Reduction in chemical usage for crop management due to the environmental and health issues is a key area in achieving sustainable agricultural practices. One area in which this can be achieved is through the development of intelligent spraying systems which can identify the target for example crop disease or weeds allowing for precise spraying reducing chemical usage. Artificial intelligence and computer vision has the potential to be applied for the precise detection and classification of crops. In this paper, a study is presented that uses instance segmentation for the task of leaf and rust disease detection in apple orchards using Mask R-CNN. Three different Mask R-CNN network backbones (ResNet-50, MobileNetV3-Large and MobileNetV3-Large-Mobile) are trained and evaluated for the tasks of object detection, segmentation and disease detection. Segmentation masks on a subset of the Plant Pathology Challenge 2020 database are annotated by the authors, and these are used for the training and evaluation of the proposed Mask R-CNN based models. The study highlights that a Mask R-CNN model with a ResNet-50 backbone provides good accuracy for the task, particularly in the detection of very small rust disease objects on the leaves.

The capability to perform facial analysis from video sequences has significant potential to positively impact in many areas of life. One such area relates to the medical domain to specifically aid in the diagnosis and rehabilitation of patients with facial palsy. With this application in mind, this paper presents an end-to-end framework, named 3DPalsyNet, for the tasks of mouth motion recognition and facial palsy grading. 3DPalsyNet utilizes a 3D CNN architecture with a ResNet backbone for the prediction of these dynamic tasks. Leveraging transfer learning from a 3D CNNs pre-trained on the Kinetics data set for general action recognition, the model is modified to apply joint supervised learning using center and softmax loss concepts. 3DPalsyNet is evaluated on a test set consisting of individuals with varying ranges of facial palsy and mouth motions and the results have shown an attractive level of classification accuracy in these tasks of 82% and 86% respectively. The frame duration and the loss function affect was studied in terms of the predictive qualities of the proposed 3DPalsyNet, where it was found shorter frame duration’s of 8 performed best for this specific task. Centre loss and softmax have shown improvements in spatio-temporal feature learning than softmax loss alone, this is in agreement with earlier work involving the spatial domain.

The outcome for patients diagnosed with facial palsy has been shown to be linked to rehabilitation. Dense 3D morphable models have been shown within the computer vision to create accurate representations of human faces even from single 2D images. This has the potential to provide feedback to both the patient and medical expert dealing with the rehabilitation plan. It is proposed that a framework for the creation and measuring of patient facial movement consisting of a hybrid 2D facial landmark fitting technique which shows better accuracy in testing than current methods and 3D model fitting.

The tasks of face detection and landmark localisation are a key foundation for many facial analysis applications, while great advancements have been achieved in recent years there are still challenges to increase the precision of face detection. Within this paper, we present our novel method the Integrated Deep Model (IDM), fusing two state-of-the-art deep learning architectures, namely, Faster R-CNN and a stacked hourglass for improved face detection precision and accurate landmark localisation. Integration is achieved through the application of a novel optimisation function and is shown in experimental evaluation to increase accuracy of face detection specifically precision by reducing false positive detection's by an average of 62%. Our proposed IDM method is evaluated on the Annotated Faces In-The-Wild, Annotated Facial Landmarks In The Wild and the Face Detection Dataset and Benchmark face detection test sets and shows a high level of recall and precision when compared with previously proposed methods. Landmark localisation is evaluated on the Annotated Faces In-The-Wild and 300-W test sets, this specifically focuses on localisation accuracy from detected face bounding boxes when compared with baseline evaluations using ground truth bounding boxes. Our findings highlight only a small 0.005% maximum increase in error which is more profound for the subset of facial landmarks which border the face.