Machine Vision for Grading Southern Pine Seedlings

ABSTRACT A machine vision algorithm for grading pine seedlings in real time has been developed. Singulated seedlings were inspected on a moving belt. Orientation and lateral position were loosely constrained. Classification as acceptable or cull was based on minimum criteria for stem diameter, shoot height, and projected root area. Seedlings were graded in approximately 0.25 s, with an average classification error rate of 5.7%.