A New Method for Sperm Detection in Infertility Cure: Hypothesis Testing Based on Fuzzy Entropy Decision

In this paper, a new method is introduced for sperm detection inmicroscopic images for infertility treatment. In this method, firstly ahypothesis testing function is defined to separate sperms from plasma,non-sperm semen particles and noise. Then, some primary candidates areselected for sperms by watershed-based segmentation algorithm. Finally,candidates are either confirmed or rejected using fuzzy entropy decisionalgorithm. Performance of the proposed method is evaluated on realcaptured images containing sperms and other specimens of semen in twodifferent scenarios. In the first scenario, semen has low density of spermshowever the second scenario belongs to semen with high density ofsperms. The obtained results show the greater ability of the proposedmethod in sperm detection compared to present approaches in both ofscenarios. Furthermore, it is shown that 8% and 15% improvements insperm detection in the first and second scenarios can be achieved by theproposed algorithm. As the final results, the proposed algorithm not onlydoesn't lead to extract more false objects but also decrease the rate offalse detections are decreased compared to existing algorithms.

Keywords:

Sperm detection , Microscopic image , Hypothesis testing , Fuzzy entropy decision