- OpenCV - GUI
- OpenCV - Writing an Image
- OpenCV - Reading Images
- OpenCV - Storing Images
- OpenCV - Environment
- OpenCV - Overview
- OpenCV - Home
Types of Images
Image Conversion
Drawing Functions
- OpenCV - Adding Text
- OpenCV - Drawing Arrowed Lines
- OpenCV - Drawing Convex Polylines
- OpenCV - Drawing Polylines
- OpenCV - Drawing an Ellipse
- OpenCV - Drawing a Rectangle
- OpenCV - Drawing a Line
- OpenCV - Drawing a Circle
Blur
Filtering
- OpenCV - Image Pyramids
- OpenCV - Morphological Operations
- OpenCV - Erosion
- OpenCV - Dilation
- OpenCV - Filter2D
- OpenCV - SQRBox Filter
- OpenCV - Box Filter
- OpenCV - Bilateral Filter
Thresholding
Sobel Derivatives
Transformation Operations
Camera and Face Detection
Geometric Transformations
Miscellaneous Chapters
OpenCV Useful Resources
Selected Reading
- Who is Who
- Computer Glossary
- HR Interview Questions
- Effective Resume Writing
- Questions and Answers
- UPSC IAS Exams Notes
OpenCV - Image Pyramids
Pyramid is an operation on an image where,
An input image is initially smoothed using a particular smoothing filter (ex: Gaussian, Laplacian) and then the smoothed image is subsampled.
This process is repeated multiple times.
During the pyramid operation, the smoothness of the image is increased and the resolution (size) is decreased.
Pyramid Up
In Pyramid Up, the image is initially up-sampled and then blurred. You can perform Pyramid Up operation on an image using the pyrUP() method of the imgproc class. Following is the syntax of this method −
pyrUp(src, dst, dstsize, borderType)
This method accepts the following parameters −
src − An object of the class Mat representing the source (input) image.
mat − An object of the class Mat representing the destination (output) image.
size − An object of the class Size representing the size to which the image is to be increased or decreased.
borderType − A variable of integer type representing the type of border to be used.
Example
The following program demonstrates how to perform the Pyramid Up operation on an image.
import org.opencv.core.Core; import org.opencv.core.Mat; import org.opencv.core.Size; import org.opencv.imgcodecs.Imgcodecs; import org.opencv.imgproc.Imgproc; pubpc class PyramidUp { pubpc static void main( String[] args ) { // Loading the OpenCV core pbrary System.loadLibrary( Core.NATIVE_LIBRARY_NAME ); // Reading the Image from the file and storing it in to a Matrix object String file ="E:/OpenCV/chap13/pyramid_input.jpg"; Mat src = Imgcodecs.imread(file); // Creating an empty matrix to store the result Mat dst = new Mat(); // Applying pyrUp on the Image Imgproc.pyrUp(src, dst, new Size(src.cols()*2, src.rows()*2), Core.BORDER_DEFAULT); // Writing the image Imgcodecs.imwrite("E:/OpenCV/chap13/pyrUp_output.jpg", dst); System.out.println("Image Processed"); } }
Assume that following is the input image pyramid_input.jpg specified in the above program.
![Pyramid Input](/opencv/images/pyramid_input.jpg)
Output
On executing the program, you will get the following output −
Image Processed
If you open the specified path, you can observe the output image as follows −
![Pyramid Up Output](/opencv/images/pyramid_up_output.jpg)
Pyramid Down
In Pyramid Down, the image is initially blurred and then down-sampled. You can perform Pyramid Down operation on an image using the pyrDown() method of the imgproc class. Following is the syntax of this method −
pyrDown(src, dst, dstsize, borderType)
This method accepts the following parameters −
src − An object of the class Mat representing the source (input) image.
mat − An object of the class Mat representing the destination (output) image.
size − An object of the class Size representing the size to which the image is to be increased or decreased.
borderType − A variable of integer type representing the type of border to be used.
Example
The following program demonstrates how to perform the Pyramid Down operation on an image.
import org.opencv.core.Core; import org.opencv.core.Mat; import org.opencv.core.Size; import org.opencv.imgcodecs.Imgcodecs; import org.opencv.imgproc.Imgproc; pubpc class PyramidDown { pubpc static void main( String[] args ) { // Loading the OpenCV core pbrary System.loadLibrary( Core.NATIVE_LIBRARY_NAME ); // Reading the Image from the file and storing it in to a Matrix object String file ="E:/OpenCV/chap13/pyramid_input.jpg"; Mat src = Imgcodecs.imread(file); // Creating an empty matrix to store the result Mat dst = new Mat(); // Applying pyrDown on the Image Imgproc.pyrDown(src, dst, new Size(src.cols()/2, src.rows()/2), Core.BORDER_DEFAULT); // Writing the image Imgcodecs.imwrite("E:/OpenCV/chap13/pyrDown_output.jpg", dst); System.out.println("Image Processed"); } }
Assume that following is the input image pyramid_input.jpg specified in the above program.
![Pyramid Input](/opencv/images/pyramid_input.jpg)
Output
On executing the program, you will get the following output −
Image Processed
If you open the specified path, you can observe the output image as follows −
![Pyramid Down Output](/opencv/images/pyramid_down_output.jpg)
Mean Shift Filtering
In Mean Shifting pyramid operation, an initial step of mean shift segmentation of an image is carried out.
You can perform pyramid Mean Shift Filtering operation on an image using the pyrDown() method of the imgproc class. Following is the syntax of this method.
pyrMeanShiftFiltering(src, dst, sp, sr)
This method accepts the following parameters −
src − An object of the class Mat representing the source (input) image.
mat − An object of the class Mat representing the destination (output) image.
sp − A variable of the type double representing the spatial window radius.
sr − A variable of the type double representing the color window radius.
Example
The following program demonstrates how to perform a Mean Shift Filtering operation on a given image.
import org.opencv.core.Core; import org.opencv.core.Mat; import org.opencv.imgcodecs.Imgcodecs; import org.opencv.imgproc.Imgproc; pubpc class PyramidMeanShift { pubpc static void main( String[] args ) { // Loading the OpenCV core pbrary System.loadLibrary( Core.NATIVE_LIBRARY_NAME ); // Reading the Image from the file and storing it in to a Matrix object String file ="E:/OpenCV/chap13/pyramid_input.jpg"; Mat src = Imgcodecs.imread(file); // Creating an empty matrix to store the result Mat dst = new Mat(); // Applying meanShifting on the Image Imgproc.pyrMeanShiftFiltering(src, dst, 200, 300); // Writing the image Imgcodecs.imwrite("E:/OpenCV/chap13/meanShift_output.jpg", dst); System.out.println("Image Processed"); } }
Assume that following is the input image pyramid_input.jpg specified in the above program.
![Pyramid Input](/opencv/images/pyramid_input.jpg)
Output
On executing the program, you will get the following output −
Image Processed
If you open the specified path, you can observe the output image as follows −
![Mean Shift Filtering Output](/opencv/images/mean_shift_filtering_output.jpg)