Feature Detection Techniques Research Articles

Design of Secure ECG-Based Biometric Authentication in Body Area Sensor Networks.

Body area sensor networks (BANs) utilize wireless communicating sensor nodes attached to a human body for convenience, safety, and health applications. Physiological characteristics of the body, such as the heart rate or Electrocardiogram (ECG) signals, are promising means to simplify the setup process and to improve security of BANs. This paper describes the design and implementation steps required to realize an ECG-based authentication protocol to identify sensor nodes attached to the same human body. Therefore, the first part of the paper addresses the design of a body-area sensor system, including the hardware setup, analogue and digital signal processing, and required ECG feature detection techniques. A model-based design flow is applied, and strengths and limitations of each design step are discussed. Real-world measured data originating from the implemented sensor system are then used to set up and parametrize a novel physiological authentication protocol for BANs. The authentication protocol utilizes statistical properties of expected and detected deviations to limit the number of false positive and false negative authentication attempts. The result of the described holistic design effort is the first practical implementation of biometric authentication in BANs that reflects timing and data uncertainties in the physical and cyber parts of the system.

Feature Based Correspondence: A Comparative Study on Image Matching Algorithms

Image matching and recognition are the crux of computer vision and have a major part to play in everyday lives. From industrial robots to surveillance cameras, from autonomous vehicles to medical imaging and from missile guidance to space exploration vehicles computer vision and hence image matching is embedded in our lives. This communication presents a comparative study on the prevalent matching algorithms, addressing their restrictions and providing a criterion to define the level of efficiency likely to be expected from an algorithm. The study includes the feature detection and matching techniques used by these prevalent algorithms to allow a deeper insight. The chief aim of the study is to deliver a source of comprehensive reference for the researchers involved in image matching, regardless of specific applications.

Performance Enhancement of Content based Image Retrieval System by Integration of Suitable Image Features

Background/Objectives: Retrieving visually similar images from image database needs high speed and accuracy. Various text and content based image retrieval techniques are being investigated by the researchers in order to exactly match the image features. Methods/Statistical Analysis: The proposed technique deals with Content Based Image Retrieval (CBIR) system by applying various image feature detection and matching techniques to investigate the retrieving efficiency of the image. The newness in the proposed research is that it extracts image features like texture, color and shape by combining various angular rotation and image segmentation techniques. With the output of the rotation and segmentation algorithm, color histograms, straight line and outline features including vertical, angled and horizontal lines are extracted. Findings: The accuracy and performance related issues listed in the previous works are overcome while the database images grow. The results obtained by the proposed system obviously confirm that Partitioning and rotating of image objects helps in retrieving many numbers of similar images from the database. Conclusion/Improvements: The proposed CBIR method is compared with our previously existed methodologies and found better in the retrieval accuracy. The retrieval time and accuracy are comparatively good than previous works proposed in CBIR system.

A Survey of Autonomous Human Affect Detection Methods for Social Robots Engaged in Natural HRI

In Human-Robot Interactions (HRI), robots should be socially intelligent. They should be able to respond appropriately to human affective and social cues in order to effectively engage in bi-directional communications. Social intelligence would allow a robot to relate to, understand, and interact and share information with people in real-world human-centered environments. This survey paper presents an encompassing review of existing automated affect recognition and classification systems for social robots engaged in various HRI settings. Human-affect detection from facial expressions, body language, voice, and physiological signals are investigated, as well as from a combination of the aforementioned modes. The automated systems are described by their corresponding robotic and HRI applications, the sensors they employ, and the feature detection techniques and affect classification strategies utilized. This paper also discusses pertinent future research directions for promoting the development of socially intelligent robots capable of recognizing, classifying and responding to human affective states during real-time HRI.

A Survey of Feature Base Methods for Human Face Detection

The human face is among the most significant objects in an image or video, it contains many important information and specifications, also is required to be the cause of almost all achievable look variants caused by changes in scale, location, orientation, pose, facial expression, lighting conditions and partial occlusions. It plays a key role in face recognition systems and many other face analysis applications. We focus on the feature based approach because it gave great results on detect the human face. Face feature detection techniques can be mainly divided into two kinds of approaches are Feature base and image base approach. Feature base approach tries to extract features and match it against the knowledge of the facial features. This paper gives the idea about challenging problems in the field of human face analysis and as such, as it has achieved a great attention over the last few years because of its many applications in various domains. Furthermore, several existing face detection approaches are analyzed and discussed and attempt to give the issues regarding key technologies of feature base methods, we had gone direct comparisons of the method's performance are made where possible and the advantages/ disadvantages of different approaches are discussed.

Improved LSB based Steganography Techniques for Color Images in Spatial Domain

This research paper aims to propose a new improved approach for Information Security in RGB Color Images using a Hybrid Feature detection technique; Two Component based Least Significant Bit (LSB) Substitution Technique and Adaptive LSB substitution technique for data hiding. Advanced Encryption Standard (AES) is used to provide Two Tier Security; Random Pixel Embedding imparts resistant to attacks and Hybrid Filtering makes it immune to various disturbances like noise. An image is combination of edge and smooth areas which gives an ample opportunity to hide information in it. The proposed work is direct implementation of the principle that edge areas being high in contrast, color, density and frequency can tolerate more changes in their pixel values than smooth areas, so can be embedded with a large number of secret data while retaining the original characteristics of image. The proposed approach achieved Improved Imperceptibility, Capacity than the various existing techniques along with Better Resistance to various Steganalysis attacks like Histogram Analysis, Chi-Square and RS Analysis as proven experimentally.

HDR imaging for feature tracking in challenging visibility scenes

Purpose – In visual-based applications, lighting conditions have a considerable impact on quality of the acquired images. Extremely low or high illuminated environments are a real issue for a majority of cameras due to limitations in their dynamic range. Indeed, over or under exposure might result in loss of essential information because of pixel saturation or noise. This can be critical in computer vision applications. High dynamic range (HDR) imaging technology is known to improve image rendering in such conditions. The purpose of this paper is to investigate the level of performance that can be achieved for feature detection and tracking operations in images acquired with a HDR image sensor. Design/methodology/approach – In this study, four different feature detection techniques are selected and tracking algorithm is based on the pyramidal implementation of Kanade-Lucas-Tomasi (KLT) feature tracker. Tracking algorithm is run over image sequences acquired with a HDR image sensor and with a high resolution 5 Megapixel image sensor to comparatively assess them. Findings – The authors demonstrate that tracking performance is greatly improved on image sequences acquired with HDR sensor. Number and percentage of finally tracked features are several times higher than what can be achieved with a 5 Megapixel image sensor. Originality/value – The specific interest of this work focuses on the evaluation of tracking persistence of a set of initial detected features over image sequences taken in different scenes. This includes extreme illumination indoor and outdoor environments subject to direct sunlight exposure, backlighting, as well as dim light and dark scenarios.

Automated Detection of Low-Contrast Solar Features Using the Phase-Congruency Algorithm

We propose a new feature-detection technique based on phase-congruency (PC) measurements to automatically recognize or enhance faint features in solar observations, such as off-limb coronal loops and umbral dots. Compared with other feature-detection methods that are based on gradient illuminance and imaging filtering, PC-based measurements are particular efficient for recognizing faint features, which generally have a low-intensity contrast to their surroundings. In the present article, we carry out a PC-based measurement of the local weighted mean phase angle (LWMPA) at each point in an image to indicate or highlight low-contrast features. We first used artificial images to check the detection accuracy and sensitivity to the noise of this approach. Subsequently, we applied this approach to an EUV observation obtained by the Solar Dynamics Observatory/Atmospheric Imaging Assembly to highlight off-limb coronal loops, and a photospheric observation obtained by the Hinode/Solar Optical Telescope to recognize faint dots within the cores of sunspots and pores. The results illustrate that this PC-based measurement of the LWMPA is a robust detection method for faint structures in solar observations.

Motion Tracking, Retrieval and 3D Reconstruction from Video

The work at hand presents a novel data-driven framework for 3D full body human motion reconstruction from uncalibrated monocular video data. To this end, we develop a knowledge base by taking 2D samples of the motion capture library from dierent viewing directions. This allows later steps to handle 2D query videos without any information on the viewing direction. We detect and track features from input video sequences by utilizing low-level image based feature detection techniques like MSER and SURF. This process is stabilized by back projection of high-level 3D prior information obtained from the motion capture library to the image plane. Extraction of suitable feature sets from both, input control signals and motion capture data, enables us to retrieve the best relevant prior poses from the motion capture library by employing fast motion retrieval techniques. Finally, 3D motion sequences are reconstructed by non-linear energy minimization, that takes into account multiple prior terms. Furthermore, we propose a method to estimate camera parameters from input video itself and sampling of motion capture library.

Sparse data analysis strategy for neural spike classification.

Many of the multichannel extracellular recordings of neural activity consist of attempting to sort spikes on the basis of shared characteristics with some feature detection techniques. Then spikes can be sorted into distinct clusters. There are in general two main statistical issues: firstly, spike sorting can result in well-sorted units, but by with no means one can be sure that one is dealing with single units due to the number of neurons adjacent to the recording electrode. Secondly, the waveform dimensionality is reduced in a small subset of discriminating features. This shortening dimension effort was introduced as an aid to visualization and manual clustering, but also to reduce the computational complexity in automatic classification. We introduce a metric based on common neighbourhood to introduce sparsity in the dataset and separate data into more homogeneous subgroups. The approach is particularly well suited for clustering when the individual clusters are elongated (that is nonspherical). In addition it does need not to select the number of clusters, it is very efficient to visualize clusters in a dataset, it is robust to noise, it can handle imbalanced data, and it is fully automatic and deterministic.

Comparative analysis on SIFT features in visible and infrared aerial imaging

This paper addresses an in-depth analysis on the features extracted from both visual and infrared images in characterising natural environments for vision-based airborne navigation problems, in particular, the performance of feature extraction algorithms and matching when variant SIFT feature detection and matching techniques were utilised successfully. The application of both feature extraction and matching methods on various characteristic aerial images were investigated based on the performance metrics including processing time, number of matched features and matching rates without/with RANSAC outlier rejection applied, etc., and relevant discussion and conclusion were given.

Human Identification at a Distance Using Body Shape Information

Shape of human body is unique from one person to another. This paper presents an intelligent system approach for human identification at a distance using human body shape information. The body features used are the head, shoulder, and trunk. Image processing techniques for detection of these body features were developed in this work. Then, the features are recognized using fuzzy logic approach and used as inputs to a recognition system based on a multilayer neural network. The developed system is only applicable for recognizing a person from its frontal view and specifically constrained to male gender to simplify the algorithm. In this research, the accuracy for human identification using the proposed method is 77.5%. Thus, it is proved that human can be identified at a distance using body shape information.

An evolutionary computing frame work toward object extraction from satellite images

Image interpretation domains have witnessed the application of many intelligent methodologies over the past decade; however the effective use of evolutionary computing techniques for feature detection has been less explored. In this paper, we critically analyze the possibility of using cellular neural network for accurate feature detection. Contextual knowledge has been effectively represented by incorporating spectral and spatial aspects using adaptive kernel strategy. Developed methodology has been compared with traditional approaches in an object based context and investigations revealed that considerable success has been achieved with the procedure. Intelligent interpretation, automatic interpolation, and effective contextual representations are the features of the system.

LAPM: a tool for underwater large-area photo-mosaicking

Abstract. This paper presents a new tool for large-area photo-mosaicking (LAPM tool). This tool was developed specifically for the purpose of underwater mosaicking, and it is aimed at providing end-user scientists with an easy and robust way to construct large photo-mosaics from any set of images. It is notably capable of constructing mosaics with an unlimited number of images on any modern computer (minimum 1.30 GHz, 2 GB RAM). The mosaicking process can rely on both feature matching and navigation data. This is complemented by an intuitive graphical user interface, which gives the user the ability to select feature matches between any pair of overlapping images. Finally, mosaic files are given geographic attributes that permit direct import into ArcGIS. So far, the LAPM tool has been successfully used to construct geo-referenced photo-mosaics with photo and video material from several scientific cruises. The largest photo-mosaic contained more than 5000 images for a total area of about 105 000 m2. This is the first article to present and to provide a finished and functional program to construct large geo-referenced photo-mosaics of the seafloor using feature detection and matching techniques. It also presents concrete examples of photo-mosaics produced with the LAPM tool.

Implementation and Evaluation of SIFT Descriptors based Finger-Knuckle-Print Authentication System

Finger-Knuckle-Print (FKP) uses feature detection and matching techniques in its hard core design. It works similar for almost every authentication system. The Scale Invariant Feature Transform (SIFT) is the most reliable feature extraction technique that is used in authentication systems on FKP. The feature descriptors detected by SIFT claim to be capable of distinguishing each and every image in the dataset from one another with the cost involved in its operations. In SIFT based FKP authentication systems, the storage and computational cost will directly depend on the size of the feature descriptors used. Such matching process will directly match these feature descriptors to find an exact match and the descriptors were directly stored in storage media as templates. Hence there is a necessity for storing all the feature descriptors of the enrolled FKP images for future references. The size of these feature descriptors data will be greater than the original FKP image dataset and the performance of the system will rapidly decrease with respect to the increase in enrollment in the database. The proposed work address these issues with FKP based authentication system using SIFT for efficient computation and cost compared with the existing work and proven to be secure and tough resistant for authentication system.

Feature Conjugation for Intensity-Coded LIDAR Point Clouds

AbstractFeature conjugation is a major task in modern-day spatial analysis and contributes to efficient integration across multiple data sets. In this study, an efficient approach that utilizes the intensity information provided in most light detection and ranging (LIDAR) data sets for feature conjugation is proposed. First, a two-dimensional (2D) intensity map is generated based on the original intensity-coded LIDAR observables in three-dimensional (3D) space. The 2D map is further transformed into a regularly sampled image, and an image feature detection technique is subsequently applied to identify point conjugations between a pair of intensity maps. Finally, the paired conjugations in the image space are mapped backward into the LIDAR space, and the object coordinates of the conjugate points can be verified and obtained. Based on the numerical results from a real world case study, it is illustrated that by fully exploring the existing spectral information, a reliable feature conjugation across multipl...

Automatic Eye Detection Using Fast Corner Detector of North East Indian (NEI) Face Images

This paper has focused on automatic detection eye over North-Eastern Indian (NEI) face database, which is recently developed and continually expanding in Biometric Laboratory of Tripura University (A Central University). For this purpose one of the well-known feature detection technique, called Fast Corner detector has been used. Then after image contrast stretching has been applied over the gray scale image to reduce the illumination effect. Finally, Fast Corner detector is applied over this modified image to discard the other detected points over face. To check the efficiency, the automatically detected eye location has been matched with manually detected eye location

Comparison between Different Classification Methods with Application to Skin Cancer

recent years, skin cancer is the most common form of human cancer. It is estimated that over 1 million new cases occur annually. In order to detect skin cancer various methods have been proposed in the past decades. This paper focuses on the development of a skin cancer screening system that can be used in a general practice by non-experts to classify normal from abnormal cases. The development process consists of Feature Detection and Classification Technique. The features are extracted by decomposing images into different frequency sub- bands using wavelet transform. The output of Discrete Wavelet Transform becomes input to the Classification System which classify whether the input image is cancerous or noncancerous. The classification system is based on the application of Probabilistic Neural Network and Clustering Classifier. The Accuracy of the proposed system is calculated using different classification techniques on image database of 80 samples (40 cancerous and 40 non cancerous images).

Comparison among Cognitive Radio Architectures for Spectrum Sensing

Recently, the growing success of new wireless applications and services has led to overcrowded licensed bands, inducing the governmental regulatory agencies to consider more flexible strategies to improve the utilization of the radio spectrum. To this end, cognitive radio represents a promising technology since it allows to exploit the unused radio resources. In this context, the spectrum sensing task is one of the most challenging issues faced by a cognitive radio. It consists of an analysis of the radio environment to detect unused resources which can be exploited by cognitive radios. In this paper, three different cognitive radio architectures, namely, stand-alone single antenna, cooperative and multiple antennas, are proposed for spectrum sensing purposes. These architectures implement a relatively fast and reliable signal processing algorithm, based on a feature detection technique and support vector machines, for identifying the transmissions in a given environment. Such architectures are compared in terms of detection and classification performances for two transmission standards, IEEE 802.11a and IEEE 802.16e. A set of numerical simulations have been carried out in a challenging scenario, and the advantages and disadvantages of the proposed architectures are discussed.

Modeling protein structure at near atomic resolutions with Gorgon

Electron cryo-microscopy (cryo-EM) has played an increasingly important role in elucidating the structure and function of macromolecular assemblies in near native solution conditions. Typically, however, only non-atomic resolution reconstructions have been obtained for these large complexes, necessitating computational tools for integrating and extracting structural details. With recent advances in cryo-EM, maps at near-atomic resolutions have been achieved for several macromolecular assemblies from which models have been manually constructed. In this work, we describe a new interactive modeling toolkit called Gorgon targeted at intermediate to near-atomic resolution density maps (10-3.5 Å), particularly from cryo-EM. Gorgon's de novo modeling procedure couples sequence-based secondary structure prediction with feature detection and geometric modeling techniques to generate initial protein backbone models. Beyond model building, Gorgon is an extensible interactive visualization platform with a variety of computational tools for annotating a wide variety of 3D volumes. Examples from cryo-EM maps of Rotavirus and Rice Dwarf Virus are used to demonstrate its applicability to modeling protein structure.