Ripe or Rotten? Low-Cost Produce Quality Estimation Using Reflective Green Light Sensing

Abstract

We develop an innovative low-cost approach for characterizing fresh produce by repurposing inexpensive commercial-off-the-shelf green light sensors for quality estimation. Our approach has been designed to support all stages of the supply chain while being inexpensive and easy to deploy. We validate our approach through extensive empirical benchmarks, showing that it can correctly distinguish organic produce from nonorganic items, establish unique fingerprints for different produce, and estimate the quality or ripeness of produce. Specifically, we demonstrate that changes in the reflected green light values correlate with the so-called transpiration coefficients of the produce. We also discuss the practicability of our approach and present application use cases that can benefit from our solution.

Agustin Zuniga

Pervasive Data Science group

Dr. Agustin Zuniga works in the areas of pervasive data science and artificial intelligence of things, especially in low-cost sensing and intelligent sensing pipeline solutions.