Deep learning techniques involving image processing and data analysis are constantly evolving. Many domains adapt these techniques for object segmentation, instantiation and classification. Recently, agricultural industries adopted those techniques in order to bring automation to farmers around the globe. One analysis procedure required for automatic visual inspection in this domain is leaf count and segmentation. Collecting labeled data from field crops and greenhouses is a complicated task due to the large variety of crops, growth seasons, climate changes, phenotype diversity, and more, especially when specific learning tasks require a large amount of labeled data for training. Data augmentation for training deep neural networks is well established, examples include data synthesis, using generative semi-synthetic models, and applying various kinds of transformations. In this paper we propose a method that preserves the geometric structure of the data objects, thus keeping the physical appearance of the data-set as close as possible to imaged plants in real agricultural scenes. The proposed method provides state of the art results when applied to the standard benchmark in the field, namely, the ongoing Leaf Segmentation Challenge hosted by Computer Vision Problems in Plant Phenotyping.

Background Facial anthropometric data are scarce in African children. However, such data may be useful for the design of medical devices for high disease burden settings. The aim of this study was to obtain 3D facial anthropometric data of Congolese children aged 0–5 years. Methods & findings The faces of 287 Congolese children were successfully scanned using a portable structured-light based 3D video camera, suitable for field work in low- income settings. The images were analyzed using facial analysis algorithms. Normal growth curves were generated for the following facial dimensions: distance between nares and distance from subnasion to upper lip. At birth, 1 year, and 5 years of age the median dimensions were: 13·92, 14·66, and 17.60 mm, respectively for distance between nares, and 10·16, 10.88, and 13·79 mm, respectively for distance from subnasion to upper lip. Modeled facial contours conveniently clustered into three average sizes which could be used as templates for the design of medical instruments. Conclusion Capturing of 3D images of infants and young children in LMICs is feasible using portable cameras and computerized analysis. This method and these specific data on Congolese pediatric facial dimensions may assist in the design of appropriately sized medical devices (thermometers, face masks, pulse oximeters, etc.) for this population.

No abstract

Sleep apnea is a syndrome that is characterized by sudden breathing halts while sleeping. One of the common treatments involves wearing a mask that delivers continuous air flow into the nostrils so as to maintain a steady air pressure. These masks are designed for an average facial model and are often difficult to adjust due to poor fit to the actual patient. The incompatibility is characterized by gaps between the mask and the face, which deteriorates the impermeability of the mask and leads to air leakage. We suggest a fully automatic approach for designing a personalized nasal mask interface using a facial depth scan. The interfaces generated by the proposed method accurately fit the geometry of the scanned face, and are easy to manufacture. The proposed method utilizes cheap commodity depth sensors and 3D printing technologies to efficiently design and manufacture customized masks for patients suffering from sleep apnea.

No abstract