Multilevel thresholding for image segmentation through a fast statistical recursive algorithm

• Published in: Pattern recognition letters Vol. 29; no. 2; pp. 119 - 125
• Main Authors: Arora, S., Acharya, J., Verma, A., Panigrahi, Prasanta K.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 15.01.2008; Elsevier
• Subjects: Applied sciences; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Histogram; Image processing; Image segmentation; Information, signal and communications theory; Multilevel thresholding; Recursion; Signal and communications theory; Signal processing; Signal, noise; Sub-range; Telecommunications and information theory; Multilevel thresholding; Image segmentation; Histogram; Sub-range; Recursion; Image processing; Threshold detection; Recursive algorithm; Multilevel signal; Image quality; Extreme value; Recursive method; Fast algorithm; Multilevel system; Delta function
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2007.09.005

A novel algorithm is proposed for segmenting an image into multiple levels using its mean and variance. Starting from the extreme pixel values at both ends of the histogram plot, the algorithm is applied recursively on sub-ranges computed from the previous step, so as to find a threshold level and a new sub-range for the next step, until no significant improvement in image quality can be achieved. The method makes use of the fact that a number of distributions tend towards Dirac delta function, peaking at the mean, in the limiting condition of vanishing variance. The procedure naturally provides for variable size segmentation with bigger blocks near the extreme pixel values and finer divisions around the mean or other chosen value for better visualization. Experiments on a variety of images show that the new algorithm effectively segments the image in computationally very less time.