Comparison of Histogram Feature Based Thresholding with 3S Multi-Thresholding and Fuzzy C-Means

Thresholding is one of the most important parts of segmentation whenever we want to detect a specific part of image. There are several thresholding methods that previous researchers used them frequently as bi-level techniques such as DBT or multilevel such as 3S. New histogram feature thresholding method is implemented to detect lesion area in digital mammograms and compared with 3S (Shrinking-Search-Space) multi-thresholding and FCM method in terms of segmentation quality and segmentation time as a benchmark in thresholding.

These algorithms have been tested on 188 digital mammograms. Digital mammogram image used after preprocessing which was including crop the unnecessary area, resize the image into 1024 by 1024 pixel and then normalize pixel values by using simple contrast stretching method.

The results show that suggested method results are not similar with 3S and FCM methods, and it is faster than other methods. This is another superiority of suggested method with respect to others. Results of previous studies showed that FCM is not a reliable clustering algorithm and it needs several run to give us a reliable result. Results of this study also showed that this approach is correct.

The suggested method may use as a reliable thresholding method in order to detection of lesion area