SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
In optical pattern recognition system with self-amplification, no reference beam used in addressing mode. Polarization of laser beam and orientation of photorefractive crystal chosen to maximize photorefractive effect. Intensity of recognition signal is orders of magnitude greater than other optical correlators. Apparatus regarded as real-time or quasi-real-time optical pattern recognizer with memory and reprogrammability.
The Magellan data set constitutes an example of the large volumes of data that today's instruments can collect, providing more detail of Venus than was previously available from Pioneer Venus, Venera 15/16, or ground-based radar observations put together. However, data analysis technology has not kept pace with data collection and storage technology. Due to the sheer size of the data, complete and comprehensive scientific analysis of such large volumes of image data is no longer feasible without the use of computational aids. Our progress towards developing a pattern recognition system for aiding in the detection and cataloging of small-scale natural features in large collections of images is reported. Combining classical image processing, machine learning, and a graphical user interface, the detection of the 'small-shield' volcanoes (less than 15km in diameter) that constitute the most abundant visible geologic feature in the more that 30,000 synthetic aperture radar (SAR) images of the surface of Venus are initially targeted. Our eventual goal is to provide a general, trainable tool for locating small-scale features where scientists specify what to look for simply by providing examples and attributes of interest to measure. This contrasts with the traditional approach of developing problem specific programs for detecting Specific patterns. The approach and initial results in the specific context of locating small volcanoes is reported. It is estimated, based on extrapolating from previous studies and knowledge of the underlying geologic processes, that there should be on the order of 10(exp 5) to 10(exp 6) of these volcanoes visible in the Magellan data. Identifying and studying these volcanoes is fundamental to a proper understanding of the geologic evolution of Venus. However, locating and parameterizing them in a manual manner is forbiddingly time-consuming. Hence, the development of techniques to partially automate this task were undertaken. The primary constraints for this particular problem are that the method must be reasonably robust and fast. Unlike most geological features, the small volcanoes of Venus can be ascribed to a basic process that produces features with a short list of readily defined characteristics differing significantly from other surface features on Venus. For pattern recognition purposes the relevant criteria include (1) a circular planimetric outline, (2) known diameter frequency distribution from preliminary studies, (3) a limited number of basic morphological shapes, and (4) the common occurrence of a single, circular summit pit at the center of the edifice.
The purpose of this paper is to describe a HyperCard-based system for performing speech recognition research and to instruct Human Factors professionals on how to use the system to obtain detailed data about the user interface of a prototype speech recognition application.
This report represents the preliminary effort in studying the significance of recognition for innovators of spinoff technologies. The purpose of this initial year's effort in this area was to gather preliminary data and define the direction for the remainder of the research. This report focuses on the most recent recipients of the Hall of Fame Award, the developers of liquid-cooled garments. Liquid-cooled garments technology and its spinoffs were used as a case study to define and explore the factors involved in technology transfer and to consider the possible incentives in developing commercial applications including the Hall of Fame Award. Through interviews, views of award recipients were obtained on factors encouraging spinoffs as well as impediments to spinoffs. The researchers observed complex inter-relationships among the significant entities (government, individuals, large and small business), the importance of people, the importance of resource availability, and the significance of intrinsic motivation; drew preliminary conclusions pertaining to the direct and indirect influence of recognition like the Hall of Fame Award; and planned the direction for next year's follow-on research.
Spoken language is the most convenient and natural means by which people interact with each other and is, therefore, a promising candidate for human-machine interactions. Speech also offers an additional channel for hands-busy applications, complementing the use of motor output channels for control. Current speech recognition systems vary considerably across a number of important characteristics, including vocabulary size, speaking mode, training requirements for new speakers, robustness to acoustic environments, and accuracy. Algorithmically, these systems range from rule-based techniques through more probabilistic or self-learning approaches such as hidden Markov modeling and neural networks. This tutorial begins with a brief summary of the relevant features of current speech recognition systems and the strengths and weaknesses of the various algorithmic approaches.
Since 1989, Martin Marietta has invested in the development of an innovative concept for robust real-time pattern recognition for any two-dimensioanal sensor. This concept has been tested in simulation, and in laboratory and field hardware, for a number of DOD and commercial uses from automatic target recognition to manufacturing inspection. We have now joined Rose Health Care Systems in developing its use for medical diagnostics. The concept is based on determining regions of interest by using optical Fourier bandpassing as a scene segmentation technique, enhancing those regions using wavelet filters, passing the enhanced regions to a neural network for analysis and initial pattern identification, and following this initial identification with confirmation by optical correlation. The optical scene segmentation and pattern confirmation are performed by the same optical module. The neural network is a recursive error minimization network with a small number of connections and nodes that rapidly converges to a global minimum.
The Extravehicular Activity Helper/Retriever (EVAHR) is a robotic device currently under development at the NASA Johnson Space Center that is designed to fetch objects or to assist in retrieving an astronaut who may have become inadvertently de-tethered. The EVAHR will be required to exhibit a high degree of intelligent autonomous operation and will base much of its reasoning upon information obtained from one or more three-dimensional sensors that it will carry and control. At the highest level of visual cognition and reasoning, the EVAHR will be required to detect objects, recognize them, and estimate their spatial orientation and location. The recognition phase and estimation of spatial pose will depend on the ability of the vision system to reliably extract geometric features of the objects such as whether the surface topologies observed are planar or curved and the spatial relationships between the component surfaces. In order to achieve these tasks, three-dimensional sensing of the operational environment and objects in the environment will therefore be essential. One of the sensors being considered to provide image data for object recognition and pose estimation is a phase-shift laser scanner. The characteristics of the data provided by this scanner have been studied and algorithms have been developed for segmenting range images into planar surfaces, extracting basic features such as surface area, and recognizing the object based on the characteristics of extracted features. Also, an approach has been developed for estimating the spatial orientation and location of the recognized object based on orientations of extracted planes and their intersection points. This paper presents some of the algorithms that have been developed for the purpose of recognizing and estimating the pose of objects as viewed by the laser scanner, and characterizes the desirability and utility of these algorithms within the context of the scanner itself, considering data quality and noise.
Acoustic emission (AE) data were acquired during fatigue testing of an aluminum 2024-T4 compact tension specimen using a commercially available AE system. AE signals from crack extension were identified and separated from noise spikes, signals that reflected from the specimen edges, and signals that saturated the instrumentation. A commercially available software package was used to train a statistical pattern recognition system to classify the signals. The software trained a network to recognize signals with a 91-percent accuracy when compared with the researcher's interpretation of the data. Reasons for the discrepancies are examined and it is postulated that additional preprocessing of the AE data to focus on the extensional wave mode and eliminate other effects before training the pattern recognition system will result in increased accuracy.
It is difficult to find definitive evidence for impact in the geological record because there are many endogenous geological processes that can produce diamictites similar to those generated by impact ejecta. The classic impact criteria of shock fabrics in certain minerals, and iridium layers, for example, may be either difficult to find, or long-since erased from the impact site (shock fabrics also anneal with time). It is important to be able to recognize impact-generated materials in order to understand earth's crustal development and biological evolution. In future exploration of Mars and other solar-system bodies, recognition of impact materials will be important for elucidating planetary evolution, planetary volatile inventories, and exobiological issues. The cobble depicted is typical of many that have been found in diamictite deposits in Belize generated by the Chicxulub K-T impact event. The pebbles are roughly-hewn in general shape with smoothed corners and edges. Surfaces are almost uniformly frosted (on both protuberances and hollows), but some asperities are glazed. Optical microscopy and thin-section petrographic microscopy reveal the frosting to be only a few microns thick, with a well-defined granular structure; grains are the same size as those composing the bulk of the limestone, but their clearer appearance may represent annealing. One or two adjacent pebble faces are often decorated with striated gouges and closely-spaced hemispherical depressions representing indentation hollows produced by well-rounded impacting clasts of up to 0.5 cm in diameter. Some of the impactors are still embedded in the cobble surface. Non-destructive x-ray diffraction techniques showed the impactors to be of the same mineralogy as the target cobble. We believe this unusual glazing and frosting to be related to the impact event, but this must be reconciled with its survival for over 60 my. since it is composed of one of the most alterable substances, CaCO3. We focus, however, on the non-fractured rounded pebbles that appear to have impacted the larger cobble as a swarm of clasts, probably encountered during ballistic flight. It cannot be defined whether the cobble swept through the pebble cloud, or the pebbles rained upon a slowermoving cobble. Two interesting questions arise: (1) Where did large numbers of such well rounded pebbles come from in the ejecta curtain?, and (2) How did they embed themselves in a nominally brittle rock without suffering damage? Are the well-rounded pebbles crystalline (devitrified) melt spherules? Further investigations are in progress. If the cobble was cold and brittle, impact of well-rounded pebbles would have produced Hertzian fracture patterns (a) in the virtually elastically isotropic cobble target. For penetration depths of about 0.5 of the impactor diameter, the pebbles would require a relative impact velocity sufficient to cause pebble fragmentation and crushing, and the development of a complex Hertzian-Boussinesq fracture field (b) involving deep fracturing and lateral surface spalling (impact velocities > 50 m/s). The existing relationship could only evolve by the impact of cold, hard pebbles into a soft, plastic cobble surface (c). For limestone to have been plastic, it must have been at elevated temperature, but to prevent calcification of the material, the ambient pressure must also have been elevated. This would be possible either in the impact's gas plume, or within the confines of a thin aerodynamically-produced shock bow generated by supersonic ballistic motion of the cobble. In the latter case, it is implied that the cobble swept through the pebbles rather than vice-versa. Although there are high T-P conditions associated with volcanism, such textures have not been reported on volcaniclastic materials, nor from other high T-P environments; e.g., metamorphic (as far as the authors are aware). We propose that this very easily recognizable embedding and indentation surface texture can be used as a diagnostic criterion for the recognition of impact ejecta. The term "peening texture" is suggested, because it is absolutely analogous to the plastic-deformation induced, metal-surface textures generated by ball-bearing bombardment used in engineering metallurgy to work-harden metal surfaces. Additional information is contained in the original (Figures).
This paper describes an active (real time) recognition strategy whereby information is inferred iteratively across several viewpoints in descent imagery. We will show how we use inverse theory within the context of parametric model generation, namely height and spectral reflection functions, to generate model assertions. Using this strategy in an active context implies that, from every viewpoint, the proposed system must refine its hypotheses taking into account the image and the effect of uncertainties as well. The proposed system employs probabilistic solutions to the problem of iteratively merging information (images) from several viewpoints. This involves feeding the posterior distribution from all previous images as a prior for the next view. Novel approaches will be developed to accelerate the inversion search using novel statistic implementations and reducing the model complexity using foveated vision. Foveated vision refers to imagery where the resolution varies across the image. In this paper, we allow the model to be foveated where the highest resolution region is called the foveation region. Typically, the images will have dynamic control of the location of the foveation region. For descent imagery in the Entry, Descent, and Landing (EDL) process, it is possible to have more than one foveation region. This research initiative is directed towards descent imagery in connection with NASA's EDL applications. Three-Dimensional Model Recognition, Generation, Fusion, Update, and Refinement (RGFUR or RG4) for height and the spectral reflection characteristics are in focus for various reasons, one of which is the prospect that their interpretation will provide for real time active vision for automated EDL.
A new star pattern recognition method is developed using singular value decomposition of a measured unit column vector matrix in a measurement frame and the corresponding cataloged vector matrix in a reference frame. It is shown that singular values and right singular vectors are invariant with respect to coordinate transformation and robust under uncertainty. One advantage of singular value comparison is that a pairing process for individual measured and cataloged stars is not necessary, and the attitude estimation and pattern recognition process are not separated. An associated method for mission catalog design is introduced and simulation results are presented.
Sub-vocal electromyogram/electro palatogram (EMG/EPG) signal classification is demonstrated as a method for silent speech recognition. Recorded electrode signals from the larynx and sublingual areas below the jaw are noise filtered and transformed into features using complex dual quad tree wavelet transforms. Feature sets for six sub-vocally pronounced words are trained using a trust region scaled conjugate gradient neural network. Real time signals for previously unseen patterns are classified into categories suitable for primitive control of graphic objects. Feature construction, recognition accuracy and an approach for extension of the technique to a variety of real world application areas are presented.
The Feature Analyst is a computer program for assisted (partially automated) recognition of targets in images. This program was developed to accelerate the processing of high-resolution satellite image data for incorporation into geographic information systems (GIS). This program creates an advanced user interface that embeds proprietary machine-learning algorithms in commercial image-processing and GIS software. A human analyst provides samples of target features from multiple sets of data, then the software develops a data-fusion model that automatically extracts the remaining features from selected sets of data. The program thus leverages the natural ability of humans to recognize objects in complex scenes, without requiring the user to explain the human visual recognition process by means of lengthy software. Two major subprograms are the reactive agent and the thinking agent. The reactive agent strives to quickly learn the user's tendencies while the user is selecting targets and to increase the user's productivity by immediately suggesting the next set of pixels that the user may wish to select. The thinking agent utilizes all available resources, taking as much time as needed, to produce the most accurate autonomous feature-extraction model possible.
To elucidate the mechanism of interaction of restriction endonuclease EcoRII with DNA, we studied by native gel electrophoresis the binding of this endonuclease to a set of synthetic DNA-duplexes containing the modified or canonical recognition sequence 5'-d(CCA/TGG)-3'. All binding substrate or substrate analogues tested could be divided into two major groups: (i) duplexes that, at the interaction with endonuclease EcoRII, form two types of stable complexes on native gel in the absence of Mg2+ cofactor; (ii) duplexes that form only one type of complex, observed both in the presence and absence of Mg2+. Unlike the latter, duplexes under the first group can be hydrolyzed by endonuclease. Data obtained suggest that the active complex is most likely formed by one protein subunit and one DNA recognition sequence. A model of EcoRII endonuclease action is presented.
Autonomous recognition of scientifically important information provides the capability of: 1) Prioritizing data return; 2) Intelligent data compression; 3) Reactive behavior onboard robotic vehicles. Such capabilities are desirable as mission scenarios include longer durations with decreasing interaction from mission control. To address such issues, we have implemented several computer algorithms, intended to autonomously recognize morphological shapes of scientific interest within a software architecture envisioned for future rover missions. Mars Exploration Rovers (MER) instrument payloads include a Panoramic Camera (PANCAM) and Microscopic Imager (MI). These provide a unique opportunity to evaluate our algorithms when applied to data obtained from the surface of Mars. Early in the mission we applied our algorithms to images available at the mission web site (http://marsrovers.jpl.nasa.gov/gallery/images.html), even though these are not at full resolution. Some algorithms would normally use ancillary information, e.g. camera pointing and position of the sun, but these data were not readily available. The initial results of applying our algorithms to the PANCAM and MI images are encouraging. The horizon is recognized in all images containing it; such information could be used to eliminate unwanted areas from the image prior to data transmission to Earth. Additionally, several rocks were identified that represent targets for the mini-thermal emission spectrometer. Our algorithms also recognize the layers, identified by mission scientists. Such information could be used to prioritize data return or in a decision-making process regarding future rover activities. The spherules seen in MI images were also autonomously recognized. Our results indicate that reliable recognition of scientifically relevant morphologies in images is feasible.
We have prepared phosphorothioate-containing cyclic oligodeoxynucleotides that fold into 'dumbbells' containing CRE and TRE sequences, the binding sequences for the CREB and JUN proteins, respectively. Six phosphorothioate residues were introduced into each of the recognition sequences. K2PtCl4 crosslinks CRE to CREB and TRE to JUN. The extent of crosslinking is about eight times greater than that observed with standard oligodeoxynucleotides and amounts to 30-50% of the efficiency of non-covalent association as estimated by gel-shift assays. Crosslinking is reversed by incubation with NaCN. The crosslinking reaction is specific--a dumbbell oligonucleotide with six phosphorothioate groups introduced into the Sp1 recognition sequence could not be crosslinked efficiently to CREB or JUN proteins with K2PtCl4. The binding of TRE to CREB is not strong enough for effective detection by gel-shift assays, but the TRE-CREB complex is crosslinked efficiently by K2PtCl4 and can then readily be detected.
Optical measurements provide a non-invasive method for measuring deformation of wind tunnel models. Model deformation systems use targets mounted or painted on the surface of the model to identify known positions, and photogrammetric methods are used to calculate 3-D positions of the targets on the model from digital 2-D images. Under ideal conditions, the reflective targets are placed against a dark background and provide high-contrast images, aiding in target recognition. However, glints of light reflecting from the model surface, or reduced contrast caused by light source or model smoothness constraints, can compromise accurate target determination using current algorithmic methods. This paper describes a technique using a neural network and image processing technologies which increases the reliability of target recognition systems. Unlike algorithmic methods, the neural network can be trained to identify the characteristic patterns that distinguish targets from other objects of similar size and appearance and can adapt to changes in lighting and environmental conditions.
As the focus of our present paper, we have used the cascade error projection (CEP) learning algorithm (shown to be hardware-implementable) with on-chip learning (OCL) scheme to obtain three orders of magnitude speed-up in target recognition compared to software-based learning schemes. Thus, it is shown, real time learning as well as data processing for target recognition can be achieved.