491 Matching Results

Search Results

Advanced search parameters have been applied.

Recognition using gait.

Description: Gait or an individual's manner of walking, is one approach for recognizing people at a distance. Studies in psychophysics and medicine indicate that humans can recognize people by their gait and have found twenty-four different components to gait that taken together make it a unique signature. Besides not requiring close sensor contact, gait also does not necessarily require a cooperative subject. Using video data of people walking in different scenarios and environmental conditions we develop and test an algorithm that uses shape and motion to identify people from their gait. The algorithm uses dynamic time warping to match stored templates against an unknown sequence of silhouettes extracted from a person walking. While results under similar constraints and conditions are very good, the algorithm quickly degrades with varying conditions such as surface and clothing.
Date: September 1, 2007
Creator: Koch, Mark William
Partner: UNT Libraries Government Documents Department

Optimizing connected component labeling algorithms

Description: This paper presents two new strategies that can be used to greatly improve the speed of connected component labeling algorithms. To assign a label to a new object, most connected component labeling algorithms use a scanning step that examines some of its neighbors. The first strategy exploits the dependencies among them to reduce the number of neighbors examined. When considering 8-connected components in a 2D image, this can reduce the number of neighbors examined from four to one in many cases. The second strategy uses an array to store the equivalence information among the labels. This replaces the pointer based rooted trees used to store the same equivalence information. It reduces the memory required and also produces consecutive final labels. Using an array instead of the pointer based rooted trees speeds up the connected component labeling algorithms by a factor of 5 {approx} 100 in our tests on random binary images.
Date: January 16, 2005
Creator: Wu, Kesheng; Otoo, Ekow & Shoshani, Arie
Partner: UNT Libraries Government Documents Department

ROCIT : a visual object recognition algorithm based on a rank-order coding scheme.

Description: This document describes ROCIT, a neural-inspired object recognition algorithm based on a rank-order coding scheme that uses a light-weight neuron model. ROCIT coarsely simulates a subset of the human ventral visual stream from the retina through the inferior temporal cortex. It was designed to provide an extensible baseline from which to improve the fidelity of the ventral stream model and explore the engineering potential of rank order coding with respect to object recognition. This report describes the baseline algorithm, the model's neural network architecture, the theoretical basis for the approach, and reviews the history of similar implementations. Illustrative results are used to clarify algorithm details. A formal benchmark to the 1998 FERET fafc test shows above average performance, which is encouraging. The report concludes with a brief review of potential algorithmic extensions for obtaining scale and rotational invariance.
Date: June 1, 2004
Creator: Gonzales, Antonio Ignacio; Reeves, Paul C.; Jones, John J. & Farkas, Benjamin D.
Partner: UNT Libraries Government Documents Department

Hierarchical image feature extraction by an irregular pyramid of polygonal partitions

Description: We present an algorithmic framework for hierarchical image segmentation and feature extraction. We build a successive fine-to-coarse hierarchy of irregular polygonal partitions of the original image. This multiscale hierarchy forms the basis for object-oriented image analysis. The framework incorporates the Gestalt principles of visual perception, such as proximity and closure, and exploits spectral and textural similarities of polygonal partitions, while iteratively grouping them until dissimilarity criteria are exceeded. Seed polygons are built upon a triangular mesh composed of irregular sized triangles, whose spatial arrangement is adapted to the image content. This is achieved by building the triangular mesh on the top of detected spectral discontinuities (such as edges), which form a network of constraints for the Delaunay triangulation. The image is then represented as a spatial network in the form of a graph with vertices corresponding to the polygonal partitions and edges reflecting their relations. The iterative agglomeration of partitions into object-oriented segments is formulated as Minimum Spanning Tree (MST) construction. An important characteristic of the approach is that the agglomeration of polygonal partitions is constrained by the detected edges; thus the shapes of agglomerated partitions are more likely to correspond to the outlines of real-world objects. The constructed partitions and their spatial relations are characterized using spectral, textural and structural features based on proximity graphs. The framework allows searching for object-oriented features of interest across multiple levels of details of the built hierarchy and can be generalized to the multi-criteria MST to account for multiple criteria important for an application.
Date: January 1, 2008
Creator: Skurikhin, Alexei N
Partner: UNT Libraries Government Documents Department

Design Molecular Recognition Materials for Chiral Sensors, Separtations and Catalytic Materials

Description: The goal is the development of materials that are highly sensitive and selective for chid chemicals and biochemical (such as insecticides, herbicides, proteins, and nerve agents) to be used as sensors, catalysts and separations membranes. Molecular modeling methods are being used to tailor chiral molecular recognition sites with high affinity and selectivity for specified agents. The work focuses on both silicate and non-silicate materials modified with chirally-pure fictional groups for the catalysis or separations of enantiomerically-pure molecules. Surfactant and quaternary amine templating is being used to synthesize porous frameworks, containing mesopores of 30 to 100 angstroms. Computer molecukw modeling methods are being used in the design of these materials, especially in the chid surface- modi~ing agents. Molecular modeling is also being used to predict the catalytic and separations selectivities of the modified mesoporous materials. The ability to design and synthesize tailored asymmetric molecular recognition sites for sensor coatings allows a broader range of chemicals to be sensed with the desired high sensitivity and selectivity. Initial experiments target the selective sensing of small molecule gases and non-toxic model neural compounds. Further efforts will address designing sensors that greatly extend the variety of resolvable chemical species and forming a predictive, model-based method for developing advanced sensors.
Date: November 1, 1998
Creator: Jia, S.; Nenoff, T.M.; Provencio, P.; Qiu, Y.; Shelnutt, J.A.; Thoma, S.G. et al.
Partner: UNT Libraries Government Documents Department

Analysis of wolves and sheep. Final report

Description: In evaluating speaker verification systems, asymmetries have been observed in the ease with which people are able to break into other people`s voice locks. People who are good at breaking into voice locks are called wolves, and people whose locks are easy to break into are called sheep. (Goats are people that have a difficult time opening their own voice locks.) Analyses of speaker verification algorithms could be used to understand wolf/sheep asymmetries. Using the notion of a ``speaker space``, it is demonstrated that such asymmetries could arise even though the similarity of voice 1 to voice 2 is the same as the inverse similarity. This explains partially the wolf/sheep asymmetries, although there may be other factors. The speaker space can be computed from interspeaker similarity data using multidimensional scaling, and such speaker space can be used to given a good approximation of the interspeaker similarities. The derived speaker space can be used to predict which of the enrolled speakers are likely to be wolves and which are likely to be sheep. However, a speaker must first enroll in the speaker key system and then be compared to each of the other speakers; a good estimate of a person`s speaker space position could be obtained using only a speech sample.
Date: August 1, 1997
Creator: Hogden, J.; Papcun, G.; Zlokarnik, I. & Nix, D.
Partner: UNT Libraries Government Documents Department

Shape from equal thickness contours

Description: A unique imaging modality based on Equal Thickness Contours (ETC) has introduced a new opportunity for 3D shape reconstruction from multiple views. We present a computational framework for representing each view of an object in terms of its object thickness, and then integrating these representations into a 3D surface by algebraic reconstruction. The object thickness is inferred by grouping curve segments that correspond to points of second derivative maxima. At each step of the process, we use some form of regularization to ensure closeness to the original features, as well as neighborhood continuity. We apply our approach to images of a sub-micron crystal structure obtained through a holographic process.
Date: May 10, 1998
Creator: Cong, G. & Parvin, B.
Partner: UNT Libraries Government Documents Department

Practical Cursive Script Recognition

Description: This research focused on the off-line cursive script recognition application. The problem is very large and difficult and there is much room for improvement in every aspect of the problem. Many different aspects of this problem were explored in pursuit of solutions to create a more practical and usable off-line cursive script recognizer than is currently available.
Date: August 1995
Creator: Carroll, Johnny Glen, 1953-
Partner: UNT Libraries

Examining the Relationship between Variability in Acquisition and Variability in Extinction

Description: Using the "revealed operant" technique, variability during acquisition and extinction was examined with measures of response rate and a detailed analysis of response topography. During acquisition, subjects learned to emit four response patterns. A continuous schedule of reinforcement (CRF) for 100 repetitions was used for each pattern and a 30 min extinction phase immediately followed. One group of subjects learned the response patterns via a "trial-and-error" method. This resulted in a wide range of variability during acquisition and extinction. Only one subject emitted a substantial amount of resurgent behavior. A second group of subjects was given instructions on what keys to press to earn reinforcers. This group had less variability in acquisition and extinction and resurgent responding was prevalent.
Date: December 1997
Creator: Neff, Bryon (Bryon R.)
Partner: UNT Libraries

Signal analysis approach to ultrasonic evaluation of diffusion bond quality

Description: Solid state bonds like the diffusion bond are attractive techniques for joining dissimilar materials since they are not prone to the defects that occur with fusion welding. Ultrasonic methods can detect the presence of totally unbonded regions but have difficulty sensing poor bonded areas where the substrates are in intimate contact. Standard ultrasonic imaging is based on amplitude changes in the signal reflected from the bond interface. Unfortunately amplitude alone is not sensitive to bond quality. We demonstrated that there is additional information in the ultrasonic signal that correlates with bond quality. In our approach we interrogated a set of dissimilar diffusion bonded samples with broad band ultrasonic signals. The signals were digitally processed and the characteristics of the signals that corresponded to bond quality were determined. These characteristics or features were processed with pattern recognition algorithms to produce predictions of bond quality. The predicted bond quality was then compared with the destructive measurement to assess the classification capability of the ultrasonic technique
Date: June 8, 1999
Creator: Chinn, D & Thomas, G
Partner: UNT Libraries Government Documents Department

Forensic 3D Scene Reconstruction

Description: Traditionally law enforcement agencies have relied on basic measurement and imaging tools, such as tape measures and cameras, in recording a crime scene. A disadvantage of these methods is that they are slow and cumbersome. The development of a portable system that can rapidly record a crime scene with current camera imaging, 3D geometric surface maps, and contribute quantitative measurements such as accurate relative positioning of crime scene objects, would be an asset to law enforcement agents in collecting and recording significant forensic data. The purpose of this project is to develop a feasible prototype of a fast, accurate, 3D measurement and imaging system that would support law enforcement agents to quickly document and accurately record a crime scene.
Date: October 12, 1999
Partner: UNT Libraries Government Documents Department

Vibration-Based Damage Detection in Rotating Machinery

Description: Damage detection as determined from changes in the vibration characteristics of a system has been a popular research topic for the last thirty years. Numerous damage identification algorithms have been proposed for detecting and locating damage in structural and mechanical systems. To date, these damage-detection methods have shown mixed results. A particular application of vibration-based damage detection that has perhaps enjoyed the greatest success is that of damage detection in rotating machinery. This paper summarizes the state of technology in vibration-based damage detection applied to rotating machinery. The review interprets the damage detection process in terms of a statistical pattern recognition paradigm that encompasses all vibration-based damage detection methods and applications. The motivation for the study reported herein is to identify the reasons that vibration-based damage detection has been successfully applied to rotating machinery, but has yet to show robust applications to civil engineering infrastructure. The paper concludes by comparing and contrasting the vibration-based damage detection applied to rotating machinery with large civil engineering infrastructure applications.
Date: June 28, 1999
Creator: Farrar, C.R. & Duffey, T.A.
Partner: UNT Libraries Government Documents Department

ISIS; An Information-efficient Spectral Imaging System

Description: A specialized hyperspectral imager has been developed that preprocesses the spectra from an image before the light reaches the detectors. This "optical computer" does not allow the flexibility of digital post-processing. However, the processing is done in real time and the system can examine = 2 x 10{sup 6} scene pixels/sec. Therefore, outdoors it could search for pollutants, vegetation types, minerals, or man-made objects. On a high- speed production line it could identify defects in sheet products like plastic wrap or film, or on painted or plastic parts. ISIS is a line scan imager. A spectrally dispersed slit image is projected on a Spatial Light Modulator. The SLM is programmed to take the inner product of the spectral intensity vector and a spectral basis vector. The SLM directs the positive and negative parts of the inner product to different linear detector arrays so the signal difference equals the inner product. We envision a system with one telescope and =4 SLMS.
Date: July 19, 1998
Creator: Boye, C.A.; Descour, M.R.; Gentry, S.M.; Grotbeck, C.L.; Stallard, B.R. & Sweatt, W.C.
Partner: UNT Libraries Government Documents Department

National Society of Black Physicists XXV Annual Day of Scientific Lectures and 21st Annual Meeting - NSBP '98: The Next Generation/12th Annual National Conference of Black Physics Students - NCPBS '98: Physics/Life in Motion

Description: The 12th Annual National Conference of Black Physics Students (NCBPS) was held jointly with the Annual Meeting of the National Society of Black Physicists (NSBP) March 4-8, 1998 in Lexington, Ky. The Proceedings consists of scientific talks and abstracts given by NSBP members and students attending the NCBPS meeting. One joint session of general scientific interest was held, with NCBPS students, NSBP members, and about 75 high school students from the state of Kentucky present. NCBPS session included ''How to get into Graduate School'', ''How to Survive in Graduate School'', and a Panel on ''Opportunities for Physics Graduates.'' The report by AIP: ''Survey of Participants of the 12th Annual NCBPS'' is included in the Proceedings.
Date: February 28, 1999
Creator: MacKellar, Alan (ed.)
Partner: UNT Libraries Government Documents Department

Commissioning of the ATLAS pixel detector

Description: The ATLAS pixel detector is a high precision silicon tracking device located closest to the LHC interaction point. It belongs to the first generation of its kind in a hadron collider experiment. It will provide crucial pattern recognition information and will largely determine the ability of ATLAS to precisely track particle trajectories and find secondary vertices. It was the last detector to be installed in ATLAS in June 2007, has been fully connected and tested in-situ during spring and summer 2008, and is ready for the imminent LHC turn-on. The highlights of the past and future commissioning activities of the ATLAS pixel system are presented.
Date: September 1, 2008
Creator: Collaboration, ATLAS & Golling, Tobias
Partner: UNT Libraries Government Documents Department

Monitoring international nuclear activity

Description: The LBNL Table of Isotopes website provides primary nuclearinformation to>150,000 different users annually. We have developedthe covert technology to identify users by IP address and country todetermine the kinds of nuclear information they are retrieving. Wepropose to develop pattern recognition software to provide an earlywarning system to identify Unusual nuclear activity by country or regionSpecific nuclear/radioactive material interests We have monitored nuclearinformation for over two years and provide this information to the FBIand LLNL. Intelligence is gleaned from the website log files. Thisproposal would expand our reporting capabilities.
Date: May 19, 2006
Creator: Firestone, R. B.
Partner: UNT Libraries Government Documents Department

Implementing Graph Pattern Queries on a Relational Database

Description: When a graph database is implemented on top of a relational database, queries in the graph query language are translated into relational SQL queries. Graph pattern queries are an important feature of a graph query language. Translating graph pattern queries into single SQL statements results in very poor query performance. By taking into account the pattern query structure and generating multiple SQL statements, pattern query performance can be dramatically improved. The performance problems encountered with the single SQL statements generated for pattern queries reflects a problem in the SQL query planner and optimizer. Addressing this problem would allow relational databases to better support semantic graph databases. Relational database systems that provide good support for graph databases may also be more flexible platforms for data warehouses.
Date: December 26, 2007
Creator: Kaplan, I L; Abdulla, G M; Brugger, S T & Kohn, S R
Partner: UNT Libraries Government Documents Department

The application of Tiny Triplet Finder (TTF) in BTeV pixel trigger

Description: We describe a track segment recognition scheme called the Tiny Triplet Finder (TTF) that involves grouping of three hits satisfying a constraint such as forming of a straight line. The TTF performs this O(n{sup 3}) function in O(n) time, where n is number of hits in each detector plane. The word ''tiny'' reflects the fact that the FPGA resource usage is small. The number of logic elements needed for the TTF is O(Nlog(N)), where N is the number of bins in the coordinate considered, which for large N, is significantly smaller than O(N{sup 2}) needed for typical implementations of similar functions. The TTF is also suitable for software implementations as well as many other pattern recognition problems.
Date: March 1, 2006
Creator: Wu, Jin-Yuan; Wang, M.; Gottschalk, E.; Shi, Z. & /Fermilab
Partner: UNT Libraries Government Documents Department

Obstacle detection for autonomous navigation : an LDRD final report.

Description: This report summarizes the analytical and experimental efforts for the Laboratory Directed Research and Development (LDRD) project entitled 'Obstacle Detection for Autonomous Navigation'. The principal goal of this project was to develop a mathematical framework for obstacle detection. The framework provides a basis for solutions to many complex obstacle detection problems critical to successful autonomous navigation. Another goal of this project was to characterize sensing requirements in terms of physical characteristics of obstacles, vehicles, and terrain. For example, a specific vehicle traveling at a specific velocity over a specific terrain requires a sensor with a certain range of detection, resolution, field-of-view, and sufficient sensitivity to specific obstacle characteristics. In some cases, combinations of sensors were required to distinguish between different hazardous obstacles and benign terrain. In our framework, the problem was posed as a multidimensional, multiple-hypothesis, pattern recognition problem. Features were extracted from selected sensors that allow hazardous obstacles to be distinguished from benign terrain and other types of obstacles. Another unique thrust of this project was to characterize different terrain classes with respect to both positive (e.g., rocks, trees, fences) and negative (e.g., holes, ditches, drop-offs) obstacles. The density of various hazards per square kilometer was statistically quantified for different terrain categories (e.g., high desert, ponderosa forest, and prairie). This quantification reflects the scale, or size, and mobility of different types of vehicles. The tradeoffs between obstacle detection, position location, path planning, and vehicle mobility capabilities were also to be characterized.
Date: March 1, 2004
Creator: Padilla, Denise D.
Partner: UNT Libraries Government Documents Department