Pulse Coupled Neural Network

This paper presents the first physiologically motivated pulse coupled neural network (PCNN)-based image fusion network for object detection. Primate vision processing principles, such as expectation driven filtering, state dependent modulation, temporal synchronization, and multiple processing paths are applied to create a physiologically motivated image fusion network. PCNN's are used to fuse the results of several object detection techniques to improve object detection accuracy. Image processing techniques (wavelets, morphological, etc.) are used to extract target features and PCNN's are used to focus attention by segmenting and fusing the information. The object detection property of the resulting image fusion network is demonstrated on mammograms and Forward Looking Infrared Radar (FLIR) images. The network removed 94% of the false detections without removing any true detections in the FLIR images and removed 46% of the false detections while removing only 7% of the true detections in the mammograms. The model exceeded the accuracy obtained by any individual filtering methods or by logical ANDing the individual object detection technique results.

Brain extraction is an important preprocessing step for further processing (e.g., registration and morphometric analysis) of brain MRI data. Due to the operator-dependent and timeconsuming nature of manual extraction, automated or semi-automated methods are essential for large-scale studies. Automatic methods are widely available for human brain imaging, but they are not optimized for rodent brains and hence may not perform well. To date, little work has been done on rodent brain extraction. We present an extended pulse-coupled neural network algorithm that operates in 3-D on the entire image volume. We evaluated its performance under varying SNR and resolution and tested this method against the brain-surface extractor (BSE) and a level-set algorithm proposed for mouse brain. The results show that this method outperforms existing methods and is robust under low SNR and with partial volume effects at lower resolutions. Together with the advantage of minimal user intervention, this method will facilitate automatic processing of large-scale rodent brain studies.

A novel method for pattern recognition using Discrete Fourier Transforms on the global pulse signal of a pulse-coupled neural network (PCNN) is presented in this paper. We describe the mathematical model of the PCNN and an original way of analyzing the pulse of the network in order to achieve scale-and translation-independent recognition for isolated objects. We also analyze the error as a result of rotation. The system is used for recognizing simple geometric shapes and letters.

Biologically inspired image/signal processing like the pulse coupled neural network (PCNN) and the wavelet (packet) transforms are described. The two methods are applied to two-dimensional data in order to demonstrate the features of each method, pinpoint differences as well as similarities. The inherent properties (with respect to filtering, segmentation, etc) of the two appraches with respect to detectors for physics experiments as well as remote sensing are discussed.

This paper introduces an efficient approach to protect the ownership by hiding the iris data into a digital image for authentication purposes. The idea is to secretly embed an iris code data into the content of the image, which identifies the owner. Algorithms based on Biologically inspired Spiking Neural Networks, called Pulse Coupled Neural Network (PCNN) are first applied to increase the contrast of the human iris image and adjust the intensity with the median filter. It is followed by the PCNN segmentation algorithm to determine the boundaries of the human iris image by locating the pupillary boundary and limbus boundary of the human iris for further processing. A texture segmentation algorithm for isolating the iris from the human eye in a more accurate and efficient manner is presented.

Humans do not stare at an image, they foveate. Their eyes move about points of interest within the image collecting clues as to the content of the image. Object shape is one of the driving forces of foveation. These foveation points are generally corners and, to a lesser extent, the edges. The Pulse-Coupled Neural Network (PCNN) has the inherent ability to segment an image and the corners and edges of these segments are similar to the foveation points. Thus, it is a natural extension of PCNN technology to use it as a foveation engine. This paper will present theory and examples of foveation through the use of a PCNN, and it will also demonstrate that it can be quite useful in image recognition.

Motion-based segmentation is a very important capability for computer vision and video analysis. It depends fundamentally on the system's ability to estimate optic flow using temporally proximate image frames. This is often done using blockmatching. However, block-matching is sensitive to the presence of observational noise, which is inevitable in real images. Also, images often include regions of homogeneous intensity, where blockmatching is problematic. A better method in this case is to estimate motion at the region level. In the approach described in this paper, we have attempted to address the noise-sensitivity and texture-insufficiency problems using a two-pathway system. The pixel-level pathway is a multilayer pulse-coupled neural network (PCNN)like locally coupled network used to correct outliers in the blockmatching motion estimates and produce improved estimates in regions with sufficient texture. In contrast, the region-level pathway is used to estimate the motion for regions with little intensity variation. In this pathway, a PCNN network first partitions intensity images into homogeneous regions, and a motion vector is then determined for the whole region. The optic flows from both pathways are fused together based on the estimated intensity variation. The fused optic flow is then segmented by a one-layer PCNN network. Results on synthetic and real images are presented to demonstrate that the accuracy of segmentation is improved significantly by taking advantage of the complementary strengths and weaknesses of the two pathways. (S'86-M'91) received the Ph.D. degree in electrical engineering and post-doctoral training in computational neuroscience from the University of Virginia, Charlottesville.

We describe the implementation of a vision system based on a hardware neural processor. The architecture of the neural network processor has been designed to exploit the computational characteristics of electronics and the communication characteristics of optics in an optimal manner, thus it is based on an optical broadcast of input signals to a dense array of processing elements. The vision system has been built by use of a prototype implementation of a neural network processor with discrete optic and optoelectronic devices. It has been adapted to work as a Hamming classifier of the images taken with a 128 ϫ 128 complementary metal-oxide semiconductor image sensor. Its results, performance characteristics of the image classification system, and an analysis of its scalability in size and speed, with the improvement of the optoelectronic neural processor, are presented.

This paper will combine biological findings in the visual cortex of some small mammals with the increasing evidence of feedback from the brain to the sensors to create a Feedback Pulse-Coupled Neural Network. The main advantage of this algorithm is that it extracts portions of the input information with each iteration. The input is eventually altered to a steady-state output. However, during transition the input at different iterations presents primitive information of the input.

Pulse-coupled neural networks (PCNNs) are a biologically inspired type of neural networks. It is a simplified model of the cat’s visual cortex with local connections to other neurons. PCNN has the ability to extract edges, segments and texture information from images. Only a few changes to the PCNN parameters are necessary for effective operation on different types of data. This is an advantage over published image processing algorithms that generally require information about the target before they are effective. The main aim of this paper is to provide an accurate boundary detection algorithm of the prostate ultrasound images to assist radiologists in making their decisions. To increase the contrast of the ultrasound prostate image, the intensity values of the original images were adjusted firstly using the PCNN with median filter. It is followed by the PCNN segmentation algorithm to detect the boundary of the image. Combining adjusting and segmentation enable us to eliminate PCNN sensitivity to the setting of the various PCNN parameters whose optimal selection can be difficult and can vary even for the same problem. The experimental results obtained show that the overall boundary detection overlap accuracy offered by the employed PCNN approach is high compared with other machine learning techniques including Fuzzy C-mean and Fuzzy Type-II.

Image segmentation has attracted the attention of researcher for many decades. Different approaches have been developed in order to find the solution in many different segmentation situations. In this paper we propose a novel edge detection approach aimed to generate useful information to achieve segmentation. The proposed method is based on analysis of the information provided by the time matrix generated from a pulse coupled neural network, PCNN. This information represents gray level differences among the pixel images. Two different schemes for edge detection are presented. The first scheme is developed to generate edges from coarse images and the second one to deal with more detailed edges. Similarity of this method with a previous developed method based on fuzzy edge level detection is also covered in the paper. Final results show that the proposed method may be used as a new alternative to define image edges of different levels for further analysis.

Recent advances in the understanding of the mammalian visual cortex have led to new approaches for image processing techniques. As a result of this, computer simulations using the proposed visual cortex model have become very useful in the field of image processing. Models of this kind have the ability to efficiently extract image segments, edges and texture. They Ž . operate by generating a set of pulse images images with binary pixels for a static input. These pulse images display synchronized activity of neighboring neurons, and it is these images in which the information about segments, edges and texture are displayed. Pulse image generation is dependent on autowaves that travel throughout the image. In order to extend pulse Ž . image processing to multidimensional data i.e., data cubes , the autowaves are designed to expand in all of the cube's dimensions. In this fashion, pulse cubes can be created and the same analysis techniques that have been applied to two-dimensional pulse images can be applied to pulse image cubes. This paper examines and discusses multidimensional pulse image Ž . analysis applied to three-dimensional 3D chemical structural data of 17b-estradiol. q

Baoqing Prefecture in the Qing Dynasty In t he Qing Dynasty Baoqing prefecture in Hunan Province was a remote and economically underdeveloped region1 In order to overcome hardships , such as natural calamities , epidemics , poverty and female infanticide , social welfare institu2 tions naturally came into being1 Furt hermore , t here was an obvious trend toward cooperation between official and civil in2 stitutions1 Local social custom , official and gentry initiatives , as well as"courtesy toward commoners"educational mea2 sures facilitated t his cooperation1

This work presents a bottom-up visual attention model based on a Pulse-Coupled Neural Network for scene segmentation. Each object in a given scene is represented by a synchronized pulse train, while different objects fire at different phases. Taking this into account, the model focuses on one object at a time. Using this model, the limit of linear non-separability can be easily overcome and computer simulations show its good performance.

Image registration determines the relative orientation between two images. As there are different techniques for image registration, it is important to compare these techniques to identify the advantages and disadvantages of each one. In this paper, a comparison between a fast Fourier transform (FFT)-based technique, a contour-based technique, a wavelet-based technique, a Harris-Pulse Coupled Neural Network (PCNN)-based technique and Harris-Moment-based technique is presented. The algorithms were tested on Landsat Thematic Mapper (TM) and SPOT remote sensing images and its performance were compared using the Root Mean Square Error (RMSE).

Canada is one of the major exporters of wheat in the world. The quality of these exports is well known and factors such as lack of insect infestation are very important. The use of thermal images for subsequent analysis of temperatures profiles for grain ...

We present a new method to transform the spectral" pixel information of a micrograph into an tine geometric description, which allows us to analyse the morphology of granular materials. We use spectral and pulse-coupled neural network based segmentation techniques to generate blobs, and a newly developed algorithm to extract dilated contours. A constrained Delaunay tesselation of the contour points results in a triangular mesh. This mesh is the basic ingredient of the Discrete Chodal Axis Transform, which provides a morphological decomposition. Such decomposition allows for grain separation and the efficient computation of the granular materiak statistical features.

In this paper, we investigate the performance of pulse-coupled neural networks (PCNNs) to detect the damage caused by an earthquake. PCNN is an unsupervised model in the sense that it does not need to be trained, which makes it an operational tool during ...

In this paper we test an unsupervised neural network approach for extracting features from very high resolution X-band SAR images. The purpose of this study is buildings recognition in images of low density urban areas, acquired by COSMO-Skymed and TerraSAR-X satellites, by means of Pulse Coupled Neural Network (PCNN), a relatively novel unsupervised algorithm based on models of the visual cortex of small mammals. The features retrieved from georeferenced SAR images are compared against the ground truth provided by corresponding optical images. The accuracy yielded by PCNN is quantitatively evaluated and critically discussed, also in comparison with commonly used feature extraction techniques.

Pulse Coupled Neural Networks are a very useful tool for image processing and visual applications, since it has the advantages of being invariant to image changes as rotation, scale, or certain distortion. Among other characteristics, the PCNN changes a given image input into a temporal representation which can be easily later analyzed for pattern recognition. The structure of a PCNN though, makes it necessary to determine all of its parameters very carefully in order to function optimally, so that the responses to the kind of inputs it will be subjected are clearly discriminated allowing for an easy and fast post-processing yielding useful results. This tweaking of the system is a taxing process. In this paper we analyze and compare two methods for modeling PCNNs. A purely mathematical model is programmed and a similar circuital model is also designed. Both are then used to determine the optimal values of the several parameters of a PCNN: gain, threshold, time constants for feed-in and threshold and linking leading to an optimal design for image recognition. The results are compared for usefulness, accuracy and speed, as well as the performance and time requirements for fast and easy design, thus providing a tool for future ease of management of a PCNN for different tasks.

Information mining from heavy SAR images is considered from the point of view of the procedure automatization. Two schemes based on Neural Networks are evaluated, one based on the Self Organizing Map method exploiting polarimetric information and oriented to land cover classification, the other based on the Pulse-Coupled Neural Networks aiming at characterizing the imaged buildings.

The concept of research was based on the selection of several representations, which later were correlated by means of classic, and neural methods. In the course of research, classic methods of image matching were tested and compared with neural methods that originated in the course of research. Additionally, experiments consisting in manual measurements, performed by independent observers, were conducted. The essence of methodology that was based on neural networks consisted in the preparation of suitable representations of image fragments and using them for the classification of various types of neural networks. One of the assumed methods was based on the distribution of image gradient module value and of its direction. The usability of that representation for the selection of sub-images was tested by means of SOM Kohonen neural network. Another method consisted in the utilization of the log-polar and log-Hough transforms, which are considered to be simplified models of preliminar...

An automatic parameter setting method of a simpli- fied pulse coupled neural network (SPCNN) is proposed here. Our method successfully determines all the adjustable parameters in SPCNN and does not need any training and trials as required by previous methods. In order to achieve this goal, we try to derive the general formulae of dynamic threshold and internal activity of

Although the Pulse Coupled Neural Network (PCNN) as well as FBPCNN (with feed-back) have been, since 1990, well known image analysis methods, they are still developed to solve the problems related to estimation of initial network parameters. Most of such parameters vary dependently on the character of input images (e.g. range of colors, noise strength, shapes diversity) to offer the best results. This work aims to establish parameters of the network based on FBPCNN architecture, applied in processing of images of metals' microstructures. The paper contains detailed description of implemented neural network followed by sensitivity analysis of the network on parameters' change. On the basis of the performed analysis, the parameters with major influence on the final results were determined and investigated in details. The results obtained in the process of image analysis by using proposed FBPCNN were passed as input data initiating Watershed algorithm for the purposes of segmentation. Results of segmentation are presented in the paper as well.

In this paper, we present an automated approach for Ultrasound Biomicroscopy (UBM) glaucoma images analysis. To increase the efficiency of the introduced approach, an intensity adjustment process is applied first using the Pulse Coupled Neural Network with a median filter. This is followed by applying the PCNN-based segmentation algorithm to detect the boundary of the anterior chamber of the eye image. Then, glaucoma clinical parameters have been calculated and normalized, followed by application of a rough set analysis to discover the dependency between the parameters and to generate set of reduct that contains minimal number of attributes. Experimental results show that the introduced approach is very successful and has high detection accuracy.