Adaptive Thresholding using the Integral Image

TLDR

Image thresholding classifies pixels as dark or light and is widely used in computer vision and graphics; adaptive thresholding accounts for spatial illumination variations. We present a technique for real‑time adaptive thresholding that uses the integral image of the input. Our technique extends a previous method by employing the integral image to enable fast, real‑time adaptive thresholding. The method is more robust to illumination changes, simple to implement, supports real‑time processing of live video streams for interactive applications such as augmented reality, and its source code is available online.

Abstract

Image thresholding is a common task in many computer vision and graphics applications. The goal of thresholding an image is to classify pixels as either "dark" or "light." Adaptive thresholding is a form of thresholding that takes into account spatial variations in illumination. We present a technique for real-time adaptive thresholding using the integral image of the input. Our technique is an extension of a previous method. However, our solution is more robust to illumination changes in the image. Additionally, our method is simple and easy to implement. Our technique is suitable for processing live video streams at a real-time frame-rate, making it a valuable tool for interactive applications such as augmented reality. Source code is available online.