Efficient annotation of image data sets for computer vision applications

Automatic image compositing of very large data sets is necessary for the creation of extensive mosaics based on high spatial resolution remotely sensed imagery. A novel morphological image compositing algorithm has been developed which adapts to salient images edges. This technique produces seam lines that are difficult to identify by the naked eye which is also a characteristic to measure the quality of the resulting seam line. This paper begins with a description of the methodology and results based on Landsat 7 ETM+ imagery. It is also shown how updates to an already composited image data set can be easily made without having to reprocess the entire data set. Finally, ways of quantifying the quality of an automatically delineated cut line and future research directions are discussed.

<h3>Abstract</h3> Much of the DNA and RNA sequencing data available is in the form of high-throughput sequencing (HTS) reads and is currently unindexed by established sequence search databases. Recent succinct data structures for indexing both reference sequences and HTS data, along with associated metadata, have been based on either hashing or graph models, but many of these structures are static in nature, and thus, not well-suited as backends for dynamic databases. We propose a parallel construction method for and novel application of the <i>wavelet trie</i> as a dynamic data structure for compressing and indexing graph metadata. By developing an algorithm for merging wavelet tries, we are able to construct large tries in parallel by merging smaller tries constructed concurrently from batches of data. When compared against general compression algorithms and those developed specifically for graph colors (VARI and Rainbowfish), our method achieves compression ratios superior to gzip and VARI, converging to compression ratios of 6.5% to 2% on data sets constructed from over 600 virus genomes. While marginally worse than compression by bzip2 or Rainbowfish, this structure allows for both fast extension and query. We also found that additionally encoding graph topology metadata improved compression ratios, particularly on data sets consisting of several mutually-exclusive reference genomes. It was also observed that the compression ratio of wavelet tries grew sublinearly with the density of the annotation matrices. This work is a significant step towards implementing a dynamic data structure for indexing large annotated sequence data sets that supports fast query and update operations. At the time of writing, no established standard tool has filled this niche.

Is power everything? What can we learn from large data sets

The massive adoption of smart phones and other mobile devices has generated humongous amount of spatial and spatio-temporal data. The importance of spatial analytics and aggregation is ever-increasing. An important challenge is to support interactive exploration over such data. However, spatial analytics and aggregation using all data points that satisfy a query condition is expensive, especially over large data sets, and could not meet the needs of interactive exploration. To that end, we present novel indexing structures that support spatial online sampling and aggregation on large spatial and spatio-temporal data sets. In spatial online sampling, random samples from the set of spatial (or spatio-temporal) points that satisfy a query condition are generated incrementally in an online fashion. With more and more samples, various spatial analytics and aggregations can be performed in an online, interactive fashion, with estimators that have better accuracy over time. Our design works well for both memory-based and disk-resident data sets, and scales well towards different query and sample sizes. More importantly, our structures are dynamic, hence, they are able to deal with insertions and deletions efficiently. Extensive experiments on large real data sets demonstrate the improvements achieved by our indexing structures compared to other baseline methods.

Improving semi-supervised learning through optimum connectivity

The value of protein models obtained with automated protein structure prediction depends primarily on their accuracy. Protein model quality assessment is thus critical to select the model that can best answer biologically relevant questions from an ensemble of predictions. However, despite many advances in the field, different methods capture different types of errors, begging the question of which method to use. We introduce TopScore, a meta Model Quality Assessment Program (meta-MQAP) that uses deep neural networks to combine scores from 15 different primary predictors to predict accurate residue-wise and whole-protein error estimates. The predictions on six large independent data sets are highly correlated to superposition-independent errors in the model, achieving a Pearson's Rall2 of 0.93 and 0.78 for whole-protein and residue-wise error predictions, respectively. This is a significant improvement over any of the investigated primary MQAPs, demonstrating that much can be gained by optimally combining different methods and using different and very large data sets.

We present a fast point cloud clustering technique which is suitable for outlier detection, object segmentation and region labeling for large multi-dimensional data sets. The basis is a minimal data structure similar to a kd-tree which enables us to detect connected subsets very fast. The proposed algorithms utilizing this tree structure are parallelizable which further increases the computation speed for very large data sets. The procedures given are a vital part of the data preprocessing. They improve the input data properties for a more reliable computation of surface measures, polygonal meshes and other visualization techniques. In order to show the effectiveness of our techniques we evaluate sets of point clouds from different 3D scanning devices.

Unsupervised and simultaneous training of multiple object detectors from unlabeled surveillance video

For many learning algorithms, their learning accuracy will increase as the size of training data increases, forming the well-known learning curve. Usually a learning curve can be fitted by interpolating or extrapolating some points on it with a specified model. The obtained learning curve can then be used to predict the maximum achievable learning accuracy or to estimate the amount of data needed to achieve an expected learning accuracy, both of which will be especially meaningful to data mining on large data sets. Although some models have been proposed to model learning curves, most of them do not test their applicability to large data sets. In this paper, we focus on this issue. We empirically compare six potentially useful models by fitting learning curves of two typical classification algorithms--C4.5 (decision tree) and LOG (logistic discrimination) on eight large UCI benchmark data sets. By using all available data for learning, we fit a full-length learning curve; by using a small portion of the data, we fit a part-length learning curve. The models are then compared in terms of two performances: (1) how well they fit a full-length learning curve, and (2) how well a fitted part-length learning curve can predict learning accuracy at the full length. Experimental results show that the power law (y = a - b * x-c) is the best among the six models in both the performances for the two algorithms and all the data sets. These results support the applicability of learning curves to data mining.

Measuring airways in chest computed tomography (CT) images is important for characterizing diseases such as cystic fibrosis, yet very time-consuming to perform manually. Machine learning algorithms offer an alternative, but need large sets of annotated data to perform well. We investigate whether crowdsourcing can be used to gather airway annotations which can serve directly for measuring the airways, or as training data for the algorithms. We generate image slices at known locations of airways and request untrained crowd workers to outline the airway lumen and airway wall. Our results show that the workers are able to interpret the images, but that the instructions are too complex, leading to many unusable annotations. After excluding unusable annotations, quantitative results show medium to high correlations with expert measurements of the airways. Based on this positive experience, we describe a number of further research directions and provide insight into the challenges of crowdsourcing in medical images from the perspective of first-time users.

Recent advances in unsteady flow visualization

Recent advancements in deep learning have greatly improved computer vision tasks like object detection, image classification, and segmentation. Despite these successes, traditional supervised learning methods still depend on large annotated datasets, which are often expensive and time consuming to create. To overcome this limitation, we present a zero-shot segmentation framework that combines the strengths of CLIP (Contrastive Language-Image Pretraining), its segmentation-focused variant CLIPSeg, and the Segment Anything Model (SAM). This approach first uses the zero-shot classification ability of CLIP or CLIPSeg to produce initial segmentation cues. These cues, such as point and box prompts, are then refined by SAM to generate accurate segmentation masks. Using this prompt-based strategy, the system can perform segmentation without requiring labeled data, making it suitable for a wide range of domains, including both natural scenes and medical imaging. Our experiments on benchmarks such as MS-COCO, Pascal VOC, and chest X-ray datasets highlight the effectiveness of the method. In particular, the CLIPSeg+SAM combination achieves a mean IoU of 0.793 and a Dice score of 0.873 in the chest X-ray dataset, outperforming both CLIPSeg and SAM when used alone. Visual results also show that this method produces clearer and more precise mask boundaries, even in challenging or cluttered environments. In summary, the proposed training-free framework offers a scalable and generalizable solution for zero-shot segmentation, significantly reducing the reliance on annotated datasets while delivering strong performance on unseen classes.

Environmental monitoring programs provide large multivariate data sets that usually cover considerable spatial and temporal variabilities. The apparent complexity of these data sets requires sophisticated tools for their processing. Usually, fixed schemes are followed, including the application of numerical models, which are increasingly implemented in decision support systems. However, these schemes are too rigid with respect to detecting unexpected features, like the onset of subtle trends, non-linear relationships or patterns that are restricted to limited sub-samples of the total data set. In this study, an alternative approach is followed. It is based on an efficient non-linear visualization of the data. Visualization is the most powerful interface between computer and human brain. The idea is to apply an efficient and model-free tool, meaning without the necessity of prior assumptions about key properties of the data, such as dominant processes. In other words, processing of the data aimed at preserving a maximum amount of information and to leave it to the expert which features to analyze in more detail. A comprehensive data set from a 15-year monitoring program in the Lehstenbach watershed was used. The watershed is located in the Fichtelgebirge area, a mountainous region in South Germany, where land-use is forestry. Streamwater and groundwater have been monitored at 38 sampling sites, comprising 13 parameters. The data set was analyzed using a self-organizing map (SOM), combined with Sammon’s mapping. The 2D non-linear projection represented 89% of the variance of the data set. The visualization of the data set enabled an easy detection of outliers, assessing spatial versus temporal variance, and verifying a predefined classification of the sampling sites. Contamination of two of the observation wells was detected. Long-term trends of solute concentration in the catchment runoff could be differentiated from short-term dynamics, and a long-term shift in the dynamics was determined for different flow regimes individually. This analysis helped considerably to better understand the system’s behavior, to detect “hot spots” and to organize subsequent analyses of the data in a very efficient way.

Parallel coordinate plots (PCPs) are commonly used in information visualization to provide insight into multi-variate data. These plots help to spot correlations between variables. PCPs have been successfully applied to unstructured datasets up to a few millions of points. In this paper, we present techniques to enhance the usability of PCPs for the exploration of large, multi-timepoint volumetric data sets, containing tens of millions of points per timestep. The main difficulties that arise when applying PCPs to large numbers of data points are visual clutter and slow performance, making interactive exploration infeasible. Moreover, the spatial context of the volumetric data is usually lost. We describe techniques for preprocessing using data quantization and compression, and for fast GPU-based rendering of PCPs using joint density distributions for each pair of consecutive variables, resulting in a smooth, continuous visualization. Also, fast brushing techniques are proposed for interactive data selection in multiple linked views, including a 3D spatial volume view. These techniques have been successfully applied to three large data sets: Hurricane Isabel (Vis'04 contest), the ionization front instability data set (Vis'08 design contest), and data from a large-eddy simulation of cumulus clouds. With these data, we show how PCPs can be extended to successfully visualize and interactively explore multi-timepoint volumetric datasets with an order of magnitude more data points.

Methodology evaluation for decision support systems for health is a time-consuming task. To assess performance of polyp detection methods in colonoscopy videos, clinicians have to deal with the annotation of thousands of images. Current existing tools could be improved in terms of flexibility and ease of use. We introduce GTCreator, a flexible annotation tool for providing image and text annotations to image-based datasets. It keeps the main basic functionalities of other similar tools while extending other capabilities such as allowing multiple annotators to work simultaneously on the same task or enhanced dataset browsing and easy annotation transfer aiming to speed up annotation processes in large datasets. The comparison with other similar tools shows that GTCreator allows to obtain fast and precise annotation of image datasets, being the only one which offers full annotation editing and browsing capabilites. Our proposed annotation tool has been proven to be efficient for large image dataset annotation, as well as showing potential of use in other stages of method evaluation such as experimental setup or results analysis.