This module attempts to enhance contrast of a given image by employing a method called HBLPCE.
This module attempts to enhance contrast of a given image by employing a method called HBLPCE [Histogram-Based Locality-Preserving Contrast Enhancement]. This method enhances contrast of an image through equalizing its histogram, while keeping an eye on histogram's general shape, to conserve overall brightness and prevent excessive enhancement of the image.
You can access the article that came up with this method here.
Through formulating their approach, a minimization problem is introduced and solved using cvxpy library in python.
Run the following to install:
pip install imhblpce
import numpy as np import cv2 from imhblpce import imhblpce def imresize(img, wr=500, hr=None): # This is just for imshow-ing images with titles [ h, w, d] = img.shape hr = (h*wr)//w if not hr else hr img_resized = cv2.resize(img, dsize=(wr, hr)) return img_resized def main(): image_name = 'assets/Countryside.jpg' image = cv2.imread(image_name) # converts rgb image to hsv hsv_image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) v_image = hsv_image[:, :, 2] v_image_hblpce = imhblpce(v_image) hsv_image_hblpce = hsv_image.copy() hsv_image_hblpce[:, :, 2] = v_image_hblpce image_hblpce = cv2.cvtColor(hsv_image_hblpce, cv2.COLOR_HSV2BGR) # This is just for imshow-ing images with titles cv2.imshow('Original Image', imresize(image)) cv2.imshow('HBLPCE-d Image', imresize(image_hblpce)) cv2.waitKey(0) if __name__ == '__main__': main()
imhblpce --input 'Countryside.jpg' --output 'Countryside-imhblpce.jpg'
This is a sample image The sample image enhanced by HBLPCE method
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size imhblpce-0.0.6-py3-none-any.whl (5.1 kB)||File type Wheel||Python version py3||Upload date||Hashes View|
|Filename, size imhblpce-0.0.6.tar.gz (3.7 MB)||File type Source||Python version None||Upload date||Hashes View|