Digital Image Segmentation based Worm Count and Identified Diseases of worms in Human

This work has presented a framework for identifying disease of worms in human and has proposed a packed set of Region Props for quantifying worm's characteristics for worm detection. The worm's classification accuracy was improved when concatenating a set of KNN approach and connected component algorithm. Routine recognition of disease of worms in Human using WCE is a tough task. It aims to reduce the amount of images a clinician needs to review.This work may lead to more clinically helpful for identifying disease of worms in human intestine within a short period of time. A bounding box is an uncomplicated and trendy communication hypothesis considered by many existing interactive image segmentation frameworks. To view the whole gastrointestinal tract, wireless capsule endoscopy (WCE) has been used. The k-nearest neighbouring technique is used to classify the worms. The performance analysis shows the accuracy in the detection of worms, worm count and their related diseases with reduced time.