1,721,300 research outputs found
Interactive and dynamic web-based visual exploration of high dimensional bioimages with real time clustering
No full textWeb browsers and web applications have become common tools in bioinformatics over the past decades. Many existing web applications revolve around server-client interaction, where heavy computational tasks are often outsourced to the server and the presentation is handled on the the client-side. However more recent additions to the web browser technology embrace the capability of handling more complex operations on the client-side itself, cutting out most of the server-client interaction except for data loading. This paper contributes to the exploration of the potential of approaches to implement and speed up computational expensive tasks, like image cluster analysis, within a client-side web browser environment. The experimental results, incorporating the well known k-means algorithm which serves as a platform for various parallelization approaches, indicate the possibility to achieve real time image clustering. Especially for the available MALDI-MSI data set the results look promising. Despite good results of multithreading approaches, algorithmic approaches appear to be relevant too. Therefore advancements in accelerating the k-means algorithm itself are considered
MAIA-A machine learning assisted image annotation method for environmental monitoring and exploration
No full textDigital imaging has become one of the most important techniques in environmental monitoring and exploration. In the case of the marine environment, mobile platforms such as autonomous underwater vehicles (AUVs) are now equipped with high-resolution cameras to capture huge collections of images from the seabed. However, the timely evaluation of all these images presents a bottleneck problem as tens of thousands or more images can be collected during a single dive. This makes computational support for marine image analysis essential. Computer-aided analysis of environmental images (and marine images in particular) with machine learning algorithms is promising, but challenging and different to other imaging domains because training data and class labels cannot be collected as efficiently and comprehensively as in other areas. In this paper, we present Machine learning Assisted Image Annotation (MAIA), a new image annotation method for environmental monitoring and exploration that overcomes the obstacle of missing training data. The method uses a combination of autoencoder networks and Mask Region-based Convolutional Neural Network (Mask R-CNN), which allows human observers to annotate large image collections much faster than before. We evaluated the method with three marine image datasets featuring different types of background, imaging equipment and object classes. Using MAIA, we were able to annotate objects of interest with an average recall of 84.1% more than twice as fast as compared to "traditional" annotation methods, which are purely based on software-supported direct visual inspection and manual annotation. The speed gain increases proportionally with the size of a dataset. The MAIA approach represents a substantial improvement on the path to greater efficiency in the annotation of large benthic image collections.</p
Data for the evaluation of the MAIA method for image annotation
No full textThis dataset contains all annotations and annotation candidates that were used for the evaluation of the MAIA method for image annotation. Each row in the CSVs represents one annotation candidate or final annotation. Annotation candidates have the label "OOI candidate" (label_id 9974). All other entries represent final reviewed annotations. Each CSV contains the information for one of the three image datasets that were used in the evaluation. Visual exploration of the data is possible in the BIIGLE 2.0 image annotation system at https://biigle.de/projects/139 using the login [email protected] and the password MAIApaper.</span
Annotated Southern Ocean diatom LM micrographs from POLARSTERN cruise PS79, 10 p - masked
No full textOn the impact of Citizen Science-derived data quality on deep learning based classification in marine images
Get PDFThe evaluation of large amounts of digital image data is of growing importance for biology, including for the exploration and monitoring of marine habitats. However, only a tiny percentage of the image data collected is evaluated by marine biologists who manually interpret and annotate the image contents, which can be slow and laborious. In order to overcome the bottleneck in image annotation, two strategies are increasingly proposed: “citizen science” and “machine learning”. In this study, we investigated how the combination of citizen science, to detect objects, and machine learning, to classify megafauna, could be used to automate annotation of underwater images. For this purpose, multiple large data sets of citizen science annotations with different degrees of common errors and inaccuracies observed in citizen science data were simulated by modifying “gold standard” annotations done by an experienced marine biologist. The parameters of the simulation were determined on the basis of two citizen science experiments. It allowed us to analyze the relationship between the outcome of a citizen science study and the quality of the classifications of a deep learning megafauna classifier. The results show great potential for combining citizen science with machine learning, provided that the participants are informed precisely about the annotation protocol. Inaccuracies in the position of the annotation had the most substantial influence on the classification accuracy, whereas the size of the marking and false positive detections had a smaller influence.</p
Annotated Southern Ocean diatom LM micrographs from POLARSTERN cruise PS79, 10 p - unmasked
No full textAnnotated Southern Ocean diatom LM micrographs from POLARSTERN cruise PS79, 100 p - unmasked
No full textAnnotated Southern Ocean diatom LM micrographs from POLARSTERN cruise PS103, 10 p - masked
No full textAnnotated Southern Ocean diatom LM micrographs from POLARSTERN cruise PS79, 100 p - masked
No full textAnnotated Southern Ocean diatom LM micrographs from Polarstern cruises PS79 & PS103
No full textSeveral sets of annotated (taxon, expedition, station) high resolution focus-enhanced light micoscopy images depicting valves of the Southern Ocean diatom species and genera Fragilariopsis kerguelensis, Pseudonitzschia, Chaetoceros, Thalassiosira lentiginosa, Fragilariopsis rhombica, Rhizosolenia, Asteromphalus, Thalassiosira gracilis and Nitzschia, plus the non-diatom taxon silicoflagellates. Objects are imaged with and without background masking. Pixel size is 0.098 x 0.098 µm²
- …
