Classification of human parasitic worm using microscopic image processing technique
Human parasitic infection causes diseases to people whether this infection will be inside the body called endoparasites, or outside of the body called ectoparasites. Human intestinal parasite worms infected by air, food, and water are the causes of major diseases and health problems. So in this stud...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/7597/1/Classification%20of%20human%20parasitic%20worm%20using%20microscopic%20imaging%20processing%20technique.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Human parasitic infection causes diseases to people whether this infection will be inside the body called endoparasites, or outside of the body called ectoparasites. Human intestinal parasite worms infected by air, food, and water are the causes of major diseases and health problems. So in this study, a technique to identify two types of parasites in human fecal, that is, the eggs of the worms is proposed. In this strategy, digital image processing methods such as noise reduction, contrast enhancement, and other morphological process are applied to extract the eggs images based on their features. The technique suggested in this study enables us to classify two different parasite eggs from their microscopic images which are roundworms (Ascaris lumbricoides ova, ALO) and whipworms (Trichuris trichiura ova, TTO). This proposed recognition method includes three stages. The first stage is a pre-processing sub-system, which is used to obtain unique features after performing noise reduction, contrast enhancement, edge enhancement, and detection. The next stage is an extraction mechanism which is based on five features of the three characteristics (shape, shell smoothness, and size. The final stage, the Filtration with Determinations Thresholds System (F-DTS) classifier is used to recognize the process using the ranges of feature values as a database to identify and classify the two types of parasites. The overall success rates are 93% and 94% in Ascaris lumbricoides and Trichuris trichiura, respectively. |
|---|