Image+processing
Upcoming SlideShare
Loading in...5
×
 

Image+processing

on

  • 552 views

 

Statistics

Views

Total Views
552
Views on SlideShare
552
Embed Views
0

Actions

Likes
0
Downloads
18
Comments
0

0 Embeds 0

No embeds

Accessibility

Categories

Upload Details

Uploaded via as Microsoft Word

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

Image+processing Image+processing Document Transcript

  • ABSTRACTA novel method for imageprocessing and pattern recognitionusing Discrete FourierTransformations on the global pulsesignal of a pulse-coupled neuralnetwork (PCNN) is presented inthis paper. The PCNN is an imagetransform that removes“unimportant” details whileimproving the overall quality of the INTRODUCTION During the last few years there was aimage. It may also provides shift of the emphasis in the artificial neuralsubstantial noise smoothing without network community toward spiking or pulse-losing image pattern and shape coupled neural networks. Motivated by biological discoveries, many studies considerinformation. pulse coupled neural networks with spike- We describe the timing as an essential component inmathematical model of the PCNN information processing by the brain.and an original way of analyzing Pulse-coupled neural networksthe pulse of the network in order to (PCNN) were introduced as a simple model for the cortical neurons in the visual area ofachieve better quality of the the cats brain.These neural models areimage ,scale and translation- proposed by Eckhorn and Johnson.independent recognition for isolated . The essential model of PCNN, isobjects. described with details, that can be implemented to perform a number of digital image processing applications. We describe in the next sections a model that evaluates the global pulse of a PCNN in order to find correlation in the pulse signal and achieve pattern recognition. IMAGE PROCESSING & its Purpose: 1
  • Image processing is any form of information trained to fire (or not), for particular inputprocessing for which the input is an image, patterns. In the using mode, when a taughtsuch as photographs or frames of video; the input pattern is detected at the input, itsoutput of image processing can be either an associated output becomes the currentimage or a set of characteristics or parameters output. If the input pattern does not belong inrelated to the image. Most image-processing the taught list of input patterns, the firing ruletechniques involve treating the image as a is used to determine whether to fire or not.two-dimensional signal and applying standard In PCNN,a neuron is operated in using mode.signal-processing techniques to it. .Basic purpose of image processing is for: 1. Improvement of pictorial information for human interpretation. 2. Processing of image data for storage, transmission, and representation for autonomous machine perception. WHAT IS PCNN ? A simple neuron A PCNN is a two-dimensional neuralnetwork. They are treated as the third WHY WE USE PCNN ?? In the field of digital image processing andgeneration of NN models, that takes in to pattern recognition , traditional models areaccount spiking nature of neurons. Each either subject to problems determined byneuron in the processing layer is directly tied geometric transforms (scaling, translation orto an image pixel or a set of neighboring rotation) or to high computational complexity.image pixels, the two linking and feeding Moreover, it is known today that parallelinputs are iteratively processed and together processing could solve determined byto produce a pulse image with features, that geometric transforms to take advantage of itcan be changed by varying the PCNN we need parallelisable models.parameters. Neural models fits this requirement.A Simple NeuronA neuron is a device with many inputs and IMAGE PROCESSING USING PCNNone output. The neuron has two modes of When PCNN is applied in image processing,operation; the training mode and the using it is a single layer two dimensional array ofmode. In the training mode, the neuron can be laterally linked neurons. 2
  • STRUCTURE OF PCNN ♦ At each time step the neuron output . ♦ Y is set to 1 when the internal♦ The number of neurons in the network activity U is greater than the thresholdis equal to the number of input image. One- function T. The threshold input at each timeto-one correspondence exists between image step is updated.pixels and neurons. ♦ The output of the neuron is consequently reset to zero when T is larger♦ Each pixel is connected to a unique than U. Thus at one time step the pulseneuron and each neuron is connected with the generator produces a single pulse at itssurrounding neurons with a radius of linking output whenever the value of U exceeds T.field.♦ The neuron receives input signalsfrom other neurons and ACTION OF PCNN IN IMAGEfrom external sources through the receptive PROCESSINGfields. • Segment Ability ♦ After the receptive fields have Because of the local interconnections betweencollected the inputs, they are divided into two the neurons, neurons encourage theiror more internal channels. One channel is the neighbours to fire only when they fire.feeding input F and the other is the linking Thus, if a group of neurons is close to firinginput L. then one neuron can trigger the entire group.♦ The feeding connections are required Thus, similar segments ofto have a slower characteristic response time the image fire in unison. This creates theconstant than those of the linking inputs. segmenting ability of the PCNN.♦ The linking inputs are biased and • Availability of Texturethen multiplied together, and further informationmultiplied with the feeding input to form the The edges have differing neighboring activitytotal internal activity U. than do the interior of the object. Thus, the♦ The pulse generator of the neuron edges, which will still fire in unison, but willconsists of a stepfunction do so at different times than do the interiorgenerator and a threshold signal signal segments. Thus, the edges are may begenerator. 3
  • isolated. After several iterations the groupings This is all about the behavior of PCNNof neurons tend to break in time. This “break- in image processing.up” is dependent upon the texture within a What is Pattern Recognition ?segment. This is caused by minor differences Pattern recognition can be defined as "the actthat eventually propagate (in time) to alter the of taking in raw data and taking an actionneural potentials. Thus, texture information based on the category of the data".becomesavailable. A complete pattern recognition system consists of a sensor that gathers the • Denoising observations to be classified or described; aFor denoising, the intensity of a noisy pixel is feature extraction mechanism that computessignificantly different from the numeric or symbolic information from theintensities of its surrounding pixels. observations; and a classification orTherefore, most neurons corresponding to description scheme that does the actual job ofnoisy pixels do not capture neighboring classifying or describing observations, relyingneurons or get captured by the neighboring on the extracted features.neurons. PATTERN RECOGNITION USING PCNN we can evaluates the global pulse of a PCNN in order to find correlation in the pulse signal and achieve pattern recognition. • Smoothing PCNNs can be thought of as a combination ofImage smoothing is accomplished by two kinds of pattern recognition:adjusting the intensity of each pixel based on • Statistical Pattern Recognitionthe neuron-firing pattern in its neighborhood. In this kind,a set of features is extracted from If a neuron fires sooner than a the pattern, grouped into a feature classes, andmajority of its neighbors fire, its intensity is recognition is based upon the partitioning ofadjusted downwards. the feature space in such a manner that new If a neuron fires after the majority of views are classified properly.its neighbors have fired, its intensity is • syntactic pattern recognitionadjusted upwards. It deals with the relationship between the If a neuron fires with the majority of features as well as the features themselves, soits neighbors no change is made. After that the face in that partially damaged picturecompleting the firing would still be recognizable.cycle (all neurons fire exactly once) thenetwork may be reset by forcing the threshold The problem with statistical recognition is itsvalues of all neurons to zero and the partially limited processing ability, and thesmoothing process may be repeated. problem with syntactic lies in the difficulty of gaining real time information (its very slow). 4
  • However, when the two are combined, the Information flow is mainly feed-forward butend result is a system that comes extremely there are also lateral interactions between theclose to obtaining the level of pattern pulse-coupled neurons.recognition that humans possess.ARCHITECTURE OF • The Pulse Coupled NeuralMODEL NetworksThe model proposed here is based on three The key of the entire system lies inmodules of processing: the neural analyzer that, in our case, is made • The pulse coupled neural of pulsecoupled neurons, which act like local network analyzer cells . • The Discrete Fourier Transform (DFT) module • The multilayer perceptron (MLP) classifier. ♣ The pulse train generated by the neurons is a direct result of stimulus 5
  • excitation and lateral interaction between Sijkl is the stimulus componentneurons. computed from the pixel intensity (<i+k, j+l>, ♣ Lateral interaction and further "<x,y>" meaning the intensity of the pixelstimulation determine the neurons to fire in with coordinates x and y) in the inputsynchrony in the homogenous areas image.Usually this value is normalized.associated to the image. These effects can be ♣ VF and VL are normalizingexploited in image segmentation. However, constants and M and W represent the constantour assumption is that the pulse train of the synaptic weights. M and W are computed byneurons captures somehow morphological using the inverse square ruleinformation from the image neurons captures f(k, l)=2/√ ( k2 + l2 )somehow morphological information from Y stands for the output of the neuron and canthe image. only take a binary value of 0 or 1. In the next equations we will refer ♣ The linking effect can be modeledto “n” as being the current iteration (discrete as follows:time step) where "n" varies from 1 to N-1 (NN is the total number of iterations; n = 0 is Uij [n] = F ij [n] .(1 - β. L ij [n] )the initial state).The dendritic tree can -(3)bedescribed by Thedendritic tree can be Uij[n] represents the internal activation of thedescribed by e neuron and β is the linking weight parameter.following equations: ♣ The pulse generator determines the -αFFij[n] = e .Fij [n - 1]+ firing events in the model. In fact, the pulse V F.∑ kl M kl S ijkl --(1) generator is also responsible for the modeling of the refractory period.Lij [n] = e-αF. Lij [n - 1] + ♣ As the neuron produces a spike, its V L.∑ kl W kl Yijkl[n-1] --(2) threshold is raised to prevent it from firing The two main components F and L again in the near future (established by theare called feeding and linking. The(i,j) pair stands for the position of the neuronin the map. αF and αL are time constants forfeed and link. 6
  • ♣ For each iteration the total numberparameter settings). The threshold is then of firings (Equation 6) over the entire PCNNdecreased to allow the neuron to fire when its is computed and stored in a global array Gactivation is increased. (see Fig. 1). G[n] =∑ ijY ij[n] , --(6) 1,if Uij[n] >Θij [n - 1]— where n is the iteration (n =0 …. N-1)(4) ♣ The global array is then used at theY ij[n] ={ 0,otherwise next levels of the system (to compute the DFT of the global pulse signal).Θij [n] = e-αΘ .Θij [n - 1]+VΘ.Y ij –(5) • The Discrete Fourier In equations (4) and (5) Θ ij[n] Transformationsrepresents the dynamic threshold of the We used the standard analysisneuron while αΘand VΘ are the time constant equations to calculate the DFT:and the normalization constant respectively. ♣ During the simulation, each Re X[k]= ∑N-1 i=0 G (i ) cos(2Πkiiteration updates the internal activity and the --( 7 )output for every neuron in the network, based /N) k=0,…N/2on the stimulus signal from the image and theprevious state of the network. 7
  • lm X[k]= ∑ N-1 i=0 G (i ) sin(2Πki  PCNN s can be used in several tasks of pattern recognition such as Face -( 8 ) recognition,Finger print/N) k=0,…N/2 identification etc.Computing the DFT means basically  PCNN s can be used in Image tocorrelating the input signal with each basis sound converters where the datafunction. produced by the PCNN (usually in ♥ The DFT yields two shorter signals the form of icons that can beto be analyzed. We used only the imaginary represented by only a few bits) willpart of the DFT in further processing but a be gathered and encode it for thecombination may be possible as well. sound generator.Our choicehad been motivated byexperimental observations that show arelative stability of the real part over all theshapes used for testing. ♥ We also enhanced speed by usingonly the imaginary part in the higher levels. CONCLUSIONS • The classifier Single-layered, laterally linked pulse-coupled Our classifier is basically a multilayer neural networks, being fairly insensitive toperceptron (MLP). The neural architecture local intensity variations and noise in digitalconsists of one input layer, one hidden layer images, are highly effective for imageand one output neuron. smoothing without♦ The input layer contains a number of blurring and eroding or dilating edges.inputs equal to the samples in the imaginary Furthermore, PCNNs are able topart of the DFT signal (Im X in eq. (8)). perform image segmentation.♦ Then, a hidden layer has an extension The PCNNs are presented in different models, not all the models are fully evaluated toof about 10 to 20% of the input layer.Because discover its potentials in image process.of the specific tasks used to test the system. However, this paper presented an evaluation ♦ The output layer contained only one for one of the PCNNs models, against manyneuron (target detection). An output value of variables that control the output..1 is equivalent to target detection whereas a Since PCNNs are still a rathervalue of 0 means no target detect. recent development, their future will undoubtedly bring a wealth of APPLICATIONS OF opportunities and challenges alike. Among PCNN the current problems that researchers are  PCNN s can be used in several tasks actively working on of image processing, such as image is: segmentation, edge extraction, object  An exact determination of the identification, object isolation. relationship between the various 8
  • parameter values and the performance of the network.  The establishment of an automated PCNN system, which can set parameters optimally.  Designing digital and optical hardware for the PCNNs, which can function in real- time applications. REFERENCES1) Image processing with pulse-coupledNeural Networks --J. M. Kinser, T.Lindbladh, -- Springer- Verlag LondonLimited,2)Image Processing with Neural Networks-areview -M. Egmont-Petersena., D. deRidderb, H. Handelsc,3)Network of spiking Neuron -The Thirdgeneration of Neural Network model ,NeuralNetwork--W. Maass,4)www.sciencedaily.com/releases5)www.yet2.com 9