Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6539281 | Computers and Electronics in Agriculture | 2018 | 12 Pages |
Abstract
Recent researches have shown that spectroscopy is a valid non-destructive technique for fruit quality detection. Yet the high cost, large volume, and complicated operation of the traditional spectral system makes it hard to be adapted to real field applications. In this paper, a low-cost, cloud-based portable Near Infrared (NIR) system called 'SeeFruits' was designed for fruit quality detection. The system was developed based on two integrated modules, DLP® NIRscan Nano EVM and ESP12-F. Main structures of hardware and software as well as the operation and workflow of the system were described in detail. A total of 240 sweet cherries were chosen as our fruit samples in order to evaluate the performance of 'SeeFruits'. By targeting maturity level as a qualitative index and total soluble solids content as a quantitative index, we compared the results between 'SeeFruits' and a benchtop NIR-hyperspectral imaging system. The 'SeeFruits' system achieved F1-score of 0.89 on qualitative task and R2 of 0.83 on quantitative task. Overall, with the features of ultra-portability, cloud computing and Internet of things feasibility, 'SeeFruits' can provide a fast, flexible and friendly application for sweet cherry quality detection to nonprofessionals with satisfactory accuracy.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science Applications
Authors
Tao Wang, Jian Chen, Yangyang Fan, Zhengjun Qiu, Yong He,