Difference between revisions of "Example Thresholding"
From BoofCV
Jump to navigationJump to search (Created page with "<center> <gallery caption="Variable Lighting" heights=200 widths=600> File:VariableLight_Otsu_Square.jpg|Calibration grid. ''Left:'' original, ''Middle:'' Global Otsu, ''Right...") |
m |
||
(9 intermediate revisions by the same user not shown) | |||
Line 1: | Line 1: | ||
<center> | <center> | ||
<gallery caption="Variable Lighting" heights=200 widths=600> | <gallery caption="Variable Lighting" heights=200 widths=600> | ||
File:VariableLight_Otsu_Square.jpg|Calibration grid. ''Left:'' original, ''Middle:'' Global Otsu, ''Right:'' | File:VariableLight_Otsu_Square.jpg|Calibration grid. ''Left:'' original, ''Middle:'' Global Otsu, ''Right:'' Local Square | ||
</gallery> | </gallery> | ||
<gallery caption="Difficult Text Example" heights=200 widths=600> | <gallery caption="Difficult Text Example" heights=200 widths=600> | ||
File:Text_square_sauvola.jpg|''Left:'' Original, ''Middle:'' | File:Text_square_sauvola.jpg|''Left:'' Original, ''Middle:'' Local Square, ''Right:'' Sauvola | ||
</gallery> | </gallery> | ||
</center> | </center> | ||
Thresholding gray scale images is one of the most basic ways to segment an image. It is quick and effective in many situations. BoofCV provides several algorithms for computing both global and | Thresholding gray scale images is one of the most basic ways to segment an image. It is quick and effective in many situations. BoofCV provides several algorithms for computing both global and locally adaptive thresholds. | ||
Example Code: | Example Code: | ||
* [https://github.com/lessthanoptimal/BoofCV/blob/v0. | * [https://github.com/lessthanoptimal/BoofCV/blob/v0.37/examples/src/main/java/boofcv/examples/segmentation/ExampleThresholding.java ExampleThresholding.java] | ||
Concepts: | Concepts: | ||
* Segmentation | * Segmentation | ||
* Thresholding | * Thresholding | ||
Relevant Videos: | |||
* [https://youtu.be/TGg-xgTyaU8?t=525 New Algorithms in v0.28] | |||
Relevant Examples/Tutorials: | Relevant Examples/Tutorials: | ||
Line 29: | Line 32: | ||
* Demonstration of different techniques for automatic thresholding an image to create a binary image. The binary | * Demonstration of different techniques for automatic thresholding an image to create a binary image. The binary | ||
* image can then be used for shape analysis and other applications. Global methods apply the same threshold | * image can then be used for shape analysis and other applications. Global methods apply the same threshold | ||
* to the entire image. Local | * to the entire image. Local methods compute a local threshold around each pixel and can handle uneven | ||
* lighting, but produce noisy results in regions with uniform lighting. | * lighting, but produce noisy results in regions with uniform lighting. | ||
* | * | ||
Line 42: | Line 45: | ||
// convert into a usable format | // convert into a usable format | ||
GrayF32 input = ConvertBufferedImage.convertFromSingle(image, null, GrayF32.class); | |||
GrayU8 binary = new GrayU8(input.width,input.height); | |||
// Display multiple images in the same window | // Display multiple images in the same window | ||
Line 50: | Line 53: | ||
// Global Methods | // Global Methods | ||
GThresholdImageOps.threshold(input, binary, ImageStatistics.mean(input), true); | GThresholdImageOps.threshold(input, binary, ImageStatistics.mean(input), true); | ||
gui.addImage(VisualizeBinaryData.renderBinary(binary, null),"Global: Mean"); | gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Global: Mean"); | ||
GThresholdImageOps.threshold(input, binary, GThresholdImageOps.computeOtsu(input, 0, | GThresholdImageOps.threshold(input, binary, GThresholdImageOps.computeOtsu(input, 0, 255), true); | ||
gui.addImage(VisualizeBinaryData.renderBinary(binary, null),"Global: Otsu"); | gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Global: Otsu"); | ||
GThresholdImageOps.threshold(input, binary, GThresholdImageOps.computeEntropy(input, 0, | GThresholdImageOps.threshold(input, binary, GThresholdImageOps.computeEntropy(input, 0, 255), true); | ||
gui.addImage(VisualizeBinaryData.renderBinary(binary, null),"Global: Entropy"); | gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Global: Entropy"); | ||
// Local method | // Local method | ||
GThresholdImageOps. | GThresholdImageOps.localMean(input, binary, ConfigLength.fixed(57), 1.0, true, null, null,null); | ||
gui.addImage(VisualizeBinaryData.renderBinary(binary, null)," | gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Square"); | ||
GThresholdImageOps. | GThresholdImageOps.blockMinMax(input, binary, ConfigLength.fixed(21), 1.0, true, 15 ); | ||
gui.addImage(VisualizeBinaryData.renderBinary(binary, null)," | gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Block Min-Max"); | ||
GThresholdImageOps. | GThresholdImageOps.blockMean(input, binary, ConfigLength.fixed(21), 1.0, true ); | ||
gui.addImage(VisualizeBinaryData.renderBinary(binary, null)," | gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Block Mean"); | ||
GThresholdImageOps.blockOtsu(input, binary, false,ConfigLength.fixed(21),0.5, 1.0, true ); | |||
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Block Otsu"); | |||
GThresholdImageOps.localGaussian(input, binary, ConfigLength.fixed(85), 1.0, true, null, null); | |||
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Gaussian"); | |||
GThresholdImageOps.localSauvola(input, binary, ConfigLength.fixed(11), 0.30f, true); | |||
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Sauvola"); | |||
GThresholdImageOps.localNick(input, binary, ConfigLength.fixed(11), -0.2f, true); | |||
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: NICK"); | |||
// Sauvola is tuned for text image. Change radius to make it run better in others. | // Sauvola is tuned for text image. Change radius to make it run better in others. | ||
Line 75: | Line 86: | ||
public static void main(String[] args) { | public static void main(String[] args) { | ||
// example in which global thresholding works best | // example in which global thresholding works best | ||
threshold(" | threshold(UtilIO.pathExample("particles01.jpg")); | ||
// example in which adaptive/local thresholding works best | // example in which adaptive/local thresholding works best | ||
threshold(" | threshold(UtilIO.pathExample("segment/uneven_lighting_squares.jpg")); | ||
// hand written text with non-uniform stained background | // hand written text with non-uniform stained background | ||
threshold(" | threshold(UtilIO.pathExample("segment/stained_handwriting.jpg")); | ||
} | } | ||
} | } | ||
</syntaxhighlight> | </syntaxhighlight> |
Revision as of 19:39, 21 December 2020
Thresholding gray scale images is one of the most basic ways to segment an image. It is quick and effective in many situations. BoofCV provides several algorithms for computing both global and locally adaptive thresholds.
Example Code:
Concepts:
- Segmentation
- Thresholding
Relevant Videos:
Relevant Examples/Tutorials:
Example Code
/**
* Demonstration of different techniques for automatic thresholding an image to create a binary image. The binary
* image can then be used for shape analysis and other applications. Global methods apply the same threshold
* to the entire image. Local methods compute a local threshold around each pixel and can handle uneven
* lighting, but produce noisy results in regions with uniform lighting.
*
* @see boofcv.examples.imageprocessing.ExampleBinaryOps
*
* @author Peter Abeles
*/
public class ExampleThresholding {
public static void threshold( String imageName ) {
BufferedImage image = UtilImageIO.loadImage(imageName);
// convert into a usable format
GrayF32 input = ConvertBufferedImage.convertFromSingle(image, null, GrayF32.class);
GrayU8 binary = new GrayU8(input.width,input.height);
// Display multiple images in the same window
ListDisplayPanel gui = new ListDisplayPanel();
// Global Methods
GThresholdImageOps.threshold(input, binary, ImageStatistics.mean(input), true);
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Global: Mean");
GThresholdImageOps.threshold(input, binary, GThresholdImageOps.computeOtsu(input, 0, 255), true);
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Global: Otsu");
GThresholdImageOps.threshold(input, binary, GThresholdImageOps.computeEntropy(input, 0, 255), true);
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Global: Entropy");
// Local method
GThresholdImageOps.localMean(input, binary, ConfigLength.fixed(57), 1.0, true, null, null,null);
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Square");
GThresholdImageOps.blockMinMax(input, binary, ConfigLength.fixed(21), 1.0, true, 15 );
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Block Min-Max");
GThresholdImageOps.blockMean(input, binary, ConfigLength.fixed(21), 1.0, true );
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Block Mean");
GThresholdImageOps.blockOtsu(input, binary, false,ConfigLength.fixed(21),0.5, 1.0, true );
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Block Otsu");
GThresholdImageOps.localGaussian(input, binary, ConfigLength.fixed(85), 1.0, true, null, null);
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Gaussian");
GThresholdImageOps.localSauvola(input, binary, ConfigLength.fixed(11), 0.30f, true);
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: Sauvola");
GThresholdImageOps.localNick(input, binary, ConfigLength.fixed(11), -0.2f, true);
gui.addImage(VisualizeBinaryData.renderBinary(binary, false, null),"Local: NICK");
// Sauvola is tuned for text image. Change radius to make it run better in others.
// Show the image image for reference
gui.addImage(ConvertBufferedImage.convertTo(input,null),"Input Image");
String fileName = imageName.substring(imageName.lastIndexOf('/')+1);
ShowImages.showWindow(gui,fileName);
}
public static void main(String[] args) {
// example in which global thresholding works best
threshold(UtilIO.pathExample("particles01.jpg"));
// example in which adaptive/local thresholding works best
threshold(UtilIO.pathExample("segment/uneven_lighting_squares.jpg"));
// hand written text with non-uniform stained background
threshold(UtilIO.pathExample("segment/stained_handwriting.jpg"));
}
}