Colour quantization with Ant-tree

• The Ant-tree clustering algorithm is adapted for colour quantization.
• The algorithm performs the two basic operations of colour quantization.
• A threshold determines if a pixel is associated to the most similar cluster.
• Palette size can be limited, but a smaller size can be obtained for an image.
• Computational results improve some well-known quantization methods.

Ant-tree is a clustering algorithm inspired by biological ants. This paper defines a variant of such algorithm to perform colour quantization. Some of the features of the basic Ant-tree have been adapted to obtain a quicker algorithm and to perform the main steps of colour quantization on a big input set. The centroid of every cluster defines a colour of the palette and once the complete colour palette is established, the algorithm represents each pixel of the original image by the colour associated to its cluster.Computational results show that the error obtained for the quantized images is smaller than the error generated by some other well-known quantization methods.

Figure optionsDownload as PowerPoint slide