A Segmentation-Guided Deep Learning Framework for Leaf Counting

Enhancing plant morphological trait identification in herbarium collections through deep learning-based segmentation

Premise

Deep learning has become increasingly important in the analysis of digitized herbarium collections, which comprise millions of scans that provide valuable resources for studying plant evolution and biodiversity. However, leveraging deep learning algorithms to analyze these scans presents significant challenges, partly due to the heterogeneous nature of the non-plant material that forms the background of the scans. We hypothesize that removing such backgrounds can improve the performance of these algorithms.

Methods

We propose a novel method based on deep learning to segment and generate plant masks from herbarium scans and subsequently remove the non-plant backgrounds. The semi-automatic preprocessing stages involve the identification and removal of non-plant elements, substantially reducing the manual effort required to prepare the training dataset.

Results

The results highlight the importance of effective image segmentation, which achieved an F1 score of up to 96.6%. Moreover, when used in classification models for plant morphological trait identification, the images resulting from segmentation improved classification accuracy by up to 3% and F1 score by up to 7% compared to non-segmented images.

Discussion

Our approach isolates plant elements in herbarium scans by removing background elements to improve classification tasks. We demonstrate that image segmentation significantly enhances the performance of plant morphological trait identification models.

Lightweight Corn Leaf Detection and Counting Using Improved YOLOv8

The number of maize leaves is an important indicator for assessing plant growth and regulating population structure. However, the traditional leaf counting method mainly relies on manual work, which is both time-consuming and straining, while the existing image processing methods have low accuracy and poor adaptability, making it difficult to meet the standards for practical application. To accurately detect the growth status of maize, an improved lightweight YOLOv8 maize leaf detection and counting method was proposed in this study. Firstly, the backbone of the YOLOv8 network is replaced using the StarNet network and the convolution and attention fusion module (CAFM) is introduced, which combines the local convolution and global attention mechanisms to enhance the ability of feature representation and fusion of information from different channels. Secondly, in the neck network part, the StarBlock module is used to improve the C2f module to capture more complex features while preserving the original feature information through jump connections to improve training stability and performance. Finally, a lightweight shared convolutional detection head (LSCD) is used to reduce repetitive computations and improve computational efficiency. The experimental results show that the precision, recall, and mAP50 of the improved model are 97.9%, 95.5%, and 97.5%, and the numbers of model parameters and model size are 1.8 M and 3.8 MB, which are reduced by 40.86% and 39.68% compared to YOLOv8. This study shows that the model improves the accuracy of maize leaf detection, assists breeders in making scientific decisions, provides a reference for the deployment and application of maize leaf number mobile end detection devices, and provides technical support for the high-quality assessment of maize growth.

Transforming Poultry Farming: A Pyramid Vision Transformer Approach for Accurate Chicken Counting in Smart Farm Environments

Smart farm environments, equipped with cutting-edge technology, require proficient techniques for managing poultry. This research investigates automated chicken counting, an essential part of optimizing livestock conditions. By integrating artificial intelligence and computer vision, it introduces a transformer-based chicken-counting model to overcome challenges to precise counting, such as lighting changes, occlusions, cluttered backgrounds, continual chicken growth, and camera distortions. The model includes a pyramid vision transformer backbone and a multi-scale regression head to predict precise density maps of the crowded chicken enclosure. The customized loss function incorporates curriculum loss, allowing the model to learn progressively, and adapts to diverse challenges posed by varying densities, scales, and appearances. The proposed annotated dataset includes data on various lighting conditions, chicken sizes, densities, and placements. Augmentation strategies enhanced the dataset with brightness, contrast, shadow, blur, occlusion, cropping, and scaling variations. Evaluating the model on the proposed dataset indicated its robustness, with a validation mean absolute error of 27.8, a root mean squared error of 40.9, and a test average accuracy of 96.9%. A comparison with the few-shot object counting model SAFECount demonstrated the model's superior accuracy and resilience. The transformer-based approach was 7.7% more accurate than SAFECount. It demonstrated robustness in response to different challenges that may affect counting and offered a comprehensive and effective solution for automated chicken counting in smart farm environments.

Multi-classification of disease induced in plant leaf using chronological Flamingo search optimization with transfer learning

Agriculture is imperative research in visual detection through computers. Here, the disease in plants can distress the quality and cultivation of farming. Earlier detection of disease lessens economic losses and provides better crop yield. Detection of disease from crops manually is an expensive and time-consuming task. A new scheme is devised for accomplishing multi-classification of disease using plant leaf images considering the chronological Flamingo search algorithm (CFSA) with transfer learning (TL). The leaf image undergoes pre-processing using Adaptive Anisotropic diffusion to discard noise. Here, the segmentation of plant leaf is done with U-Net++, and trained by the Moving Gorilla Remora algorithm (MGRA). The image augmentation is further applied considering two techniques namely position augmentation and color augmentation to reduce data dimensionality. Thereafter the feature mining is done to produce crucial features. Next, the classification in terms of the first level is considered for classifying plant type and classification in terms of the second level is done to categorize disease using convolutional neural network (CNN)-based TL with LeNet and it undergoes training using CFSA. The CFSA-TL-based CNN with LeNet provided better accuracy of 95.7%, sensitivity of 96.5% and specificity of 94.7%. Thus, this model is better for earlier plant leaf disease detection.

Deep learning for automated segmentation and counting of hypocotyl and cotyledon regions in mature Pinus radiata D. Don. somatic embryo images

In commercial forestry and large-scale plant propagation, the utilization of artificial intelligence techniques for automated somatic embryo analysis has emerged as a highly valuable tool. Notably, image segmentation plays a key role in the automated assessment of mature somatic embryos. However, to date, the application of Convolutional Neural Networks (CNNs) for segmentation of mature somatic embryos remains unexplored. In this study, we present a novel application of CNNs for delineating mature somatic conifer embryos from background and residual proliferating embryogenic tissue and differentiating various morphological regions within the embryos. A semantic segmentation CNN was trained to assign pixels to cotyledon, hypocotyl, and background regions, while an instance segmentation network was trained to detect individual cotyledons for automated counting. The main dataset comprised 275 high-resolution microscopic images of mature Pinus radiata somatic embryos, with 42 images reserved for testing and validation sets. The evaluation of different segmentation methods revealed that semantic segmentation achieved the highest performance averaged across classes, achieving F1 scores of 0.929 and 0.932, with IoU scores of 0.867 and 0.872 for the cotyledon and hypocotyl regions respectively. The instance segmentation approach demonstrated proficiency in accurate detection and counting of the number of cotyledons, as indicated by a mean squared error (MSE) of 0.79 and mean absolute error (MAE) of 0.60. The findings highlight the efficacy of neural network-based methods in accurately segmenting somatic embryos and delineating individual morphological parts, providing additional information compared to previous segmentation techniques. This opens avenues for further analysis, including quantification of morphological characteristics in each region, enabling the identification of features of desirable embryos in large-scale production systems. These advancements contribute to the improvement of automated somatic embryogenesis systems, facilitating efficient and reliable plant propagation for commercial forestry applications.

Completing the picture of field-grown cereal crops: a new method for detailed leaf surface models in wheat

BACKGROUND

The leaf angle distribution (LAD) is an important structural parameter of agricultural crops that influences light interception, radiation fluxes and consequently plant performance. Therefore, LAD and its parametrized form, the Beta distribution, is used in many photosynthesis models. However, in field cultivations, these parameters are difficult to assess and cereal crops in particular pose challenges since their leaves are thin, flexible, and often bent and twisted around their own axis. To our knowledge, there is only a very limited set of methods currently available to calculate LADs of field-grown cereal crops that explicitly takes these special morphological properties into account.

RESULTS

In this study, a new processing pipeline is introduced that allows for the generation of realistic leaf surface models and the analysis of LADs of field-grown cereal crops from 3D point clouds. The data acquisition is based on a convenient stereo imaging setup. The approach was validated with different artificial targets and results on the accuracy of the 3D reconstruction, leaf surface modeling and calculated LAD are given. The mean error of the 3D reconstruction was below 1 mm for an inclination angle range between 0° and 75° and the leaf surface could be quantified with an average accuracy of 90%. The concordance correlation coefficient (CCC) of 99.6% (p-value = [Formula: see text]) indicated a high correlation between the reconstructed inclination angle and the identity line. The LADs for bent leaves were reconstructed with a mean error of 0.21° and a standard deviation of 1.55°. As an additional parameter, the insertion angle was reconstructed for the artificial leaf model with an average error < 5°. Finally, the method was tested with images of field-grown cereal crops and Beta functions were approximated from the calculated LADs. The mean CCC between reconstructed LAD and calculated Beta function was 0.66. According to Cohen, this indicates a high correlation.

CONCLUSION

This study shows that our image processing pipeline can reconstruct the complex leaf shape of cereal crops from stereo images. The high accuracy of the approach was demonstrated with several validation experiments including artificial leaf targets. The derived leaf models were used to calculate LADs for artificial leaves and naturally grown cereal crops. This helps to better understand the influence of the canopy structure on light absorption and plant performance and allows for a more precise parametrization of photosynthesis models via the derived Beta distributions.

To What Extent Does Yellow Rust Infestation Affect Remotely Sensed Nitrogen Status?

The utilization of high-throughput in-field phenotyping systems presents new opportunities for evaluating crop stress. However, existing studies have primarily focused on individual stresses, overlooking the fact that crops in field conditions frequently encounter multiple stresses, which can display similar symptoms or interfere with the detection of other stress factors. Therefore, this study aimed to investigate the impact of wheat yellow rust on reflectance measurements and nitrogen status assessment. A multi-sensor mobile platform was utilized to capture RGB and multispectral images throughout a 2-year fertilization-fungicide trial. To identify disease-induced damage, the SegVeg approach, which combines a U-NET architecture and a pixel-wise classifier, was applied to RGB images, generating a mask capable of distinguishing between healthy and damaged areas of the leaves. The observed proportion of damage in the images demonstrated similar effectiveness to visual scoring methods in explaining grain yield. Furthermore, the study discovered that the disease not only affected reflectance through leaf damage but also influenced the reflectance of healthy areas by disrupting the overall nitrogen status of the plants. This emphasizes the importance of incorporating disease impact into reflectance-based decision support tools to account for its effects on spectral data. This effect was successfully mitigated by employing the NDRE vegetation index calculated exclusively from the healthy portions of the leaves or by incorporating the proportion of damage into the model. However, these findings also highlight the necessity for further research specifically addressing the challenges presented by multiple stresses in crop phenotyping.

A CNN-LSTM-att hybrid model for classification and evaluation of growth status under drought and heat stress in chinese fir (Cunninghamia lanceolata)

BACKGROUND

Cunninghamia lanceolata (Chinese fir), is one of the most important timber trees in China. With the global warming, to develop new resistant varieties to drought or heat stress has become an essential task for breeders of Chinese fir. However, classification and evaluation of growth status of Chinese fir under drought or heat stress are still labor-intensive and time-consuming.

RESULTS

In this study, we proposed a CNN-LSTM-att hybrid model for classification of growth status of Chinese fir seedlings under drought and heat stress, respectively. Two RGB image datasets of Chinese fir seedling under drought and heat stress were generated for the first time, and utilized in this study. By comparing four base CNN models with LSTM, the Resnet50-LSTM was identified as the best model in classification of growth status, and LSTM would dramatically improve the classification performance. Moreover, attention mechanism further enhanced performance of Resnet50-LSTM, which was verified by Grad-CAM. By applying the established Resnet50-LSTM-att model, the accuracy rate and recall rate of classification was up to 96.91% and 96.79% for dataset of heat stress, and 96.05% and 95.88% for dataset of drought, respectively. Accordingly, the R2 value and RMSE value for evaluation on growth status under heat stress were 0.957 and 0.067, respectively. And, the R2 value and RMSE value for evaluation on growth status under drought were 0.944 and 0.076, respectively.

CONCLUSION

In summary, our proposed model provides an important tool for stress phenotyping in Chinese fir, which will be a great help for selection and breeding new resistant varieties in future.