Equalize Histogram

Overview

Histogram equalization is a method in image processing of contrast adjustment using the image's histogram. For more information, see [1].

Input	Output

Implementation

This algorithm is trying to find a new mapping palette based on the histogram. Consider a grayscale image X, whose total number of gray levels in the image is L, Denote the histogram of the image as \(H_x\). The probability of an occurrence of a pixel of level \(i\) in the image is:

\[ p[i] = H_x[i] / N \]

where:

• \(N\) is total number of pixels in the image.

The cumulative distribution function corresponding to \(p[i]\) is:

\[ cdf_x[i] = \sum_{j=0}^{i}p[j] \]

Using the cumulative distribution function to transform the original pixel value to a new pixel value, the corresponding pixel value is:

\[ y[i] = \sum_{j=0}^{i}p[j] * L \]

Example of image histogram after equalization:

Input	Equalized Output

Usage

Language: C/C++ Python

1. Import VPI module

   import vpi

2. Use the CUDA backend to equalize the input image histogram, creating output VPI image with the result.

   with vpi.Backend.CUDA:
       output = input.eqhist()

1. Initialization phase
   1. Include the header that defines the image equalize histogram function.

      #include <vpi/algo/EqualizeHist.h>

   2. Define the input image.

          VPIImage input = /*...*/;

   3. Create the output image.

          int w, h;
          vpiImageGetSize(input, &w, &h);
       
          VPIImage output;
          vpiImageCreate(w, h, VPI_IMAGE_FORMAT_U8, 0, &output);

   4. Since this algorithm needs temporary memory buffers, create the payload for it on the CUDA backend.

          VPIPayload payload;
          vpiCreateEqualizeHist(VPI_BACKEND_CUDA, VPI_IMAGE_FORMAT_U8, &payload);

   5. Create the stream where the algorithm will be submitted for execution.

          VPIStream stream;
          vpiStreamCreate(0, &stream);

2. Processing phase
   1. Submit the algorithm to the stream using the CUDA backend, along with all parameters.

          vpiSubmitEqualizeHist(stream, VPI_BACKEND_CUDA, payload, input, output);

   2. Optionally, wait until the processing is done.

          vpiStreamSync(stream);

3. Cleanup phase
   1. Free resources held by the stream and the input and output images.

          vpiStreamDestroy(stream);
          vpiImageDestroy(input);
          vpiImageDestroy(output);
          vpiPayloadDestroy(payload);

For more information, see Equalize Image histogram in the "API Reference" section of VPI - Vision Programming Interface.

Limitations and Constraints

CPU and CUDA backends

• The following image formats are accepted:
  • VPI_IMAGE_FORMAT_U8
  • VPI_IMAGE_FORMAT_U16
  • VPI_IMAGE_FORMAT_NV12
  • VPI_IMAGE_FORMAT_NV12_ER
• For VPI_IMAGE_FORMAT_NV12 and VPI_IMAGE_FORMAT_NV12_ER formats, only the Y channel is equalized. The remaining channels are left unchanged.

Other backends

• Not supported.

Performance

For information on how to use the performance table below, see Algorithm Performance Tables.
Before comparing measurements, consult Comparing Algorithm Elapsed Times.
For further information on how performance was benchmarked, see Performance Benchmark.

clear filters Device: Jetson AGX Xavier Jetson TX2 Jetson Nano  -  Streams: 1 4 8

References

1. https://en.wikipedia.org/wiki/Histogram_equalization