [] Key Method Also, in order to work with the SCRF model, is proposed here a new artificial neural network, called IPyraNet, which is a hybrid implementation of the recently described PyraNet and the nonclassical receptive fields inhibition. Furthermore, the model and the network are applied together in order to realize a satellite image segmentation task.

Figures and Tables from this paper

Nonclassical Receptive Field Inhibition Applied to Image Segmentation
A new artiflcial neural network, called I-PyraNet, is proposed, which is a hybrid implementation of the recently described PyraNet and the nonclassical receptive flelds inhibition to accomplish a satellite image segmentation task.
Lateral Inhibition Pyramidal Neural Network for Image Classification
The proposed model is a supervised image segmentation system, called segmentation and classification based on receptive fields, and the results obtained are better than that of other state-of-the-art methods.
A receptive field based approach for face detection
The neural network is called I-PyraNet which is a hybrid implementation of the PyraNet and the concepts of the inhibitory fields and the 2-D Gabor filter is presented.
Enhancing Semantic Segmentation of Aerial Images with Inhibitory Neurons
This paper begins with deep network architectures such as VGG and ResNet, and proposes an approach to add lateral inhibition in each output neuron to reduce its impact on its neighbours, both in fine-tuning pre-trained models and training from scratch.
A novel similarity-based approach for image segmentation
  • Juan Deng
  • Computer Science
    2009 International Conference on Image Analysis and Signal Processing
  • 2009
A similarity-based approach which segments an image into different regions according to a similarity measurement C which reflects the relationship between a pixel and its neighborhood, and presents an information-lessening method to reduce unnecessary details.
Multilevel Object Extraction by BDSONN Architecture
The BDSONN architecture addresses the inherent limitations of the multilayer self-organizing neural network (MLSONN) architecture when it comes to the extraction of binary objects.
Binary Object Extraction by Bidirectional Self-Organizing Neural Network Architecture
A multilevel version of the standard sigmoidal activation function was introduced in [33, 34, 232, 233] for inducing multiscaling capability in the functionality of the architecture, without increasing the network complexity in the process.
Target Tracking Using Fuzzy Hostility Induced Segmentation of Optical Flow Field
An interesting application of the soft computing paradigm involving fuzzy set-theoretic concepts is the tracking of targets from a motion scene preceded by faithful extraction of motion object


Contour detection based on nonclassical receptive field inhibition
The proposed biologically motivated method to improve contour detection in machine vision, called nonclassical receptive field (non-CRF) inhibition (more generally, surround inhibition or suppression), is proposed and is more useful for contour-based object recognition tasks, than traditional edge detectors, which do not distinguish between contour and texture edges.
A Pyramidal Neural Network For Visual Pattern Recognition
This paper applies PyraNet to determine gender from a facial image, and compares its performance on the standard facial recognition technology (FERET) database with three classifiers: The convolutional neural network (NN), the k-nearest neighbor (k-NN), and the support vector machine (SVM).
A threshold selection method from gray level histograms
A nonparametric and unsupervised method ofautomatic threshold selection for picture segmentation is presented. An optimal threshold is selected by the discriminant criterion, namely, so as to
Neural Networks for Pattern Recognition
A supervised segmentation scheme for cancerology color images
  • C. Meurle, G. Lebrun, O. Lézoray, A. Elmoataz
  • Environmental Science, Computer Science
    Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795)
  • 2003
A new scheme for color image segmentation based on supervised pixel classification methods, which is suitable for the detection of color objects in noisy environment and is particularly efficient on cytological color images.
Backpropagation Applied to Handwritten Zip Code Recognition
This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
Skin segmentation using color pixel classification: analysis and comparison
This work finds that color quantization can be as low as 64 bins per channel, although higher histogram sizes give better segmentation performance, and that the Bayesian classifier with the histogram technique and the multilayer perceptron classifier are found to perform better compared to other tested classifiers.
Some methods for classification and analysis of multivariate observations
The main purpose of this paper is to describe a process for partitioning an N-dimensional population into k sets on the basis of a sample. The process, which is called 'k-means,' appears to give
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
The fundamental principles, basic mechanisms, and formal analyses involved in the development of parallel distributed processing (PDP) systems are presented in individual chapters contributed by
A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters
Abstract Two fuzzy versions of the k-means optimal, least squared error partitioning problem are formulated for finite subsets X of a general inner product space. In both cases, the extremizing