Click here to Skip to main content
Click here to Skip to main content

Image Recognition with Neural Networks

, 30 Oct 2007 CPOL
Rate this:
Please Sign up or sign in to vote.
This article contains a brief description of BackPropagation Artificial Neural Network and its implementation for Image Recognition
Screenshot - screen211.png

Introduction

Artificial Neural Networks are a recent development tool that are modeled from biological neural networks. The powerful side of this new tool is its ability to solve problems that are very hard to be solved by traditional computing methods (e.g. by algorithms). This work briefly explains Artificial Neural Networks and their applications, describing how to implement a simple ANN for image recognition.

Background

I will try to make the idea clear to the reader who is just interested in the topic.

About Artificial Neural Networks (ANNs)

Artificial Neural Networks (ANNs) are a new approach that follow a different way from traditional computing methods to solve problems. Since conventional computers use algorithmic approach, if the specific steps that the computer needs to follow are not known, the computer cannot solve the problem. That means, traditional computing methods can only solve the problems that we have already understood and knew how to solve. However, ANNs are, in some way, much more powerful because they can solve problems that we do not exactly know how to solve. That's why, of late, their usage is spreading over a wide range of area including, virus detection, robot control, intrusion detection systems, pattern (image, fingerprint, noise..) recognition and so on.

ANNs have the ability to adapt, learn, generalize, cluster or organize data. There are many structures of ANNs including, Percepton, Adaline, Madaline, Kohonen, BackPropagation and many others. Probably, BackPropagation ANN is the most commonly used, as it is very simple to implement and effective. In this work, we will deal with BackPropagation ANNs.

BackPropagation ANNs contain one or more layers each of which are linked to the next layer. The first layer is called the "input layer" which meets the initial input (e.g. pixels from a letter) and so does the last one "output layer" which usually holds the input's identifier (e.g. name of the input letter). The layers between input and output layers are called "hidden layer(s)" which only propagate the previous layer's outputs to the next layer and [back] propagates the following layer's error to the previous layer. Actually, these are the main operations of training a BackPropagation ANN which follows a few steps.

A typical BackPropagation ANN is as depicted below. The black nodes (on the extreme left) are the initial inputs. Training such a network involves two phases. In the first phase, the inputs are propagated forward to compute the outputs for each output node. Then, each of these outputs are subtracted from its desired output, causing an error [an error for each output node]. In the second phase, each of these output errors is passed backward and the weights are fixed. These two phases is continued until the sum of [square of output errors] reaches an acceptable value.

Screenshot - fig1_nnet_thinner.png

Implementation

The network layers in the figure above are implemented as arrays of structs. The nodes of the layers are implemented as follows:

[Serializable]
struct PreInput
{
    public double Value;
    public double[] Weights;            
};

[Serializable]
struct Input
{
    public double InputSum;                
    public double Output;                
    public double Error;                
    public double[] Weights;        
};
            
[Serializable]        
struct Hidden        
{                
    public double InputSum;                    
    public double Output;                
    public double Error;                
    public double[] Weights;        
};
            
[Serializable]        
struct Output<T> where T : IComparable<T>         
{                
    public double InputSum;                
    public double output;                
    public double Error;                
    public double Target;     
    public T Value;   
};

The layers in the figure are implemented as follows (for a three layer network):

private PreInput[] PreInputLayer;
private Input[] InputLayer;
private Hidden[] HiddenLayer;
private Output<string>[] OutputLayer;

Training the network can be summarized as follows:

  • Apply input to the network.
  • Calculate the output.
  • Compare the resulting output with the desired output for the given input. This is called the error.
  • Modify the weights for all neurons using the error.
  • Repeat the process until the error reaches an acceptable value (e.g. error < 1%), which means that the NN was trained successfully, or if we reach a maximum count of iterations, which means that the NN training was not successful.

It is represented as shown below:

void TrainNetwork(TrainingSet,MaxError)
{
     while(CurrentError>MaxError)
     {
          foreach(Pattern in TrainingSet)
          {
               ForwardPropagate(Pattern);//calculate output 
               BackPropagate()//fix errors, update weights
          }
     }
}

This is implemented as follows:

public bool Train()
{
    double currentError = 0;
    int currentIteration = 0;
    NeuralEventArgs Args = new NeuralEventArgs() ;

    do
    {
        currentError = 0;
        foreach (KeyValuePair<T, double[]> p in TrainingSet)
        {
            NeuralNet.ForwardPropagate(p.Value, p.Key);
            NeuralNet.BackPropagate();
            currentError += NeuralNet.GetError();
        }
                
        currentIteration++;
    
        if (IterationChanged != null && currentIteration % 5 == 0)
        {
            Args.CurrentError = currentError;
            Args.CurrentIteration = currentIteration;
            IterationChanged(this, Args);
        }

    } while (currentError > maximumError && currentIteration < 
    maximumIteration && !Args.Stop);

    if (IterationChanged != null)
    {
        Args.CurrentError = currentError;
        Args.CurrentIteration = currentIteration;
        IterationChanged(this, Args);
    }

    if (currentIteration >= maximumIteration || Args.Stop)   
        return false;//Training Not Successful
            
    return true;
}

Where ForwardPropagate(..) and BackPropagate() methods are as shown for a three layer network:

private void ForwardPropagate(double[] pattern, T output)
{
    int i, j;
    double total;
    //Apply input to the network
    for (i = 0; i < PreInputNum; i++)
    {
        PreInputLayer[i].Value = pattern[i];
    }
    //Calculate The First(Input) Layer's Inputs and Outputs
    for (i = 0; i < InputNum; i++)
    {
        total = 0.0;
        for (j = 0; j < PreInputNum; j++)
        {
            total += PreInputLayer[j].Value * PreInputLayer[j].Weights[i];
        }
        InputLayer[i].InputSum = total;
        InputLayer[i].Output = F(total);
    }
    //Calculate The Second(Hidden) Layer's Inputs and Outputs
    for (i = 0; i < HiddenNum; i++)
    {
        total = 0.0;
        for (j = 0; j < InputNum; j++)
        {
            total += InputLayer[j].Output * InputLayer[j].Weights[i];
        }

        HiddenLayer[i].InputSum = total;
        HiddenLayer[i].Output = F(total);
    }
    //Calculate The Third(Output) Layer's Inputs, Outputs, Targets and Errors
    for (i = 0; i < OutputNum; i++)
    {
        total = 0.0;
        for (j = 0; j < HiddenNum; j++)
        {
            total += HiddenLayer[j].Output * HiddenLayer[j].Weights[i];
        }

        OutputLayer[i].InputSum = total;
        OutputLayer[i].output = F(total);
        OutputLayer[i].Target = OutputLayer[i].Value.CompareTo(output) == 0 ? 1.0 : 0.0;
        OutputLayer[i].Error = (OutputLayer[i].Target - OutputLayer[i].output) *
                                       (OutputLayer[i].output) * (1 - OutputLayer[i].output);
        }
    }        
    
private void BackPropagate()
{
    int i, j;
    double total;
    //Fix Hidden Layer's Error
    for (i = 0; i < HiddenNum; i++)
    {
        total = 0.0;
        for (j = 0; j < OutputNum; j++)
        {
            total += HiddenLayer[i].Weights[j] * OutputLayer[j].Error;
        }
        HiddenLayer[i].Error = total;
    }
    //Fix Input Layer's Error
    for (i = 0; i < InputNum; i++)
    {
        total = 0.0;
        for (j = 0; j < HiddenNum; j++)
        {
            total += InputLayer[i].Weights[j] * HiddenLayer[j].Error;
        }
        InputLayer[i].Error = total;
    }
    //Update The First Layer's Weights
    for (i = 0; i < InputNum; i++)
    {
        for(j = 0; j < PreInputNum; j++)
        {
            PreInputLayer[j].Weights[i] +=
                LearningRate * InputLayer[i].Error * PreInputLayer[j].Value;
        }
    }
    //Update The Second Layer's Weights
    for (i = 0; i < HiddenNum; i++)
    {
        for (j = 0; j < InputNum; j++)
        {
            InputLayer[j].Weights[i] +=
                LearningRate * HiddenLayer[i].Error * InputLayer[j].Output;
        }
    }
    //Update The Third Layer's Weights
    for (i = 0; i < OutputNum; i++)
    {
        for (j = 0; j < HiddenNum; j++)
        {
            HiddenLayer[j].Weights[i] +=
                LearningRate * OutputLayer[i].Error * HiddenLayer[j].Output;
        }
    }
}

Testing the App

The program trains the network using bitmap images that are located in a folder. This folder must be in the following format:

  • There must be one (input) folder that contains input images [*.bmp].
  • Each image's name is the target (or output) value for the network (the pixel values of the image are the inputs, of course) .

As testing the classes requires to train the network first, there must be a folder in this format. "PATTERNS" and "ICONS" folders [depicted below] in the Debug folder fit this format.

Screenshot - fig2_sampleInput_thinner.png Screenshot - fig3_sampleInput_thinner.png

History

  • 30th September, 2007: Simplified the app
  • 24th June, 2007: Initial Release

References & External Links

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Share

About the Author

Murat Firat
Software Developer (Senior)
Turkey Turkey
Has BS degree on CS, working as SW engineer at istanbul.

Comments and Discussions

 
AnswerRe: ImageProcessing.ToMatrix PinmemberMurat Firat17-Jun-08 11:05 
GeneralRe: ImageProcessing.ToMatrix Pinmemberdenny_cucu28-Jun-08 23:25 
GeneralRe: ImageProcessing.ToMatrix PinmemberHimdevi24-Mar-12 21:18 
GeneralRe: ImageProcessing.ToMatrix PinmemberMurat Firat25-Mar-12 12:55 
GeneralRe: ImageProcessing.ToMatrix PinmemberHimdevi26-Mar-12 5:22 
QuestionImage Detection PinmemberYehudaG12-May-08 5:12 
Questionwhat is the initial value of output layer??? Pinmembersandipmuk7-May-08 22:18 
AnswerRe: what is the initial value of output layer??? PinmemberMurat Firat11-May-08 21:22 
Questionwhats the network archeticture? Pinmemberjamilkhan00723-Apr-08 22:46 
GeneralRe: whats the network archeticture? PinmemberMurat Firat23-Apr-08 23:32 
QuestionRe: whats the network archeticture? Pinmemberjamilkhan00727-Apr-08 0:52 
GeneralRe: whats the network archeticture? PinmemberMurat Firat27-Apr-08 12:05 
GeneralRe: whats the network archeticture? Pinmemberjamilkhan0072-May-08 23:29 
QuestionFace Detection Nueral Network? Pinmemberjamilkhan00718-Apr-08 2:53 
Great job buddySmile | :) i need a bit help, how can i decide the architecture of a nueral network? means for how many inputs, outputs etc for a particular problem? can u suggest me architecture for face detection in an image plzz? or any other resource u can suggest which can ans my question?
Thanx in advance
 
(Jameel)

QuestionImage Recognition Advanced Engine Development Pinmemberankswe15-Apr-08 4:51 
GeneralExcellent! Pinmembernewbie0827-Mar-08 2:00 
GeneralRe: Excellent! PinmemberMurat Firat28-Mar-08 22:52 
GeneralYou are awesome! Pinmemberjadeburton20-Mar-08 15:52 
GeneralRe: You are awesome! PinmemberMurat Firat23-Mar-08 6:29 
Generalpattern recognition PinmemberK|nS|ayer28-Feb-08 22:01 
AnswerRe: pattern recognition PinmemberMurat Firat29-Feb-08 22:29 
Questionpattern recognition method Pinmemberrie athena6-Feb-08 15:00 
AnswerRe: pattern recognition method PinmemberMurat Firat7-Feb-08 8:01 
GeneralThreshold Value Pinmembercbc100031-Dec-07 15:40 
AnswerRe: Threshold Value PinmemberMurat Firat1-Jan-08 3:14 
GeneralAbout the pattern and input Pinmemberrandy1014198326-Nov-07 3:51 
GeneralRe: About the pattern and input PinmemberMurat Firat26-Nov-07 5:26 
GeneralAbout demo project Pinmembernewrocker24-Nov-07 21:27 
AnswerRe: About demo project PinmemberMurat Firat25-Nov-07 11:08 
GeneralQuestions Pinmemberrandy1014198324-Nov-07 17:43 
GeneralRe: Questions PinmemberMurat Firat25-Nov-07 11:01 
QuestionDoubt in Input and Hidden Node. PinmemberVimalr18-Nov-07 20:24 
AnswerRe: Doubt in Input and Hidden Node. PinmemberMurat Firat19-Nov-07 2:09 
GeneralReg deciding the layer units Pinmemberi_coder15-Nov-07 7:57 
GeneralRe: Reg deciding the layer units PinmemberMurat Firat15-Nov-07 21:15 
QuestionCan I use your Neural network implementation for this... PinmemberJean-Francois Dufour12-Nov-07 23:42 
AnswerRe: Can I use your Neural network implementation for this... PinmemberMurat Firat13-Nov-07 9:36 
GeneralExcellent Pinmembermerlin98131-Oct-07 5:01 
GeneralRe: Excellent PinmemberMurat Firat1-Nov-07 0:10 
GeneralError in HiddenNum.cs PinmemberCBrauer4-Oct-07 9:07 
GeneralRe: Error in HiddenNum.cs PinmemberMurat Firat30-Oct-07 14:16 
Questionerror in backpropagation code Pinmemberleeyang114012-Sep-07 10:01 
AnswerRe: error in backpropagation code PinmemberMurat Firat12-Sep-07 11:31 
GeneralRe: error in backpropagation code Pinmemberleeyang114012-Sep-07 12:40 
GeneralRe: error in backpropagation code PinmemberMurat Firat12-Sep-07 18:50 
QuestionAbout Question Of Hidden Layer Pinmembercbc100011-Sep-07 22:49 
AnswerRe: About Question Of Hidden Layer PinmemberMurat Firat12-Sep-07 4:00 
QuestionQuestion Pinmemberbelenong10-Sep-07 19:02 
AnswerRe: Question PinmemberMurat Firat11-Sep-07 0:29 
Generalhelp Pinmembershec3-Sep-07 11:42 

General General    News News    Suggestion Suggestion    Question Question    Bug Bug    Answer Answer    Joke Joke    Rant Rant    Admin Admin   

Use Ctrl+Left/Right to switch messages, Ctrl+Up/Down to switch threads, Ctrl+Shift+Left/Right to switch pages.

| Advertise | Privacy | Terms of Use | Mobile
Web03 | 2.8.141223.1 | Last Updated 30 Oct 2007
Article Copyright 2007 by Murat Firat
Everything else Copyright © CodeProject, 1999-2014
Layout: fixed | fluid