Fuzzy Features for Facial Shape Classification on Panoramic Dental Image

Nur Nafi’iyah,Chastine Fatichah

International Conference on Industrial Revolution for Polytechnic Education
Vol. 1 No. 1 (2019): International Conference on Industrial Revolution for Polytechnic Education

Research on human face shape identificationcan assist forensic teams in reconstructing an unidentifiedvictim’s facial features. Human face shape identificationusing panoramic dental imaging is suitable for use byforensic teams in identifying a large number of victims dueto the teeth’s ability to withstand heat of up to 1000°C. Thisstudy proposes an application for face shapes classificationon panoramic dental image using fuzzy features and decisiontree method. It will be used to assist forensic scientists inreconstructing unidentified people identifying numerousvictims from their facial features. There are threeclassifications of human face shapes, namely oval, tapered,and square. The steps in this study are digitizing panoramicdental images into files; segmenting the upper jaw’s incisorteeth; then extracting the features by area, parameter, width,length, width-to-length ratio, area-to-parameter ratio,center_x and center_y. Fuzzy theory is used to convertnumeric features into category features, while decision treemethod will be used for training features. The experimentalresults show that the proposed method obtain accuracy 67%of 42 panoramic dental image.