bioRxiv2020
Plant phenotyping using machine learning and computer vision approaches is a challenging task. Deep learning-based systems for plant phenotyping is more efficient for measuring different plant traits for diverse genetic discoveries compared to the traditional image-based phenotyping approaches. Plant biologists have recently demanded more reliable and accurate image-based phenotyping systems for assessing various features of plants and crops. The core of these image-based phenotyping systems is structural classification and features segmentation. Deep learning-based systems, however, have shown outstanding results in extracting very complicated features and structures of above-ground plants. Nevertheless, the below-ground part of the plant is usually more complicated to analyze due to its complex arrangement and distorted appearance. We proposed a deep convolutional neural networks (CNN) model named "RootNet" that detects and pixel-wise segments plant roots features. The feature of the proposed method is detection and segmentation of very thin (1-3 pixels wide roots). The proposed approach segment high definition images without significantly sacrificing pixel density, it leads to more accurate root type detection and segmentation results. It is hard to train CNNs with high definition images due to GPU memory limitations. The proposed patch-based CNN training setup makes use of the entire image (with maximum pixel desisity) to recognize and segment give root system efficiently. We have used wheat (Triticum aestivum L.) seedlings dataset, which consists of wheat roots grown in visible pouches. The proposed system segments are given root systems and save it to the Root System Markup Language (RSML) for future analysis. RootNet trained on the dataset mentioned above along with popular semantic segmentation architectures, and it achieved a benchmark accuracy.