Histogram Equalization and Specification Guide | educator explainer video made with ngram

About the video

This educator explainer video was made with ngram to explain core concepts in digital image processing related to histogram-based contrast adjustment. The video uses a grainy black-and-white crowd photograph as a running example to illustrate brightness levels across an image, showing how pixel intensity varies from dark hair and clothing to lighter skin tones and backgrounds. It introduces the probability density function used in histogram equalization, presenting the formula p(r) = n / N, where n represents the number of pixels at a given intensity level and N represents the total number of pixels in the image. This formula is shown alongside the sample photo with a highlighted intensity band to demonstrate how a specific brightness range is measured. The video also displays a uniform red bar chart representing an equalized histogram, where intensity levels are spread evenly across the range, illustrating the goal of histogram equalization: transforming an image so its pixel intensities are more uniformly distributed, which typically improves contrast in images that are too dark, too bright, or low-contrast. Viewers can take away an understanding of how probability density functions underpin histogram equalization, how equalized histograms visually differ from unequalized ones, and how these statistical techniques apply to real photographic data in image processing workflows.