Abstract
Abstract Pathologists, microbiologists and cytologists are very interested to automatically identify and quantify the sperms, cells or nucleus in the cellular level images. Complexities like voluminous data sets, variability in data sets, millions of colors, and different kinds of artifacts make the detection and quantification process very difficult. This paper is an attempt to design a sophisticated cellular diagnostic system based on color image processing, mathematical morphology and connected components based on run length encoding. This system runs on Windows ‘98/NT PC platform, in Visual C++, 6.0 environment using three different architectures: Single document interface, multiple document interface and dialog based applications. The system takes around 1.5 seconds per image of 512 x 484 square pixels using high speed threading architecture written on the on 400 MHz Pentiumll processor. The system has an accuracy of 95%. The software has been validated tested on NASA and machine vision real world images.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call