Image processing algorithm to estimate ice-plant leaf area from RGB images under different light conditions

Abstract

The productivity of horticultural crops in an artificial light condition are highly influenced by the structure of plant and the area coverage. Accurate measurement of leaf area is very important for predicting plant water demand and optimal growth. In this paper, we proposed an image processing algorithm to estimate the ice-plant leaf area from the RGB images under the artificial light condition. The images were taken using a digital camera and the RGB images were transformed to grayscale images. A binary masking was applied from a grayscale image by classifying each pixel, belonging to the region of interest from the background. Then the masked images were segmented and the leaf region was filled using region filling technique. Finally, the leaf area was calculated from the number of pixel and using known object area. The experiment was carried out in three different light conditions with same plant variety (Ice-plant, Mesembryanthemum crystallinum). The results showed that the correlation between the actual and measured leaf area was found over 0.97 (R2:0.973) by our proposed method. Different light condition also showed significant impact on plant growth. Our results inspired further research and development of algorithms for the specific applications.