Abstract:
Sorting plastic covering is very important before plastic waste was brought into
landfill. Manual sorting process has disadvantages such as tediousness,
infefficiency, in cost to time, and subjectivity. Multispectral imaging has
advantages for plastic waste classification, because it can cover visible range of
electromagnetic spectrum, and infrared range (700 – 2500 nm). Reflectance
intensity was obtained for each pixel in Region of Interest to classify plastics
category. Plastics waste has better response in Near-Infrared range. Results show
that average reflectance intensity are different for each plastic category which is
0.170, 0.671, and 0.109 for PET, HDPE, and PP plastic, respectively