Abdominal palpation characterization using computer vision
Date of Publication
2016
Document Type
Bachelor's Thesis
Degree Name
Bachelor of Science in Computer Engineering
Subject Categories
Computer Engineering
College
Gokongwei College of Engineering
Department/Unit
Electronics and Communications Engineering
Thesis Adviser
Melvin K. Cabatuan
Defense Panel Chair
Alexander C. Abad
Defense Panel Member
Mark Lorenze Torregoza
Roy Francis R. Navea
Abstract/Summary
This study intends to develop a tracking algorithm that will segment the hand from the skin using real time multicolor space segmentation. The tracking system uses keypoints and descriptors as its feature extraction. The system will work on different skin colors, namely, fair, brown, and dark. The generalization of these levels used calibrated weights as its basis on how much force the user needs to exert to his hand while palpating. Its measurement is in terms of grams. The result of experimenting with how much force is the light palpation ranges from 0 to 1.25 kilograms. Medium level palpation ranges from 1.25 to 1.75 kilograms while deep level palpation starts from 1.75 kilograms and above.
The system will also differentiate the levels of palpation with the force exerted by the hand. The levels of palpation that were used in this study are light, medium, and deep. Support Vector Machine (SVM) was used in separating the levels of palpation from each other. SVM is an algorithm that sorts out the features that belong to a group and acts as an efficient classification method. In each of the datasets, the person who is palpating uses different combinations of palpation level throughout the video. This tested the system's effectiveness on how it can handle the levels of palpation while also using the system in different skin colors.
Abstract Format
html
Language
English
Format
Accession Number
TU17414
Shelf Location
Archives, The Learning Commons, 12F, Henry Sy Sr. Hall
Physical Description
xi, 128 leaves ; illustrations (some color) ; 28 cm. ; 1 computer disc ; 4 3/4 in.
Keywords
Palpation; Computer vision; Computer vision in medicine
Recommended Citation
Rosaldo, A. F. (2016). Abdominal palpation characterization using computer vision. Retrieved from https://animorepository.dlsu.edu.ph/etd_bachelors/2975