Cardiovascular diseases are the number one cause of death worldwide. Currently, portable batteryoperated systems such as mobile phones with wireless ECG sensors have the potential to be used in continuous cardiac function assessment that can be easily integrated into daily life. These portable point-of-care diagnostic systems can therefore help unveil and treat cardiovascular diseases. The basis for ECG analysis is a robust detection of the prominent QRS complex, as well as other ECG signal characteristics. However, it is not clear from the literature which ECG analysis algorithms are suited for an implementation on a mobile device. We investigate current QRS detection algorithms based on three assessment criteria: 1) robustness to noise, 2) parameter choice, and 3) numerical eciency, in order to target a universal fast-robust detector. Furthermore, existing QRS detection algorithms may provide an acceptable solution only on small segments of ECG signals, within a certain amplitude range, or amid particular types of arrhythmia and/or noise. These issues are discussed in the context of a comparison with the most conventional algorithms, followed by future recommendations for developing reliable QRS detection schemes suitable for implementation on battery-operated mobile devices.

/pdf/revisiting-qrs-detection-methodologies-for-portable-wearable-37qan10upr.pdf

Revisiting QRS detection methodologies for portable, wearable, battery-operated, and wireless ECG systems

Cardiovascular diseases are the number one cause of death worldwide. Currently, portable battery-operated systems such as mobile phones with wireless ECG sensors have the potential to be used in continuous cardiac function assessment that can be easily integrated into daily life. These portable point-of-care diagnostic systems can therefore help unveil and treat cardiovascular diseases. The basis for ECG analysis is a robust detection of the prominent QRS complex, as well as other ECG signal characteristics. However, it is not clear from the literature which ECG analysis algorithms are suited for an implementation on a mobile device. We investigate current QRS detection algorithms based on three assessment criteria: 1) robustness to noise, 2) parameter choice, and 3) numerical efficiency, in order to target a universal fast-robust detector. Furthermore, existing QRS detection algorithms may provide an acceptable solution only on small segments of ECG signals, within a certain amplitude range, or amid particular types of arrhythmia and/or noise. These issues are discussed in the context of a comparison with the most conventional algorithms, followed by future recommendations for developing reliable QRS detection schemes suitable for implementation on battery-operated mobile devices.

/pdf/revisiting-qrs-detection-methodologies-for-portable-wearable-1zu9zzg9yx.pdf

Revisiting QRS detection methodologies for portable, wearable, battery-operated, and wireless ECG systems.

Over the last decade, it has become well-established that a captcha's ability to withstand automated solving lies in the difficulty of segmenting the image into individual characters. The standard approach to solving captchas automatically has been a sequential process wherein a segmentation algorithm splits the image into segments that contain individual characters, followed by a character recognition step that uses machine learning. While this approach has been effective against particular captcha schemes, its generality is limited by the segmentation step, which is hand-crafted to defeat the distortion at hand. No general algorithm is known for the character collapsing anti-segmentation technique used by most prominent real world captcha schemes.

This paper introduces a novel approach to solving captchas in a single step that uses machine learning to attack the segmentation and the recognition problems simultaneously. Performing both operations jointly allows our algorithm to exploit information and context that is not available when they are done sequentially. At the same time, it removes the need for any hand-crafted component, making our approach generalize to new captcha schemes where the previous approach can not. We were able to solve all the real world captcha schemes we evaluated accurately enough to consider the scheme insecure in practice, including Yahoo (5.33%) and ReCaptcha (33.34%), without any adjustments to the algorithm or its parameters. Our success against the Baidu (38.68%) and CNN (51.09%) schemes that use occluding lines as well as character collapsing leads us to believe that our approach is able to defeat occluding lines in an equally general manner. The effectiveness and universality of our results suggests that combining segmentation and recognition is the next evolution of catpcha solving, and that it supersedes the sequential approach used in earlier works. More generally, our approach raises questions about how to develop sufficiently secure captchas in the future.

/pdf/the-end-is-nigh-generic-solving-of-text-based-captchas-3w55ws65ax.pdf

The end is nigh: generic solving of text-based CAPTCHAs

Since their inception, captchas have been widely used for preventing fraudsters from performing illicit actions. Nevertheless, economic incentives have resulted in an arms race, where fraudsters develop automated solvers and, in turn, captcha services tweak their design to break the solvers. Recent work, however, presented a generic attack that can be applied to any text-based captcha scheme. Fittingly, Google recently unveiled the latest version of reCaptcha. The goal of their new system is twofold, to minimize the effort for legitimate users, while requiring tasks that are more challenging to computers than text recognition. ReCaptcha is driven by an "advanced risk analysis system" that evaluates requests and selects the difficulty of the captcha that will be returned. Users may be required to click in a checkbox, or solve a challenge by identifying images with similar content. In this paper, we conduct a comprehensive study of reCaptcha, and explore how the risk analysis process is influenced by each aspect of the request. Through extensive experimentation, we identify flaws that allow adversaries to effortlessly influence the risk analysis, bypass restrictions, and deploy large-scale attacks. Subsequently, we design a novel low-cost attack that leverages deep learning technologies for the semantic annotation of images. Our system is extremely effective, automatically solving 70.78% of the image reCaptcha challenges, while requiring only 19 seconds per challenge. We also apply our attack to the Facebook image captcha and achieve an accuracy of 83.5%. Based on our experimental findings, we propose a series of safeguards and modifications for impacting the scalability and accuracy of our attacks. Overall, while our study focuses on reCaptcha, our findings have wide implications, as the semantic information conveyed via images is increasingly within the realm of automated reasoning, the future of captchas relies on the exploration of novel directions.

/pdf/i-am-robot-deep-learning-to-break-semantic-image-captchas-tms7xcg6qx.pdf

I am Robot: (Deep) Learning to Break Semantic Image CAPTCHAs

We introduce a method for using deep neural networks to amortize the cost of inference in models from the family induced by universal probabilistic programming languages, establishing a framework that combines the strengths of probabilistic programming and deep learning methods. We call what we do "compilation of inference" because our method transforms a denotational specification of an inference problem in the form of a probabilistic program written in a universal programming language into a trained neural network denoted in a neural network specification language. When at test time this neural network is fed observational data and executed, it performs approximate inference in the original model specified by the probabilistic program. Our training objective and learning procedure are designed to allow the trained neural network to be used as a proposal distribution in a sequential importance sampling inference engine. We illustrate our method on mixture models and Captcha solving and show significant speedups in the efficiency of inference.

Inference Compilation and Universal Probabilistic Programming

Breaking text-based CAPTCHAs with variable word and character orientation

In this paper we present a novel approach for automatic segmentation and recognition of reCAPTCHA in Web sites. It is based on CAPTCHA image preprocessing with character alignment, morphological segmentation with three-color bar character encoding and heuristic recognition. The original proposal consists in exploiting three-color bar code for characters in CAPTCHA for their robust segmentation with presence of random collapse overlapping letters and distortions by particular patterns of waving rotation. Additionally, a novel implementation of SVM-based learning classifier for recognition of combinations of characters in training corpus has been proposed that permits to increment more than twice the recognition success rate without time extension of system response. The main goal of this research is to reduce vulnerability of CAPTCHA from spam and frauds as well as to provide a novel approach for recognizing either handwritten or degraded and damaged texts in ancient manuscripts. Our designed framework implementing the proposed approach has been tested in real-time applications with sites used CAPTCHAS achieving segmentation success rate about of 82% and recognition success rate about of 94%.

/pdf/breaking-recaptchas-with-unpredictable-collapse-heuristic-34a9waqgcu.pdf

Breaking reCAPTCHAs with unpredictable collapse: heuristic character segmentation and recognition

Real-time facial expression recognition using local appearance-based descriptors

In this paper we present a novel approach for automatic annotation of objects or regions in images based on their color and texture. According to the proposed generalized architecture for automatic generation of image content descriptions the detected regions are labeled by developed cascade SVM-based classifier mapping them to structure that reflects their hierarchical and spatial relation used by text generation engine. For testing the designed system for automatic image annotation around 2,000 images with outdoor-indoor scenes from standard IAPR-TC12 image dataset have been processed obtaining an average precision of classification about 75 % with 94 % of recall. The precision of classification based on color features has been improved up to 15 ± 5 % after extension of classifier with texture detector based on Gabor filter. The proposed approach has a good compromise between classification precision of regions in images and speed despite used considerable time processing taking up to 1 s per image. The approach may be used as a tool for efficient automatic image understanding and description.

Automatic Image Annotation for Description of Urban and Outdoor Scenes

A novel framework on cell phone for recollecting, processing and interpretation of patient’s electrocardiograms ECG as part of development of health care and assisted living environments is presented in this paper. The proposed architecture and algorithm provide continuous detection of the QRS complex during real time ECG monitoring and interaction between doctor and patient expanding coverage of medical services. The developed procedure for heart activity monitoring uses a set of filters for image noise reduction and computes ECG signal gradient for identification of the components with the greatest slope. To highlight the steepest parts of ECG, the absolute value of gradient is averaged over a moving window of 80 ms considered as the minimum duration of QRS complex. In the decision phase, a peak detector is applied. The height of detected peaks is compared to the threshold determined as the signal-to-noise ratio for final definition of heart rate. The designed prototype has been tested using standard MIT-BIH Arrhythmia Database and evaluated confirming that system has good compromise between high transmission and processing speed and satisfactory accuracy, which does not fall below the precision of commercial equipment for heart monitoring.

Claudia Cruz-Perez

Papers

Breaking text-based CAPTCHAs with variable word and character orientation

Breaking reCAPTCHAs with unpredictable collapse: heuristic character segmentation and recognition

Real-time facial expression recognition using local appearance-based descriptors

Automatic Image Annotation for Description of Urban and Outdoor Scenes

Real-Time System for Monitoring and Analyzing Electrocardiogram on Cell Phone