An efficient preprocessing algorithm for image-based plant phenotyping

Plants are such important keys of biological part of our environment, supply the human life and creatures. Understandinghow the plant’s functions react with our surroundings, helps us better to make plant growth and development of foodproducts. It means the plant phenotyping gives us bio information which needs some tools to reach the plant knowledge.Imaging tools is one of the phenotyping solutions which consists of imaging hardware such as the camera and imageanalysis software analyses the plant images changings such as plant growth rates. In this paper, we proposed apreprocessing algorithm to eliminate the noise and separate foreground from the background which results the plantimage to help the plant image segmentation. The preprocessing is one of important levels has effect on better imagesegmentation and finally better plant’s image labeling and analysis. Our proposed algorithm is focused on removingnoise such as converting the color space, applying the filters and local adaptive binarization step such as Niblack. Finally,we evaluate our algorithm with other algorithms by testing a variety of binarization methods.

Keywords:

Plant phenotyping , Noise filtering , Binarization , Accuracy evaluation , Connected components