Search

Recently, nuclear abnormalities in avian erythrocytes have been used as biomarkers of genotoxicity in several species. Anomalous shapes are usually detected in the nuclei by means of microscopy inspection. However, due to inter- and intra-observer variability, the classification of these blood cell abnormalities could be problematic for replicating research. Deep learning, as a powerful image analysis technique, can be used in this context to improve standardization in identifying the biological configurations of medical and veterinary importance. In this study, we present a standardized deep learning model for identifying and classifying abnormal shapes in erythrocyte nuclei in blood smears of the hemispheric and synanthropic Kelp Gull (Larus dominicanus). We trained three convolutional backbones (ResNet34 and ResNet50 architectures) to obtain models capable of detecting and classifying these abnormalities in blood cells. The analysis was performed at three discrimination levels of classification, with broad categories subdivided into increasingly specific subcategories (level 1: "normal", "abnormal", "other"; level 2: "normal", "ENAs", "micronucleus", "other"; level 3: "normal", "irregular", "displaced", "enucleated", "micronucleus", "other"). The results were more than adequate and very similar in levels 1 and 2 (F1-score 84.6% and 83.6%, and accuracy 83.9% and 82.6%). In level 3, performance was lower (F1-score 65.9% and accuracy 80.8%). It can be concluded that the level 2 analysis should be considered the most appropriate as it is more specific than level 1, with similar quality of performance. This method has proven to be a fast, efficient, and standardized approach that reduces the dependence on human supervision in the classification of nuclear abnormalities in avian erythrocytes, and can be adapted to be used in similar contexts with reduced effort. [ABSTRACT FROM AUTHOR]

Finding point‐wise correspondences between images is a long‐standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport changes. In this paper, we present the first attempt to obtain a learned descriptor for dense registration in line drawings. Based on recent deep learning techniques for corresponding photographs, we designed descriptors to locally match image pairs where the object of interest belongs to the same semantic category, yet still differ drastically in shape, form, and projection angle. To this end, we have specifically crafted a data set of synthetic sketches using non‐photorealistic rendering over a large collection of part‐based registered 3D models. After training, a neural network generates descriptors for every pixel in an input image, which are shown togeneralize correctly in unseen sketches hand‐drawn by humans. We evaluate our method against a baseline of correspondences data collected from expert designers, in addition to comparisons with other descriptors that have been proven effective in sketches. Code, data and further resources will be publicly released by the time of publication. [ABSTRACT FROM AUTHOR]

Abstract: Segmentation and measurement of linear characteristics in remote sensing imagery are among the first stages in several geomorphologic studies, including the length estimation of geographic features such as perimeters, coastal lines, and borders. However, unlike area measurement algorithms, widely used methods for perimeter estimation in digital images have high systematic errors. No precision improvement can be achieved with finer spatial resolution images because of the inherent geometrical inaccuracies they commit. In this work, a superresolution border segmentation and measurement algorithm is presented. The method is based on minimum distance segmentation over the initial image, followed by contour tracking using a superresolution enhancement of the marching squares algorithm. Thorough testing with synthetic and validated field images shows that this algorithm outperforms traditional border measuring methods, regardless of the image resolution or the orientation, size, and shape of the object to be analyzed. [Copyright &y& Elsevier]

Traditional marine mammal photo-identification is based on recognizing the appearances of the same individuals in pictures taken at different places and times. This task is traditionally performed by Biologists or other Scientists, which may demand a heavy cognitive burden and appreciable processing time searching and selecting information from thousands of pictures. Recently crowdsourcing and citizen science arose as a significant information source of potential scientific use. In particular, the use of non-professional photographs taken by the general public is being leveraged by many scientific projects. This represents an opportunity to enlarge the picture database required in trustable capture-recapture models, but at the same time human-assisted matching becomes unfeasible. Automated image analysis may represent an obvious aid, but applying image analytics to match individuals in large unfiltered datasets may be too slow and full of spurious results. Another strategy may be first to filter out useless images or parts thereof, retaining only the regions of interest (RoIs) in which appears the actual visible portion of the animal to be identified. In this work, we explore and develop a multi-criterion RoI detection for marine mammal pictures taken in the open. Particularly we focus on Commerson's dolphins pictures. Popular RoI detection algorithms, like Haar-wavelet-based methods, are show to perform poorly. For this reason, a convolutional neural network and a multifractal classifier based on color and texture features were developed, achieving significantly better outcomes. The resulting RoIs are much more robust, can be automated, and reduce the further burden of the identification process, either assisted or unassisted. Unlabelled Image • Automated method for detection and segmentation of sea mammals in uncontrolled pictures. • Multi-criterion region of interest detection achieved remarkable outcomes. • The resulting processing is useful to filter crowdsourced picture datasets. • It further facilitates sea mammal photo-identification based capture-recapture models. [ABSTRACT FROM AUTHOR]

Hard-cheeses are foods with high commercial value, thus fraudulent practices are frequent and difficult to detect, which reduce hard-cheese quality and consequently, decreases nutritional value. This work presents a novel and feasible tool to identify the adulteration of grated-cheese with higher levels of additives than those permitted (cellulose and silicon dioxide), and foreign substances used to increase weight and volume (wheat-flour, wheat-semolina and sawdust). The methodology is based on the use of colour histograms (obtained from digital images) and multivariate classification analysis. Satisfactory results were obtained with support vector machines with average values of accuracy and sensitivity above 82%, as adulterated samples were discriminated from original (unadulterated) samples. The proposed screening methodology represents a fast, simple, reliable and affordable way to perform quality control of grated-cheeses to avoid food fraud and nutritional detriments of worldwide consumption foods such as hard-cheeses. [ABSTRACT FROM AUTHOR]