Luc Vincent’s fast watershed algorithm has been successfully applied to determine the bubble size distribution in an image of froth when the bubbles are all of similar size [1]. This technique fails to work successfully when the image contains both tiny and large bubbles. A new technique is proposed which combines the use of a texture measure, the output of an initial watershed and a further watershed stage to successfully segment both tiny and large bubbles.
Reference:
Forbes, G., & De Jager, G. (2004, November). Texture measures for improved watershed segmentation of froth images. In Fifteenth Annual Symposium of the Pattern Recognition Association of South Africa (pp. 1-6). Grabouw.
2004. Texture measures for improved watershed segmentation of froth images. http://hdl.handle.net/11427/24216
. 2004. Texture measures for improved watershed segmentation of froth images. http://hdl.handle.net/11427/24216
. 2004. Texture measures for improved watershed segmentation of froth images. http://hdl.handle.net/11427/24216