Face recognition has become an integral part of modern security processes. This paper introduces an optimization approach for the quantile interval method (QIM), a promising classifier learning technique used in face recognition to create face templates and improve recognition accuracy. Our research offers a three-fold contribution to the field. Firstly, (i) we strengthened the evidence that QIM outperforms other contemporary template creation approaches. For this reason, we investigate seven template creation methods, which include four cluster description-based methods and three estimation-based methods. Further, (ii) we extended testing; we use a nearly four times larger database compared to the previous study, which includes a new set, and we report the recognition performance on this extended database. Additionally, we distinguish between open- and closed-set identification. Thirdly, (iii) we perform an evaluation of the cluster estimation-based method (specifically QIM) with an in-depth analysis of its parameter setup in order to make its implementation feasible. We provide instructions and recommendations for the correct parameter setup. Our research confirms that QIM's application in template creation improves recognition performance. In the case of automatic application and optimization of QIM parameters, improvement recognition is about 4-10% depending on the dataset. In the case of a too general dataset, QIM also provides an improvement, but the incorporation of QIM into an automated algorithm is not possible, since QIM, in this case, requires manual setting of optimal parameters. This research contributes to the advancement of secure and accurate face recognition systems, paving the way for its adoption in various security applications.
New methods of securing the distribution of audio content have been widely deployed in the last twenty years. Their impact on perceptive quality has, however, only been seldomly the subject of recent extensive research. We review digital speech watermarking state of the art and provide subjective testing of watermarked speech samples. Latest speech watermarking techniques are listed, with their specifics and potential for further development. Their current and possible applications are evaluated. Open-source software designed to embed watermarking patterns in audio files is used to produce a set of samples that satisfies the requirements of modern speech-quality subjective assessments. The patchwork algorithm that is coded in the application is mainly considered in this analysis. Different watermark robustness levels are used, which allow determining the threshold of detection to human listeners. The subjective listening tests are conducted following ITU-T P.800 Recommendation, which precisely defines the conditions and requirements for subjective testing. Further analysis tries to determine the effects of noise and various disturbances on watermarked speech's perceived quality. A threshold of intelligibility is estimated to allow further openings on speech compression techniques with watermarking. The impact of language or social background is evaluated through an additional experiment involving two groups of listeners. Results show significant robustness of the watermarking implementation, retaining both a reasonable net subjective audio quality and security attributes, despite mild levels of distortion and noise. Extended experiments with Chinese listeners open the door to formulate a hypothesis on perception variations with geographical and social backgrounds.
- MeSH
- Algorithms MeSH
- Language MeSH
- Data Compression methods MeSH
- Humans MeSH
- Speech Perception MeSH
- Pattern Recognition, Automated methods MeSH
- Telecommunications MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Geographicals
- China MeSH
This paper deals with the vulnerability of machine learning models to adversarial examples and its implication for robustness and generalization properties. We propose an evolutionary algorithm that can generate adversarial examples for any machine learning model in the black-box attack scenario. This way, we can find adversarial examples without access to model's parameters, only by querying the model at hand. We have tested a range of machine learning models including deep and shallow neural networks. Our experiments have shown that the vulnerability to adversarial examples is not only the problem of deep networks, but it spreads through various machine learning architectures. Rather, it depends on the type of computational units. Local units, such as Gaussian kernels, are less vulnerable to adversarial examples.
- Keywords
- Adversarial examples, Genetic algorithms, Kernel methods, Neural networks, Supervised learning,
- MeSH
- Algorithms MeSH
- Humans MeSH
- Neural Networks, Computer * MeSH
- Supervised Machine Learning * trends MeSH
- Pattern Recognition, Automated methods trends MeSH
- Machine Learning trends MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
This article presents a steganographic method StegoNN based on neural networks. The method is able to identify a photomontage from presented signed images. Unlike other academic approaches using neural networks primarily as classifiers, the StegoNN method uses the characteristics of neural networks to create suitable attributes which are then necessary for subsequent detection of modified photographs. This also results in a fact that if an image is signed by this technique, the detection of modifications does not need any external data (database of non-modified originals) and the quality of the signature in various parts of the image also serves to identify modified (corrupted) parts of the image. The experimental study was performed on photographs from CoMoFoD Database and its results were compared with other approaches using this database based on standard metrics. The performed study showed the ability of the StegoNN method to detect corrupted parts of an image and to mark places which have been most probably image-manipulated. The usage of this method is suitable for reportage photography, but in general, for all cases where verification (provability) of authenticity and veracity of the presented image are required.
- Keywords
- CoMoFoD database, Neural network, Photomontage, Steganography, StegoNN,
- MeSH
- Databases, Factual standards MeSH
- Photography methods standards MeSH
- Humans MeSH
- Neural Networks, Computer * MeSH
- Reproducibility of Results MeSH
- Pattern Recognition, Automated methods standards MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
Machine learning (ML) is a growing field that provides tools for automatic pattern recognition. The neuroimaging community currently tries to take advantage of ML in order to develop an auxiliary diagnostic tool for schizophrenia diagnostics. In this letter, we present a classification framework based on features extracted from magnetic resonance imaging (MRI) data using two automatic whole-brain morphometry methods: voxel-based (VBM) and deformation-based morphometry (DBM). The framework employs a random subspace ensemble-based artificial neural network classifier-in particular, a multilayer perceptron (MLP). The framework was tested on data from first-episode schizophrenia patients and healthy controls. The experiments differed in terms of feature extraction methods, using VBM, DBM, and a combination of both morphometry methods. Thus, features of different types were available for model adaptation. As we expected, the combination of features increased the MLP classification accuracy up to 73.12%-an improvement of 5% versus MLP-based only on VBM or DBM features. To further verify the findings, other comparisons using support vector machines in place of MLPs were made within the framework. However, it cannot be concluded that any classifier was better than another.
- MeSH
- Diagnosis, Computer-Assisted methods MeSH
- Humans MeSH
- Magnetic Resonance Imaging * methods MeSH
- Brain diagnostic imaging MeSH
- Neural Networks, Computer * MeSH
- Pattern Recognition, Automated methods MeSH
- Schizophrenia diagnostic imaging MeSH
- Check Tag
- Humans MeSH
- Male MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
We present the ROCA (ROad Curvature Analyst) software, in the form of an ESRI ArcGIS Toolbox, intended for vector line data processing. The software segments road network data into tangents and horizontal curves. Horizontal curve radii and azimuth of tangents are then automatically computed. Simultaneously, additional frequently used road section characteristics are calculated, such as the sinuosity of a road section (detour ratio), the number of turns along an individual road section and the average cumulative angle for a road section. The identification of curves is based on the naïve Bayes classifier and users are allowed to prepare their own training data files. We applied ROCA software to secondary roads within the Czech road network (9,980 km). The data processing took less than ten minutes. Approximately 43% of the road network in question consists of 42,752 horizontal curves. The ROCA software outperforms other existing automatic methods by 26% with respect to the percentage of correctly identified curves. The segmented secondary roads within the Czech road network can be viewed on the roca.cdvgis.cz/czechia web-map application. We combined data on road geometry with road crashes database to develop the crash modification factors for horizontal curves with various radii. We determined that horizontal curves with radii of 50 m are approximately 3.7 times more hazardous than horizontal curves with radii accounting for 1000 m. ROCA software can be freely downloaded for noncommercial use from https://roca.cdvinfo.cz/ website.
- MeSH
- Automobiles standards MeSH
- Safety MeSH
- Accidents, Traffic prevention & control MeSH
- Geographic Information Systems MeSH
- Humans MeSH
- Self-Help Devices * MeSH
- Automobile Driving * standards MeSH
- Rotation * MeSH
- Pattern Recognition, Automated methods MeSH
- Software * standards MeSH
- Environment Design MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
UNLABELLED: The automated detection of arrhythmia in a Holter ECG signal is a challenging task due to its complex clinical content and data quantity. It is also challenging due to the fact that Holter ECG is usually affected by noise. Such noise may be the result of the regular activity of patients using the Holter ECG-partially unplugged electrodes, short-time disconnections due to movement, or disturbances caused by electric devices or infrastructure. Furthermore, regular patient activities such as movement also affect the ECG signals and, in connection with artificial noise, may render the ECG non-readable or may lead to misinterpretation of the ECG. OBJECTIVE: In accordance with the PhysioNet/CinC Challenge 2017, we propose a method for automated classification of 1-lead Holter ECG recordings. APPROACH: The proposed method classifies a tested record into one of four classes-'normal', 'atrial fibrillation', 'other arrhythmia' or 'too noisy to classify'. It uses two machine learning methods in parallel. The first-a bagged tree ensemble (BTE)-processes a set of 43 features based on QRS detection and PQRS morphology. The second-a convolutional neural network connected to a shallow neural network (CNN/NN)-uses ECG filtered by nine different filters (8× envelograms, 1× band-pass). If the output of CNN/NN reaches a specific level of certainty, its output is used. Otherwise, the BTE output is preferred. MAIN RESULTS: The proposed method was trained using a reduced version of the public PhysioNet/CinC Challenge 2017 dataset (8183 records) and remotely tested on the hidden dataset on PhysioNet servers (3658 records). The method achieved F1 test scores of 0.92, 0.82 and 0.74 for normal recordings, atrial fibrillation and recordings containing other arrhythmias, respectively. The overall F1 score measured on the hidden test-set was 0.83. SIGNIFICANCE: This F1 score led to shared rank #2 in the follow-up PhysioNet/CinC Challenge 2017 ranking.
- MeSH
- Diagnosis, Computer-Assisted methods MeSH
- Electrocardiography methods MeSH
- Atrial Fibrillation diagnosis MeSH
- Humans MeSH
- Signal Processing, Computer-Assisted * MeSH
- Pattern Recognition, Automated methods MeSH
- Machine Learning * MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
OBJECTIVE: Nowadays proper detection of cognitive impairment has become a challenge for the scientific community. Alzheimer's Disease (AD), the most common cause of dementia, has a high prevalence that is increasing at a fast pace towards epidemic level. In the not-so-distant future this fact could have a dramatic social and economic impact. In this scenario, an early and accurate diagnosis of AD could help to decrease its effects on patients, relatives and society. Over the last decades there have been useful advances not only in classic assessment techniques, but also in novel non-invasive screening methodologies. METHODS: Among these methods, automatic analysis of speech -one of the first damaged skills in AD patients- is a natural and useful low cost tool for diagnosis. RESULTS: In this paper a non-linear multi-task approach based on automatic speech analysis is presented. Three tasks with different language complexity levels are analyzed, and promising results that encourage a deeper assessment are obtained. Automatic classification was carried out by using classic Multilayer Perceptron (MLP) and Deep Learning by means of Convolutional Neural Networks (CNN) (biologically- inspired variants of MLPs) over the tasks with classic linear features, perceptual features, Castiglioni fractal dimension and Multiscale Permutation Entropy. CONCLUSION: Finally, the most relevant features are selected by means of the non-parametric Mann- Whitney U-test.
- Keywords
- Alzheimer's disease, deep learning, emotion analysis, innovative tools, multi-tasks, speech processing, spontaneous speech,
- MeSH
- Alzheimer Disease diagnosis MeSH
- Early Diagnosis MeSH
- Deep Learning MeSH
- Diagnosis, Computer-Assisted * methods MeSH
- Adult MeSH
- Cognitive Dysfunction diagnosis MeSH
- Cohort Studies MeSH
- Middle Aged MeSH
- Humans MeSH
- Speech Production Measurement MeSH
- Nonlinear Dynamics MeSH
- Neuropsychological Tests MeSH
- Speech * MeSH
- Pattern Recognition, Automated * methods MeSH
- Aged MeSH
- Speech Recognition Software MeSH
- Check Tag
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
Examination of the common carotid artery (CCA) based on an ultrasound video sequence is an effective method for detecting cardiovascular diseases. Here, we propose a video processing method for the automated geometric analysis of CCA transverse sections. By explicitly compensating the parasitic phenomena of global movement and feature drift, our method enables a reliable and accurate estimation of the movement of the arterial wall based on ultrasound sequences of arbitrary length and in situations where state-of-the-art methods fail or are very inaccurate. The method uses a modified Viola-Jones detector and the Hough transform to localize the artery in the image. Then it identifies dominant scatterers, also known as interest points (IPs), whose positions are tracked by means of the pyramidal Lucas-Kanade method. Robustness to global movement and feature drift is achieved by a detection of global movement and subsequent IP re-initialization, as well as an adaptive removal and addition of IPs. The performance of the proposed method is evaluated using simulated and real ultrasound video sequences. Using the Harris detector for IP detection, we obtained an overall root-mean-square error, averaged over all the simulated sequences, of 2.16 ± 1.18 px. The computational complexity of our method is compatible with real-time operation; the runtime is about 30-70 ms/frame for sequences with a spatial resolution of up to 490 × 490 px. We expect that in future clinical practice, our method will be instrumental for non-invasive early-stage diagnosis of atherosclerosis and other cardiovascular diseases.
- Keywords
- Artery, Hough transform, Image processing, Interest point, Lucas–Kanade method, Optical flow, Tracking, Ultrasound, Video processing, Viola–Jones detector,
- MeSH
- Carotid Arteries diagnostic imaging MeSH
- Image Interpretation, Computer-Assisted methods MeSH
- Humans MeSH
- Image Processing, Computer-Assisted methods MeSH
- Reproducibility of Results MeSH
- Pattern Recognition, Automated methods MeSH
- Sensitivity and Specificity MeSH
- Ultrasonography methods MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
One of the biggest problems in automated diagnosis of psychiatric disorders from medical images is the lack of sufficiently large samples for training. Sample size is especially important in the case of highly heterogeneous disorders such as schizophrenia, where machine learning models built on relatively low numbers of subjects may suffer from poor generalizability. Via multicenter studies and consortium initiatives researchers have tried to solve this problem by combining data sets from multiple sites. The necessary sharing of (raw) data is, however, often hindered by legal and ethical issues. Moreover, in the case of very large samples, the computational complexity might become too large. The solution to this problem could be distributed learning. In this paper we investigated the possibility to create a meta-model by combining support vector machines (SVM) classifiers trained on the local datasets, without the need for sharing medical images or any other personal data. Validation was done in a 4-center setup comprising of 480 first-episode schizophrenia patients and healthy controls in total. We built SVM models to separate patients from controls based on three different kinds of imaging features derived from structural MRI scans, and compared models built on the joint multicenter data to the meta-models. The results showed that the combined meta-model had high similarity to the model built on all data pooled together and comparable classification performance on all three imaging features. Both similarity and performance was superior to that of the local models. We conclude that combining models is thus a viable alternative that facilitates data sharing and creating bigger and more informative models.
- Keywords
- Machine learning, classification, combining models, first-episode schizophrenia, meta-model, multi-center, prediction, support vector machines (SVM),
- MeSH
- Datasets as Topic * MeSH
- Humans MeSH
- Magnetic Resonance Imaging MeSH
- Multicenter Studies as Topic * MeSH
- Neuroimaging methods MeSH
- Pattern Recognition, Automated methods MeSH
- Schizophrenia diagnostic imaging MeSH
- Support Vector Machine * MeSH
- Check Tag
- Humans MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
