Self-normalized density map (SNDM) for counting microbiological objects.

The statistical properties of the density map (DM) approach to counting microbiological objects on images are studied in detail. The DM is given by U[Formula: see text]-Net. Two statistical methods for deep neural networks are utilized: the bootstrap and the Monte Carlo (MC) dropout. The detailed analysis of the uncertainties for the DM predictions leads to a deeper understanding of the DM model's deficiencies. Based on our investigation, we propose a self-normalization module in the network. The improved network model, called Self-Normalized Density Map (SNDM), can correct its output density map by itself to accurately predict the total number of objects in the image. The SNDM architecture outperforms the original model. Moreover, both statistical frameworks-bootstrap and MC dropout-have consistent statistical results for SNDM, which were not observed in the original model. The SNDM efficiency is comparable with the detector-base models, such as Faster and Cascade R-CNN detectors.

Multiple intermodal-vectorial four-wave mixing bands generated by selective excitation of orthogonally polarized LP01 and LP11 modes in a birefringent fiber.

This study investigates the nonlinear frequency conversions between the six polarization modes of a two-mode birefringent fiber. The aim is to demonstrate that the selective excitation of different combinations of linearly polarized spatial modes at the pump wavelength initiates distinct intermodal-vectorial four-wave mixing processes. In particular, this study shows that exciting two orthogonally polarized LP01 and LP11 modes can lead to the simultaneous generation of up to three pairs of different spatial modes of orthogonal polarizations at different wavelengths. The role of the phase birefringence of the spatial modes in the phase matching of such a four-wave mixing process is explained. Moreover, the theoretical predictions are verified through numerical simulations based on coupled nonlinear Schrödinger equations, and are also confirmed experimentally in a commercially available birefringent fiber.

Generation of microbial colonies dataset with deep learning style transfer.

We introduce an effective strategy to generate an annotated synthetic dataset of microbiological images of Petri dishes that can be used to train deep learning models in a fully supervised fashion. The developed generator employs traditional computer vision algorithms together with a neural style transfer method for data augmentation. We show that the method is able to synthesize a dataset of realistic looking images that can be used to train a neural network model capable of localising, segmenting, and classifying five different microbial species. Our method requires significantly fewer resources to obtain a useful dataset than collecting and labeling a whole large set of real images with annotations. We show that starting with only 100 real images, we can generate data to train a detector that achieves comparable results (detection mAP [Formula: see text], and counting MAE [Formula: see text]) to the same detector but trained on a real, several dozen times bigger dataset (mAP [Formula: see text], MAE [Formula: see text]), containing over 7 k images. We prove the usefulness of the method in microbe detection and segmentation, but we expect that it is general and flexible and can also be applicable in other domains of science and industry to detect various objects.

Deep learning-based waste detection in natural and urban environments.

Waste pollution is one of the most significant environmental issues in the modern world. The importance of recycling is well known, both for economic and ecological reasons, and the industry demands high efficiency. Current studies towards automatic waste detection are hardly comparable due to the lack of benchmarks and widely accepted standards regarding the used metrics and data. Those problems are addressed in this article by providing a critical analysis of over ten existing waste datasets and a brief but constructive review of the existing Deep Learning-based waste detection approaches. This article collects and summarizes previous studies and provides the results of authors' experiments on the presented datasets, all intended to create a first replicable baseline for litter detection. Moreover, new benchmark datasets detect-waste and classify-waste are proposed that are merged collections from the above-mentioned open-source datasets with unified annotations covering all possible waste categories: bio, glass, metal and plastic, non-recyclable, other, paper, and unknown. Finally, a two-stage detector for litter localization and classification is presented. EfficientDet-D2 is used to localize litter, and EfficientNet-B2 to classify the detected waste into seven categories. The classifier is trained in a semi-supervised fashion making the use of unlabeled images. The proposed approach achieves up to 70% of average precision in waste detection and around 75% of classification accuracy on the test dataset. The code and annotations used in the studies are publicly available online1.