Leveraging multiple datasets for deep leaf counting
This work addresses the problem of automated plant phenotyping for researchers by offering a more efficient annotation method, though it is incremental as it builds on existing deep learning techniques for leaf counting.
The authors tackled leaf counting in plants by proposing a deep learning regression method that only requires total leaf count annotations, avoiding per-leaf segmentation. Their approach, evaluated on the CVPPP 2017 dataset, outperformed the previous challenge winner by at least 50% on test datasets and reduced mean absolute difference in count by 20% compared to segmentation-based methods.
The number of leaves a plant has is one of the key traits (phenotypes) describing its development and growth. Here, we propose an automated, deep learning based approach for counting leaves in model rosette plants. While state-of-the-art results on leaf counting with deep learning methods have recently been reported, they obtain the count as a result of leaf segmentation and thus require per-leaf (instance) segmentation to train the models (a rather strong annotation). Instead, our method treats leaf counting as a direct regression problem and thus only requires as annotation the total leaf count per plant. We argue that combining different datasets when training a deep neural network is beneficial and improves the results of the proposed approach. We evaluate our method on the CVPPP 2017 Leaf Counting Challenge dataset, which contains images of Arabidopsis and tobacco plants. Experimental results show that the proposed method significantly outperforms the winner of the previous CVPPP challenge, improving the results by a minimum of ~50% on each of the test datasets, and can achieve this performance without knowing the experimental origin of the data (i.e. in the wild setting of the challenge). We also compare the counting accuracy of our model with that of per leaf segmentation algorithms, achieving a 20% decrease in mean absolute difference in count (|DiC|).