SkinDiRect: Skin Disease Recognition using pattern recognition

Date of Publication


Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

Subject Categories

Computer Sciences


College of Computer Studies


Computer Science

Thesis Adviser

Rigan Ap-apid

Defense Panel Member

Solomon Lim See

Jose Ronello Bartolome


Research in the field of decision-support in medicine has paved the way to the advent of new approaches to medical diagnoses. This concept of storing prior knowledge regarding the features of each disease into a system and enabling it to automate the evaluation process has significantly minimized the amount of time required to diagnose certain disorders and noticeably improved the accuracy of the diagnoses. Developments such as CLARET (Kelm, et al. 2006) in the field of radiology and STARE (Goldbaum, et al. 2000) in the field of ophthalmology have proven the possibility of utilizing such systems in actual practice. Both systems use image representation of diseases as input to generate the corresponding diagnoses. This paper presents a research that extended such technology to the branch of dermatology due to its highly visual nature. In line with its objectives, the study introduced a decision-support system that performs pattern recognition on images to identify the corresponding diseases. The accuracy of the automated diagnoses of the system reached an outstanding 93.16%, thus proving the feasibility and extensibility of the entire research.

Abstract Format




Accession Number


Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

1 v. (various foliations) : illustrations (some colored) ; 28 cm.


Pattern recognition systems; Skin--Diseases

This document is currently not available here.