Skip to main content

This module attempts to enhance contrast of a given image with a method called HBLPCE.

Project description

imhblpce

This module attempts to enhance contrast of a given image with 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 solver library in python.

Installation

Run the following to install:

pip install imhblpce

Usage

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()

Showcase

This is a sample image Countryside.jpg Image The sample image enhanced by HBLPCE method Countryside-imhblpce.jpg Image

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for imhblpce, version 0.0.1
Filename, size File type Python version Upload date Hashes
Filename, size imhblpce-0.0.1-py3-none-any.whl (4.2 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size imhblpce-0.0.1.tar.gz (2.1 MB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page