Go to top

Image Recognition with Neural Networks

, 30 Oct 2007
 Rate this:
This article contains a brief description of BackPropagation Artificial Neural Network and its implementation for Image Recognition

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.

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.

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.

History

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

Share

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

You may also be interested in...

Expanding active decision-making: The power of integrating business rules and events

 Re: Network...? Murat Firat 14-Jun-10 20:11
 Training image Minju87 13-Jun-10 4:05
 Re: Training image Murat Firat 14-Jun-10 19:55
 The program itself includes a training algorithm under "lib" directory. That if the images are not recognized can be because images are so similar or the network is not trained enough. Also each training image must state a different pattern (e.g. letter)
 hight and low? [modified] yeah1000 28-Apr-10 7:43
 Re: hight and low? Murat Firat 29-Apr-10 3:05
 Train 2 by 2 and Then Join the .Net file ? subsari12 22-Apr-10 21:40
 Re: Train 2 by 2 and Then Join the .Net file ? Murat Firat 25-Apr-10 11:56
 Re: Train 2 by 2 and Then Join the .Net file ? subsari12 30-Apr-10 4:12
 great work Mikant 8-Feb-10 10:51
 Re: great work Murat Firat 9-Feb-10 2:02
 high n low ? rasleen_13 6-Dec-09 5:00
 Re: high n low ? Murat Firat 6-Dec-09 23:08
 How can i know what is desired output of each node? ranzan Pokhrel 14-Nov-09 16:01
 Re: Complex Numbers Murat Firat 24-Oct-09 7:55
 Awesome!!!! zorou 19-Aug-09 8:11
 what is the activation function?????? shanaprasad2009 10-Jun-09 12:16
 Re: what is the activation function?????? Scott Benner 25-Jun-09 8:36
 webcame zulham97 14-May-09 22:08
 hey need help Member 4530771 4-May-09 0:03
 Re: hey need help SafarTimura 9-May-09 12:27
 what is the convergence? onuriztech 7-Apr-09 9:27
 Re: what is the convergence? Murat Firat 8-Apr-09 1:20
 Current Error jimbobmcgee 30-Mar-09 9:00
 problem running and compiling prophet86 17-Mar-09 8:15
 Re: problem running and compiling zimpzon 15-Mar-10 22:37
 [Message Deleted] Member 4530771 15-Mar-09 3:15
 Code in VB.Net mu'a 7-Mar-09 9:44
 what can i do to increase acuracy? Member 4530771 3-Mar-09 4:00
 Re: what can i do to increase acuracy? SafarTimura 9-May-09 12:21
 Unhandled exception CristinaF 8-Dec-08 7:41
 Re: Unhandled exception CristinaF 8-Dec-08 8:19
 Classification Image....? demonlove 7-Dec-08 4:04
 Re: Classification Image....? SafarTimura 9-May-09 12:32
 is this feed forward neural network? Member 4530771 29-Nov-08 20:35
 Training takes so long time, any idea? tulipvn 18-Nov-08 0:26
 Re: Training takes so long time, any idea? Murat Firat 21-Nov-08 7:54
 Re: Training takes so long time, any idea? Himdevi 27-Mar-12 4:20
 Compiling Error in Visual C# 2008 Express mangotj 17-Oct-08 16:02
 recognition brimzi 12-Oct-08 23:59
 Question [modified] tulipvn 8-Oct-08 0:41
 Java version? tulipvn 23-Sep-08 4:43
 Re: Java version? Murat Firat 27-Sep-08 10:37
 Image size and accuracy visusnet 22-Sep-08 11:00
 Re: Image size and accuracy Murat Firat 27-Sep-08 10:32
 Calculating output layer error jack_wind 11-Sep-08 22:32
 Re: Calculating output layer error Murat Firat 18-Sep-08 5:09
 Last Visit: 31-Dec-99 18:00     Last Update: 1-Oct-14 23:12 Refresh « Prev1234 Next »