Fast Fourier Transform

For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.

/pdf/fusion-of-smartphone-motion-sensors-for-physical-activity-4xdnlyv3ro.pdf

Fusion of smartphone motion sensors for physical activity recognition.

https://www.gc.cuny.edu/CUNY_GC/media/Computer-Science/Student%20Presentations/Xing%20Su/Second_Exam_Slides_Xing_Su_6-12-2014.pdf

Activity recognition with smartphone sensors

Face Recognition.- Super-Resolved Faces for Improved Face Recognition from Surveillance Video.- Face Detection Based on Multi-Block LBP Representation.- Color Face Tensor Factorization and Slicing for Illumination-Robust Recognition.- Robust Real-Time Face Detection Using Face Certainty Map.- Poster I.- Motion Compensation for Face Recognition Based on Active Differential Imaging.- Face Recognition with Local Gabor Textons.- Speaker Verification with Adaptive Spectral Subband Centroids.- Similarity Rank Correlation for Face Recognition Under Unenrolled Pose.- Feature Correlation Filter for Face Recognition.- Face Recognition by Discriminant Analysis with Gabor Tensor Representation.- Fingerprint Enhancement Based on Discrete Cosine Transform.- Biometric Template Classification: A Case Study in Iris Textures.- Protecting Biometric Templates with Image Watermarking Techniques.- Factorial Hidden Markov Models for Gait Recognition.- A Robust Fingerprint Matching Approach: Growing and Fusing of Local Structures.- Automatic Facial Pose Determination of 3D Range Data for Face Model and Expression Identification.- SVDD-Based Illumination Compensation for Face Recognition.- Keypoint Identification and Feature-Based 3D Face Recognition.- Fusion of Near Infrared Face and Iris Biometrics.- Multi-Eigenspace Learning for Video-Based Face Recognition.- Error-Rate Based Biometrics Fusion.- Online Text-Independent Writer Identification Based on Stroke's Probability Distribution Function.- Arm Swing Identification Method with Template Update for Long Term Stability.- Walker Recognition Without Gait Cycle Estimation.- Comparison of Compression Algorithms' Impact on Iris Recognition Accuracy.- Standardization of Face Image Sample Quality.- Blinking-Based Live Face Detection Using Conditional Random Fields.- Singular Points Analysis in Fingerprints Based on Topological Structure and Orientation Field.- Robust 3D Face Recognition from Expression Categorisation.- Fingerprint Recognition Based on Combined Features.- MQI Based Face Recognition Under Uneven Illumination.- Learning Kernel Subspace Classifier.- A New Approach to Fake Finger Detection Based on Skin Elasticity Analysis.- An Algorithm for Biometric Authentication Based on the Model of Non-Stationary Random Processes.- Identity Verification by Using Handprint.- Reducing the Effect of Noise on Human Contour in Gait Recognition.- Partitioning Gait Cycles Adaptive to Fluctuating Periods and Bad Silhouettes.- Repudiation Detection in Handwritten Documents.- A New Forgery Scenario Based on Regaining Dynamics of Signature.- Curvewise DET Confidence Regions and Pointwise EER Confidence Intervals Using Radial Sweep Methodology.- Bayesian Hill-Climbing Attack and Its Application to Signature Verification.- Wolf Attack Probability: A New Security Measure in Biometric Authentication Systems.- Evaluating the Biometric Sample Quality of Handwritten Signatures.- Outdoor Face Recognition Using Enhanced Near Infrared Imaging.- Latent Identity Variables: Biometric Matching Without Explicit Identity Estimation.- Poster II.- 2^N Discretisation of BioPhasor in Cancellable Biometrics.- Probabilistic Random Projections and Speaker Verification.- On Improving Interoperability of Fingerprint Recognition Using Resolution Compensation Based on Sensor Evaluation.- Demographic Classification with Local Binary Patterns.- Distance Measures for Gabor Jets-Based Face Authentication: A Comparative Evaluation.- Fingerprint Matching with an Evolutionary Approach.- Stability Analysis of Constrained Nonlinear Phase Portrait Models of Fingerprint Orientation Images.- Effectiveness of Pen Pressure, Azimuth, and Altitude Features for Online Signature Verification.- Tracking and Recognition of Multiple Faces at Distances.- Face Matching Between Near Infrared and Visible Light Images.- User Classification for Keystroke Dynamics Authentication.- Statistical Texture Analysis-Based Approach for Fake Iris Detection Using Support Vector Machines.- A Novel Null Space-Based Kernel Discriminant Analysis for Face Recognition.- Changeable Face Representations Suitable for Human Recognition.- "3D Face": Biometric Template Protection for 3D Face Recognition.- Quantitative Evaluation of Normalization Techniques of Matching Scores in Multimodal Biometric Systems.- Keystroke Dynamics in a General Setting.- A New Approach to Signature-Based Authentication.- Biometric Fuzzy Extractors Made Practical: A Proposal Based on FingerCodes.- On the Use of Log-Likelihood Ratio Based Model-Specific Score Normalisation in Biometric Authentication.- Predicting Biometric Authentication System Performance Across Different Application Conditions: A Bootstrap Enhanced Parametric Approach.- Selection of Distinguish Points for Class Distribution Preserving Transform for Biometric Template Protection.- Minimizing Spatial Deformation Method for Online Signature Matching.- Pan-Tilt-Zoom Based Iris Image Capturing System for Unconstrained User Environments at a Distance.- Fingerprint Matching with Minutiae Quality Score.- Uniprojective Features for Gait Recognition.- Cascade MR-ASM for Locating Facial Feature Points.- Reconstructing a Whole Face Image from a Partially Damaged or Occluded Image by Multiple Matching.- Robust Hiding of Fingerprint-Biometric Data into Audio Signals.- Correlation-Based Fingerprint Matching with Orientation Field Alignment.- Vitality Detection from Fingerprint Images: A Critical Survey.- Optimum Detection of Multiplicative-Multibit Watermarking for Fingerprint Images.- Fake Finger Detection Based on Thin-Plate Spline Distortion Model.- Robust Extraction of Secret Bits from Minutiae.- Fuzzy Extractors for Minutiae-Based Fingerprint Authentication.- Coarse Iris Classification by Learned Visual Dictionary.- Nonlinear Iris Deformation Correction Based on Gaussian Model.- Shape Analysis of Stroma for Iris Recognition.- Biometric Key Binding: Fuzzy Vault Based on Iris Images.- Multi-scale Local Binary Pattern Histograms for Face Recognition.- Histogram Equalization in SVM Multimodal Person Verification.- Learning Multi-scale Block Local Binary Patterns for Face Recognition.- Horizontal and Vertical 2DPCA Based Discriminant Analysis for Face Verification Using the FRGC Version 2 Database.- Video-Based Face Tracking and Recognition on Updating Twin GMMs.- Poster III.- Fast Algorithm for Iris Detection.- Pyramid Based Interpolation for Face-Video Playback in Audio Visual Recognition.- Face Authentication with Salient Local Features and Static Bayesian Network.- Fake Finger Detection by Finger Color Change Analysis.- Feeling Is Believing: A Secure Template Exchange Protocol.- SVM-Based Selection of Colour Space Experts for Face Authentication.- An Efficient Iris Coding Based on Gauss-Laguerre Wavelets.- Hardening Fingerprint Fuzzy Vault Using Password.- GPU Accelerated 3D Face Registration / Recognition.- Frontal Face Synthesis Based on Multiple Pose-Variant Images for Face Recognition.- Optimal Decision Fusion for a Face Verification System.- Robust 3D Head Tracking and Its Applications.- Multiple Faces Tracking Using Motion Prediction and IPCA in Particle Filters.- An Improved Iris Recognition System Using Feature Extraction Based on Wavelet Maxima Moment Invariants.- Color-Based Iris Verification.- Real-Time Face Detection and Recognition on LEGO Mindstorms NXT Robot.- Speaker and Digit Recognition by Audio-Visual Lip Biometrics.- Modelling Combined Handwriting and Speech Modalities.- A Palmprint Cryptosystem.- On Some Performance Indices for Biometric Identification System.- Automatic Online Signature Verification Using HMMs with User-Dependent Structure.- A Complete Fisher Discriminant Analysis for Based Image Matrix and Its Application to Face Biometrics.- SVM Speaker Verification Using Session Variability Modelling and GMM Supervectors.- 3D Model-Based Face Recognition in Video.- Robust Point-Based Feature Fingerprint Segmentation Algorithm.- Automatic Fingerprints Image Generation Using Evolutionary Algorithm.- Audio Visual Person Authentication by Multiple Nearest Neighbor Classifiers.- Improving Classification with Class-Independent Quality Measures: Q-stack in Face Verification.- Biometric Hashing Based on Genetic Selection and Its Application to On-Line Signatures.- Biometrics Based on Multispectral Skin Texture.- Application of New Qualitative Voicing Time-Frequency Features for Speaker Recognition.- Palmprint Recognition Based on Directional Features and Graph Matching.- Tongue-Print: A Novel Biometrics Pattern.- Embedded Palmprint Recognition System on Mobile Devices.- Template Co-update in Multimodal Biometric Systems.- Continual Retraining of Keystroke Dynamics Based Authenticator.

Advances in biometrics : International Conference, ICB 2007 Seoul, Korea, August 27-29, 2007 : proceedings

A range of applications, from predicting the spread of human and electronic viruses to city planning and resource management in mobile communications, depend on our ability to foresee the whereabouts and mobility of individuals, raising a fundamental question: To what degree is human behavior predictable? Here we explore the limits of predictability in human dynamics by studying the mobility patterns of anonymized mobile phone users. By measuring the entropy of each individual's trajectory, we find a 93% potential predictability in user mobility across the whole user base. Despite the significant differences in the travel patterns, we find a remarkable lack of variability in predictability, which is largely independent of the distance users cover on a regular basis.

http://absimage.aps.org/image/MAR10/MWS_MAR10-2009-007155.pdf

Limits of predictability in human mobility

Mobile devices are becoming increasingly sophisticated. These devices are inherently sensors for collection and communication of textual and voice signals. In a broader sense, the latest generation of smart cell phones incorporates many diverse and powerful sensors such as GPS (Global Positioning Systems) sensors, vision sensors (i.e., cameras), audio sensors (i.e., microphones), light sensors, temperature sensors, direction sensors (i.e., magnetic compasses), and acceleration sensors (i.e., accelerometers). The availability of these sensors in mass-marketed communication devices creates exciting new opportunities for data mining and data mining applications. So, it is not surprising that modern mobile devices, particularly cell phones of last generations that work on different mobile operating systems, got equipped with quite sensitive sensors. This paper is devoted to one approach that solves human activity classification problem with help of a mobile device carried by user. Current method is based on K-Nearest Neighbor algorithm (K-NN). Using the magnitude of the accelerometer data and K-NN algorithm we could identify general activities performed by user.

/pdf/activity-recognition-using-k-nearest-neighbor-algorithm-on-1by1zs0aub.pdf

Activity recognition using k-nearest neighbor algorithm on smartphone with tri-axial accelerometer

Endoscopy is a minimally invasive medical diagnostic procedure, which is used for observing the surfaces of organs inside human body. The surfaces usually contain specular reflections from distributing light sources, which are visible in endoscopic images and videos. For many computer vision algorithms the highlights created by specular reflections may become significant source of error. In this paper, we propose: (a) a method for segmentation of highlights based on adoptive colour thresholding and contour analyses and (b) a powerful inpainting method, which fill the highlighted regions with information propagated from adjacent areas. The inpainting algorithm conceals the specular reflections with high accuracy and provides visually pleasurable appearance of endoscopic images and videos. The methods are compared with related approaches reported for processing of endoscopic images and the efficiency is demonstrated on large set of endoscopic images.

/pdf/automatic-detection-and-concealment-of-specular-reflections-4u9mxtk65k.pdf

Automatic detection and concealment of specular reflections for endoscopic images

Mobile phone technology continuously evolves and incorporates more and more sensors for enabling advanced applications. The availability of these sensors in mass-market communication devices creates exciting new opportunities for data mining applications. Particularly healthcare applications exploiting build-in sensors are very promising. These devices open wide range of opportunities of using their potential in different branches like healthcare, financing and so on. Current paper introduces an approach which allows recognizing activity, performed by human, using smartphone acceleration and positioning sensors. We introduce an approach that retrieves signal data and stores it SQLite portable mobile database. It uses asynchronous model of signal retrieving and storing procedures. After the signals were collected we applied noise reduction, time and frequency domain feature extraction processes for stored information and acquired high-dimensional feature patterns. These patterns were later transferred on remote server instead of raw signals. The classification stage was based on “learning with teacher” method. Incoming signal sequences were collected from sensors of mobile device and were analyzed using support vector machines (SVM) learning method.

/pdf/accelerometer-and-gps-sensor-combination-based-system-for-38b2qhhr6l.pdf

Accelerometer and GPS sensor combination based system for human activity recognition

Cell phones and other mobile devices become part of human culture and change activity and lifestyle patterns. Mobile
phone technology continuously evolves and incorporates more and more sensors for enabling advanced applications.
Latest generations of smart phones incorporate GPS and WLAN location finding modules, vision cameras, microphones,
accelerometers, temperature sensors etc. The availability of these sensors in mass-market communication devices creates
exciting new opportunities for data mining applications. Particularly healthcare applications exploiting build-in sensors
are very promising. This paper reviews different approaches of human activity recognition.

Human Movement Activity Classification Approaches that use Wearable Sensors and Mobile Devices

Automated caption generation for digital images is one of the fundamental problems in artificial intelligence. Most of the existing works use Long Short-Term Memory as a recurrent neural network cell to solve this task. After training, their deep neural models can generate an image caption. But there is an issue, the next predicted word of the caption depends mainly on the last predicted word, rather than the image content. In this paper we present model that can automatically generate an image description and is based on a recurrent neural network with modified LSTM cell with an additional gate responsible for image features. This modification results in generation of more accurate captions. We have trained and tested our model on MSCOCO image dataset by using only images and their captions.

Hakob Sarukhanyan

Papers

Activity recognition using k-nearest neighbor algorithm on smartphone with tri-axial accelerometer

Automatic detection and concealment of specular reflections for endoscopic images

Accelerometer and GPS sensor combination based system for human activity recognition

Human Movement Activity Classification Approaches that use Wearable Sensors and Mobile Devices

Short-term memory with read-only unit in neural image caption generator