513 Matching Results

Search Results

Advanced search parameters have been applied.

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

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

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

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

Towards Perceptual Interface for Visualization Navigation of Large Data Sets Using Gesture Recognition with Bezier Curves and Registered 3-D Data

Description: This paper presents a gesture recognition system for visualization navigation. Scientists are interested in developing interactive settings for exploring large data sets in an intuitive environment. The input consists of registered 3-D data. A geometric method using Bezier curves is used for the trajectory analysis and classification of gestures. The hand gesture speed is incorporated into the algorithm to enable correct recognition from trajectories with variations in hand speed. The method is robust and reliable: correct hand identification rate is 99.9% (from 1641 frames), modes of hand movements are correct 95.6% of the time, recognition rate (given the right mode) is 97.9%. An application to gesture-controlled visualization of 3D bioinformatics data is also presented.
Date: March 20, 2003
Creator: Shin, M C; Tsap, L V & Goldgof, D B
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

DNA sequence pattern recognition methods in GRAIL

Description: The goal of the GRAIL project has been to create a comprehensive analysis environment where a host of questions about genes and genome structure can be answered as quickly and accurately as possible. Constructing this system has entailed solving a number of significant technical challenges including: (a) making coding recognition in sequence more sensitive and accurate, (b) compensating for isochore base compositional effects in coding prediction, (c) developing methods to determine which parts of each strand of a long genomic DNA are the coding strand, (d) improving the accuracy of splice site prediction and recognizing non-consensus sites, and (e) recognizing variable regulatory structures such as polymerase II promoters. An additional challenge has been to construct algorithms which compensate for the deleterious effects of insertion or deletion (indel) errors in the coding region recognition process. This paper addresses progress on these technical issues and the current state of sequence feature recognition methods.
Date: December 31, 1995
Creator: Uberbacher, E.C.; Xu, Ying; Shah, M.; Matis, S.; Guan, X. & Mural, R.J.
Partner: UNT Libraries Government Documents Department

Automatic TLI recognition system, programmer`s guide

Description: This report describes the software of an automatic target recognition system (version 14), from a programmer`s point of view. The intent is to provide information that will help people who wish to modify the software. In separate volumes are a general description of the ATR system, Automatic TLI Recognition System, General Description, and a user`s manual, Automatic TLI Recognition System, User`s Guide. 2 refs.
Date: February 1, 1997
Creator: Lassahn, G.D.
Partner: UNT Libraries Government Documents Department

An algorithm for segmenting range imagery

Description: This report describes the technical accomplishments of the FY96 Cross Cutting and Advanced Technology (CC&AT) project at Los Alamos National Laboratory. The project focused on developing algorithms for segmenting range images. The image segmentation algorithm developed during the project is described here. In addition to segmenting range images, the algorithm can fuse multiple range images thereby providing true 3D scene models. The algorithm has been incorporated into the Rapid World Modelling System at Sandia National Laboratory.
Date: March 1, 1997
Creator: Roberts, R. S.
Partner: UNT Libraries Government Documents Department