A Warp Speed Chain-Code Algorithm Based on Binary Decision Trees

Abstract

Contours extraction, also known as chain-code extraction, is one of the most common algorithms of binary image processing. Despite being the raster way the most cache friendly and, consequently, fast way to scan an image, most commonly used chain-code algorithms perform contours tracing, and therefore tend to be fairly inefficient. In this paper, we took a rarely used algorithm that extracts contours in raster scan, and optimized its execution time through template functions, look-up tables and decision trees, in order to reduce code branches and the average number of load/store operations required. The result is a very fast solution that outspeeds the state-of-the-art contours extraction algorithm implemented in OpenCV, on a collection of real case datasets. Contribution-This paper significantly improves the performance of existing chain-code algorithms, by smartly introducing decision trees to reduce code branches and the average number of load/store operations required.

The DeepHealth Toolkit: A Key European Free and Open-Source Software for Deep Learning and Computer Vision Ready to Exploit Heterogeneous HPC and Cloud Architectures

“…Obviously, all the classic operations for image manipulation such as rotation, resizing, mirroring and colour space change are available. Extremely optimized processing functions, like noising, blurring, contour finding [26], image skeletonization [27] and connected components labelling [28] are implemented as well. ECVL image-processing operations can be applied on-the-fly during deep neural networks training to implement data augmentation.…”