An Image-based Approach of Apex Type Descriptor State Establishment using Elliptic Fourier Analysis

An objective method to establish apex and base type descriptor states is proposed using elliptic Fourier descriptors derived from appropriately segmented images. Using pili (Canarium ovatum Engl.) kernel-in-shell as a model, 51 accessions represented by 10 images per accession were acquired calibrated VideometerLab3 setup. appropriate segmentation scheme was applied developing an algorithm that would segment blobs cover only the apical region (upper 25%) of closed contours OpenCV implemented in Python 3.7. From blobs, (EFDs) derived. Subsequently, EFDs analyzed principal component analysis cluster analysis. Two effective components able explain 94.18% variation which visualized show differences involving length width ratio, angle left-to-right leaning orientation Although single shape observed, mean three clusters represent states-narrowly acute, acute widely acute. This indicated can characterize variations regions, particularly angle, given proper protocol.