An image processing algorithm for an automated smartphone-based semen analyzer

This paper deals with the implementation of an image processing algorithm for an automated semen analyzer. The analysis of semen is the most important diagnostic tool in the initial investigation of male fertility. Semen analysis is best performed in a specialized laboratory with extensive experience in using the approved methods of the World Health Organization. Semen analysis in a specialized laboratory is labor-intensive, expensive, and time-consuming, and the accuracy depends on staff experience only. So, the use of image processing technology becomes very necessary in order to overcome these disadvantages. In this study, to improve the procedures involved in motion detection and prediction algorithms, we study Kalman filter-based object motion prediction. Furthermore, to improve accuracy and quality in the rate of object detection, the visual background extractor (ViBe) is employed. The experimental results of the proposed technique are evaluated and validated for performance and quality analysis from video data based on visual experiments. The experimental result achieved low root mean square error (RMSE) and relative root mean square error (RMSE%) values, demonstrating the effectiveness of the proposed technique for detecting and tracking sperm. The combination of two image processing approaches is proven to be effective in analyzing sperm condition. Copyrights © 2020 The Institute of Electronics and Information Engineers