FivekoGFX – Online Image Processing Library

The FivekoGFX (aka Fiveko Graphics) is a free open source online graphics project. This is a JavaScript based image processing library, which uses Canvas2D and OpenGL technologies. This library is used in all demo applications. You are welcome to visit FivekoGFX’s source code repro on GitHub, since it is publicity available.

Graphic Filters

Edge Detection

  • Edge detection and gradient operators
    Different edge detection operators are available like Sobel filter, Prewitt, Schaar and so on
  • Gradient Non-Maximum suppression
    FivekoGFX implements a nice algorithm for edge thinning by a fast GPU (Graphic Processor Unit) non-maximum suppression GLSL

Shape detection

  • Hough Transform – Basic shape detection algorithms for primitives like lines, circles and other

Image Segmentation and Clustering

  • Watershed Image Segmentation
    Our online library implements Watershed segmentation based on Meyer’s flooding algorithm
  • Human skin segmentation
    FivekoGFX comes with a build-in human skin detection capability. Certainly this feature is useful for many computer vision tasks as well as for cases like nudity detection.

This is still in progress but we are currently working on some clustering algorithms such as k-means clustering. Meanwhile feel free to visit our online image processing tutorials for many computer vision articles and examples.