Multi-Scale Memetic Image Registration

Many technological applications of our time rely on images captured by multiple cameras. Such applications include the detection and recognition of objects in captured images, the tracking of objects and analysis of their motion, and the detection of changes in appearance. The alignment of images captured at different times and/or from different angles is a key processing step in these applications. One of the most challenging tasks is to develop fast algorithms to accurately align images perturbed by various types of transformations. The paper reports a new method used to register images in the case of geometric perturbations that include rotations, translations, and non-uniform scaling. The input images can be monochrome or colored, and they are preprocessed by a noise-insensitive edge detector to obtain binarized versions. Isotropic scaling transformations are used to compute multi-scale representations of the binarized inputs. The algorithm is of memetic type and exploits the fact that the computation carried out in reduced representations usually produces promising initial solutions very fast. The proposed method combines bio-inspired and evolutionary computation techniques with clustered search and implements a procedure specially tailored to address the premature convergence issue in various scaled representations. A long series of tests on perturbed images were performed, evidencing the efficiency of our memetic multi-scale approach. In addition, a comparative analysis has proved that the proposed algorithm outperforms some well-known registration procedures both in terms of accuracy and runtime.

Signal Folding for Efficient Classification of Near-Cyclostationary Biological Signals

The classification of biological signals is important in detecting abnormal conditions in observed biological subjects. The classifiers are trained on feature vectors, which often constitute the parameters of the observed time series data models. Since the feature extraction is usually the most time-consuming step in training a classifier, in this paper, signal folding and the associated folding operator are introduced to reduce the variability in near-cyclostationary biological signals so that these signals can be represented by models that have a lower order. This leads to a substantial reduction in computational complexity, so the classifier can be learned an order of magnitude faster and still maintain its decision accuracy. The performance of different classifiers involving signal folding as a pre-processing step is studied for sleep apnea detection in one-lead ECG signals assuming ARIMA modeling of the time series data. It is shown that the R-peak-based folding of ECG segments has superior performance to other more general, similarity based signal folding methods. The folding order can be optimized for the best classification accuracy. However, signal folding requires precise scaling and alignment of the created signal fragments.

Spike sorting: new trends and challenges of the era of high-density probes

Recording from a large neuronal population of neurons is a crucial challenge to unravel how information is processed by the brain. In this review, we highlight the recent advances made in the field of “spike sorting”, which is arguably a very essential processing step to extract neuronal activity from extracellular recordings. We more specifically target the challenges faced by newly manufactured high-density multi-electrode array devices (HD-MEA), e.g. Neuropixels probes. Among them, we cover in depth the prominent problem of drifts (movements of the neurons with respect to the recording devices) and the current solutions to circumscribe it. In addition, we also review recent contributions making use of deep learning approaches for spike sorting, highlighting their advantages and disadvantages. Next, we highlight efforts and advances in unifying, validating, and benchmarking spike sorting tools. Finally, we discuss the spike sorting field in terms of its open and unsolved challenges, specifically regarding scalability and reproducibility. We conclude by providing our personal view on the future of spike sorting, calling for a community-based development and validation of spike sorting algorithms and fully automated, cloud-based spike sorting solutions for the neuroscience community.

An optimal video summarization of surveillance systems using LFOB-COA with deep features and RBLSTM

The visual data attained from surveillance single-camera or multi-view camera networks is exponentially increasing every day. Identifying the important shots in the presented video which faithfully signify the original video is the major task in video summarization. For executing efficient video summarization of the surveillance systems, optimization algorithm like LFOB-COA is proposed in this paper. Data collection, pre-processing, deep feature extraction (FE), shot segmentation JSFCM, classification using Rectified Linear Unit activated BLSTM, and LFOB-COA are the proposed method’s five steps. Finally a post-processing step is utilized. For recognizing the proposed method’s effectiveness, the results are then contrasted with the existent methods.

Inflated 3D ConvNet context analysis for violence detection

According to the Wall Street Journal, one billion surveillance cameras will be deployed around the world by 2021. This amount of information can be hardly managed by humans. Using a Inflated 3D ConvNet as backbone, this paper introduces a novel automatic violence detection approach that outperforms state-of-the-art existing proposals. Most of those proposals consider a pre-processing step to only focus on some regions of interest in the scene, i.e., those actually containing a human subject. In this regard, this paper also reports the results of an extensive analysis on whether and how the context can affect or not the adopted classifier performance. The experiments show that context-free footage yields substantial deterioration of the classifier performance (2% to 5%) on publicly available datasets. However, they also demonstrate that performance stabilizes in context-free settings, no matter the level of context restriction applied. Finally, a cross-dataset experiment investigates the generalizability of results obtained in a single-collection experiment (same dataset used for training and testing) to cross-collection settings (different datasets used for training and testing).

The Influence of Aerial Hyperspectral Image Processing Workflow on Nitrogen Uptake Prediction Accuracy in Maize

A meticulous image processing workflow is oftentimes required to derive quality image data from high-resolution, unmanned aerial systems. There are many subjective decisions to be made during image processing, but the effects of those decisions on prediction model accuracy have never been reported. This study introduced a framework for quantifying the effects of image processing methods on model accuracy. A demonstration of this framework was performed using high-resolution hyperspectral imagery (<10 cm pixel size) for predicting maize nitrogen uptake in the early to mid-vegetative developmental stages (V6–V14). Two supervised regression learning estimators (Lasso and partial least squares) were trained to make predictions from hyperspectral imagery. Data for this use case were collected from three experiments over two years (2018–2019) in southern Minnesota, USA (four site-years). The image processing steps that were evaluated include (i) reflectance conversion, (ii) cropping, (iii) spectral clipping, (iv) spectral smoothing, (v) binning, and (vi) segmentation. In total, 648 image processing workflow scenarios were evaluated, and results were analyzed to understand the influence of each image processing step on the cross-validated root mean squared error (RMSE) of the estimators. A sensitivity analysis revealed that the segmentation step was the most influential image processing step on the final estimator error. Across all workflow scenarios, the RMSE of predicted nitrogen uptake ranged from 14.3 to 19.8 kg ha−1 (relative RMSE ranged from 26.5% to 36.5%), a 38.5% increase in error from the lowest to the highest error workflow scenario. The framework introduced demonstrates the sensitivity and extent to which image processing affects prediction accuracy. It allows remote sensing analysts to improve model performance while providing data-driven justification to improve the reproducibility and objectivity of their work, similar to the benefits of hyperparameter tuning in machine learning applications.

New Stereo Vision Algorithm Composition Using Weighted Adaptive Histogram Equalization and Gamma Correction

This work presents the composition of a new algorithm for a stereo vision system to acquire accurate depth measurement from stereo correspondence. Stereo correspondence produced by matching is commonly affected by image noise such as illumination variation, blurry boundaries, and radiometric differences. The proposed algorithm introduces a pre-processing step based on the combination of Contrast Limited Adaptive Histogram Equalization (CLAHE) and Adaptive Gamma Correction Weighted Distribution (AGCWD) with a guided filter (GF). The cost value of the pre-processing step is determined in the matching cost step using the census transform (CT), which is followed by aggregation using the fixed-window and GF technique. A winner-takes-all (WTA) approach is employed to select the minimum disparity map value and final refinement using left-right consistency checking (LR) along with a weighted median filter (WMF) to remove outliers. The algorithm improved the accuracy 31.65% for all pixel errors and 23.35% for pixel errors in nonoccluded regions compared to several established algorithms on a Middlebury dataset.

Query-focused multi-document text summarization using fuzzy inference

The present paper proposes a fuzzy inference system for query-focused multi-document text summarization (MTS). The overall scheme is based on Mamdani Inferencing scheme which helps in designing Fuzzy Rule base for inferencing about the decision variable from a set of antecedent variables. The antecedent variables chosen for the task are from linguistic and positional heuristics, and similarity of the documents with the user-defined query. The decision variable is the rank of the sentences as decided by the rules. The final summary is generated by solving an Integer Linear Programming problem. For abstraction coreference resolution is applied on the input sentences in the pre-processing step. Although designed on the basis of a small set of antecedent variables the results are very promising.

Caviar-Sunflower Optimization Algorithm-Based Deep Learning Classifier for Multi-Document Summarization

This paper proposes a multi-document summarization model using an optimization algorithm named CAVIAR Sun Flower Optimization (CAV-SFO). In this method, two classifiers, namely: Generative Adversarial Network (GAN) classifier and Deep Recurrent Neural Network (Deep RNN), are utilized to generate a score for summarizing multi-documents. Initially, the simHash method is applied for removing the duplicate/real duplicate contents from sentences. Then, the result is given to the proposed CAV-SFO based GAN classifier to determine the score for individual sentences. The CAV-SFO is newly designed by incorporating CAVIAR with Sun Flower Optimization Algorithm (SFO). On the other hand, the pre-processing step is done for duplicate-removed sentences from input multi-document based on stop word removal and stemming. Afterward, text-based features are extracted from pre-processed documents, and then CAV-SFO based Deep RNN is introduced for generating a score; thereby, the internal model parameters are optimally tuned. Finally, the score generated by CAV-SFO based GAN and CAV-SFO based Deep RNN is hybridized, and the final score is obtained using a multi-document compression ratio. The proposed TaylorALO-based GAN showed improved results with maximal precision of 0.989, maximal recall of 0.986, maximal F-Measure of 0.823, maximal Rouge-Precision of 0.930, and maximal Rouge-recall of 0.870.

Assessing the utility of marine filter feeders for environmental DNA (eDNA) biodiversity monitoring

Aquatic environmental DNA (eDNA) surveys are transforming how we monitor marine ecosystems. The time-consuming pre-processing step of active filtration, however, remains a bottleneck. Hence, new approaches omitting active filtration are in great demand. One exciting prospect is to use the filtering power of invertebrates to collect eDNA. While proof-of-concept has been achieved, comparative studies between aquatic and filter feeder eDNA signals are lacking. Here, we investigated the differences among four eDNA sources (water; bivalves; sponges; and ethanol in which filter-feeding organisms were stored) along a vertical transect in Doubtful Sound, New Zealand using three metabarcoding primers (fish (16S); MiFish-E/U). While concurrent SCUBA diver observations validated eDNA results, laboratory trials corroborated in-field bivalve eDNA detection results. Combined, eDNA sources detected 59 vertebrates, while divers observed eight fish species. There were no significant differences in alpha and beta diversity between water and sponge eDNA and both sources were highly correlated. Vertebrate eDNA was detected in ethanol, although only a reduced number of species were detected. Bivalves failed to reliably detect eDNA in both field and mesocosm experiments. While additional research into filter feeder eDNA accumulation efficiency is essential, our results provide strong evidence for the potential of incorporating sponges into eDNA surveys.