Intelligent and Accurate Tobacco Curing via Image Recognition and Data Analysis

Existing tobacco curing process assumes a uniform distribution of temperature and humidity in a barn without considering surface, texture, and biochemical properties of leaves, leading to low quality or even inferior end products. This paper proposes a novel curing process by combining image recognition and data analysis techniques that aims to intelligently improve curing quality of tobacco leaves. Specifically, an image recognition technique is first proposed to classify tobacco leaves and determine their placement in a curing barn. Then, data analysis of the biochemical spectrum of the tobacco leaves are conducted to correlate the temperature and humidity with biochemical data features. Extensive experimental results show that proposed curing process achieves 98.68% accuracy in image recognition for tobacco position control and provides an accurate mapping between tobacco state and biochemical spectrum signals.