org.neuroph.imgrec

Class ImageRecognitionHelper

java.lang.Object

org.neuroph.imgrec.ImageRecognitionHelper

public class ImageRecognitionHelper
extends java.lang.Object

Provides methods to create neural network and training set for image recognition. This class is mostly based on the code from tileclassification utility by Jon Tait

Constructor Summary

Constructors

Constructor and Description
ImageRecognitionHelper()

Method Summary

Modifier and Type	Method and Description
static DataSet	createBlackAndWhiteTrainingSet(java.util.List<java.lang.String> imageLabels, java.util.Map<java.lang.String,FractionRgbData> rgbDataMap) Creates binary black and white training set for the specified image labels and rgb data white = 0 black = 1
static DataSet	createHSLTrainingSet(java.util.List<java.lang.String> imageLabels, java.util.Map<java.lang.String,FractionHSLData> hslDataMap) Creates training set for the specified image labels and hsl data
static DataSet	createImageDataSetFromFile(java.lang.String imageDir, java.util.List<java.lang.String> imageLabels, java.lang.String junkDir, ColorMode colorMode, Dimension samplingResolution, java.lang.String trainingSetName, int numOfPictures)
static NeuralNetwork	createNewNeuralNetwork(java.lang.String label, Dimension samplingResolution, ColorMode colorMode, java.util.List<java.lang.String> imageLabels, java.util.List<java.lang.Integer> layersNeuronsCount, TransferFunctionType transferFunctionType) Creates and returns new neural network for image recognition.
static DataSet	createRGBTrainingSet(java.util.List<java.lang.String> imageLabels, java.util.Map<java.lang.String,FractionRgbData> rgbDataMap) Creates training set for the specified image labels and rgb data
static DataSet	createTrainingSet(java.util.List<java.lang.String> imageLabels, java.util.Map<java.lang.String,FractionRgbData> rgbDataMap) Deprecated. Use createRGBTrainingSet instead
static java.util.Map<java.lang.String,FractionHSLData>	getFractionHSLDataForDirectory(java.io.File imgDir, Dimension samplingResolution)
static java.util.Map<java.lang.String,FractionRgbData>	getFractionRgbDataForDirectory(java.io.File imgDir, Dimension samplingResolution) Loads images from the specified dir, scales to specified resolution and creates RGB data for each image Puts HSL data in a Map using filenames as keys, and returns that map

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ImageRecognitionHelper

public ImageRecognitionHelper()

Method Detail

createNewNeuralNetwork

public static NeuralNetwork createNewNeuralNetwork(java.lang.String label,
                                                   Dimension samplingResolution,
                                                   ColorMode colorMode,
                                                   java.util.List<java.lang.String> imageLabels,
                                                   java.util.List<java.lang.Integer> layersNeuronsCount,
                                                   TransferFunctionType transferFunctionType)

Creates and returns new neural network for image recognition. Assumes that all of the FractionRgbData objects in the given map have identical length arrays in them so that the input layer of the neural network can be created here.

Parameters:

label - neural network label

samplingResolution - sampling resolution (image size)

imageLabels - image labels

layersNeuronsCount - neuron counts in hidden layers

transferFunctionType - type of transfer function to use for neurons in network

colorMode - color mode

Returns:

createTrainingSet

public static DataSet createTrainingSet(java.util.List<java.lang.String> imageLabels,
                                        java.util.Map<java.lang.String,FractionRgbData> rgbDataMap)

Deprecated. Use createRGBTrainingSet instead

Creates training set for the specified image labels and rgb data. Thi method is now forwarded to createRGBTrainingSet

Parameters:

imageLabels - image labels

rgbDataMap - map collection of rgb data

Returns:

training set for the specified image data

createRGBTrainingSet

public static DataSet createRGBTrainingSet(java.util.List<java.lang.String> imageLabels,
                                           java.util.Map<java.lang.String,FractionRgbData> rgbDataMap)

Creates training set for the specified image labels and rgb data

Parameters:

imageLabels - image labels

rgbDataMap - map collection of rgb data

Returns:

training set for the specified image data

createHSLTrainingSet

public static DataSet createHSLTrainingSet(java.util.List<java.lang.String> imageLabels,
                                           java.util.Map<java.lang.String,FractionHSLData> hslDataMap)

Creates training set for the specified image labels and hsl data

Parameters:

imageLabels - image labels

hslDataMap - map colletction of hsl data

Returns:

training set for the specified image data

createBlackAndWhiteTrainingSet

public static DataSet createBlackAndWhiteTrainingSet(java.util.List<java.lang.String> imageLabels,
                                                     java.util.Map<java.lang.String,FractionRgbData> rgbDataMap)
                                              throws VectorSizeMismatchException

Creates binary black and white training set for the specified image labels and rgb data white = 0 black = 1

Parameters:

imageLabels - image labels

rgbDataMap - map collection of rgb data

Returns:

binary black and white training set for the specified image data

Throws:

VectorSizeMismatchException

getFractionRgbDataForDirectory

public static java.util.Map<java.lang.String,FractionRgbData> getFractionRgbDataForDirectory(java.io.File imgDir,
                                                                                             Dimension samplingResolution)
                                                                                      throws java.io.IOException

Loads images from the specified dir, scales to specified resolution and creates RGB data for each image Puts HSL data in a Map using filenames as keys, and returns that map

Parameters:

imgDir -

samplingResolution -

Throws:

java.io.IOException

getFractionHSLDataForDirectory

public static java.util.Map<java.lang.String,FractionHSLData> getFractionHSLDataForDirectory(java.io.File imgDir,
                                                                                             Dimension samplingResolution)
                                                                                      throws java.io.IOException

Throws:

java.io.IOException

createImageDataSetFromFile

public static DataSet createImageDataSetFromFile(java.lang.String imageDir,
                                                 java.util.List<java.lang.String> imageLabels,
                                                 java.lang.String junkDir,
                                                 ColorMode colorMode,
                                                 Dimension samplingResolution,
                                                 java.lang.String trainingSetName,
                                                 int numOfPictures)