PubAg

Main content area

NIR/MIR dual-sensor vision system for apple defect and stem-end/calyx on-line recognition

Author:
Tao, Yang, Cheng, Xuemei, Chen, Yud-Ren, Luo, Yaguang
Source:
Acta horticulturae 2003 no.599 pp. 343-349
ISSN:
0567-7572
Subject:
apples, computer vision, image analysis, sorting, vision
Abstract:
One of the difficult problems in automated machine vision apple sorting is the distinction between true defects and the stem-end/calyx. To solve this problem, a dual imaging approach using near infrared (NIR) and mid-infrared (MIR) was developed for combined sensing. Based on this method, the MIR is sensitive to the stem-end/calyx, whereas the NIR is sensitive to both stem-end/calyx and defects. Through image processing of combined images, the distinction is achieved. Experiments show the robustness of the method for on-line defect sorting of apples.
Agid:
304953