skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Optical Character Recognition and Two Dimensional Barcode Recognition using the NGSS

 [1];  [1];  [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
DOE Contract Number:
Resource Type:
Resource Relation:
Conference: Institute of Nuclear Materials Management 56th Annual Meeting, Indian Wells, CA, USA, 20150712, 20150716
Country of Publication:
United States

Citation Formats

Stewart, Scott L, Garner, James R, and Younkin, James R. Optical Character Recognition and Two Dimensional Barcode Recognition using the NGSS. United States: N. p., 2015. Web.
Stewart, Scott L, Garner, James R, & Younkin, James R. Optical Character Recognition and Two Dimensional Barcode Recognition using the NGSS. United States.
Stewart, Scott L, Garner, James R, and Younkin, James R. 2015. "Optical Character Recognition and Two Dimensional Barcode Recognition using the NGSS". United States. doi:.
title = {Optical Character Recognition and Two Dimensional Barcode Recognition using the NGSS},
author = {Stewart, Scott L and Garner, James R and Younkin, James R},
abstractNote = {},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2015,
month = 1

Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • The problem of optical character recognition (OCR) of handwritten Arabic has not received a satisfactory solution yet. In this paper, an Arabic OCR algorithm is developed based on Hidden Markov Models (HMMs) combined with the Viterbi algorithm, which results in an improved and more robust recognition of characters at the sub-word level. Integrating the HMMs represents another step of the overall OCR trends being currently researched in the literature. The proposed approach exploits the structure of characters in the Arabic language in addition to their extracted features to achieve improved recognition rates. Useful statistical information of the Arabic language ismore » initially extracted and then used to estimate the probabilistic parameters of the mathematical HMM. A new custom implementation of the HMM is developed in this study, where the transition matrix is built based on the collected large corpus, and the emission matrix is built based on the results obtained via the extracted character features. The recognition process is triggered using the Viterbi algorithm which employs the most probable sequence of sub-words. The model was implemented to recognize the sub-word unit of Arabic text raising the recognition rate from being linked to the worst recognition rate for any character to the overall structure of the Arabic language. Numerical results show that there is a potentially large recognition improvement by using the proposed algorithms.« less
  • Optical processing technology can be applied to a variety of problems in embedded computing. It is particularly well suited for problems involving large two-dimensional arrays of data, for example in correlation based pattern recognition. For large kernel correlations, the parrellelism of optics offers the high throughput necessary to perform the desired correlation or convolution operations in real time. In addition, the latest generation of optical hardware provides the opportunity to construct processors ideally suited to the embedded computer environment because of their potential size, weight, and power consumption advantages over alternative technologies. Using currently available optical devices, one such architecturemore » was constructed which demonstrated the ability to do real-time pattern recognition. The optical processor was able to perform a 2-D correlation of a 64 x 44 pixel reference object with a 256 x 232 pixel input image at standard video rates. This represents an equivalent computation rate of over 10 billion operations per second. Results of the optical processor as well as a discussion of the potential of this technology in the embedded computer enviroment.« less
  • The authors employ Forward Scattering Particle Image Velocimetry (FSPIV) to measure all three components of the velocity of a buoyant polystyrene particle in oil. Unlike conventional particle image velocimetry (PIV) techniques, FSPIV employs coherent or partially coherent back illumination and collects the forward scattered wavefront; additionally, the field-of-view is microscopic. Using FSPIV, it is possible to easily identify the particle`s centroid and to simultaneously obtain the fluid velocity in different planes perpendicular to the viewing direction without changing the collection or imaging optics. The authors have trained a neural network to identify the scattering pattern as function of displacement alongmore » the optical axis (axial defocus) and determine the transverse velocity by tracking the centroid as function of time. They present preliminary results from Mie theory calculations which include the effect of the imaging system. To their knowledge, this is the first work of this kind; preliminary results are encouraging.« less
  • The Cretaceous Cardium Formation, Alberta, Canada, which produces oil and gas from thin stratigraphic traps comprising coastal and offshore shelf sand-ridge deposits, appears as railroad tracks on seismic sections. Ninety-seven seismic lines were examined over a 10,000 km/sup 2/ area. Here, the Cardium is divided into the Cardium Sand and the overlying Cardium Zone, both of which are 15-50 m thick. The Cardium Sand systematically grades eastward from (a) shoreface-strandplain massive sandstones to (b) inner-shelf sandstones encased in shale. The Cardium zone grades eastward from (a) marginal marine/inner-shelf sandstones (< 10 m thick) encased in shale to (b) shelf shales.more » Two major reflection patterns characterize the Cardium Formation. One consists of two high-amplitude reflections spaced 20-30 m apart, and the other consists of a single reflection; further subdivision is possible on the basis of reflection amplitude. Arealy, these patterns correlate with the regional distribution of sediment facies described above. Reflection patterns of 26 1-D seismic models generated from sonic logs correlate with those of the field seismic data thus allowing interpretation of the field data in terms of sedimentary facies. Thickness of the Cardium Zone and number and thickness of sandstone beds in the Zone were found to control seismic reflection patterns. The double reflection pattern occurs where the Cardium Zone is more than 24 m thick and contains shelf sandstone beds encased in shale. A single reflection, generated from the Cardium Sand, occurs where the zone is less than 24 m thick and lacks sandstones. These relationships can be used to detect and map potential sandstone reservoirs on seismic records.« less
  • In this paper we consider the problem of evaluating models for physical defects affecting the optical character recognition (OCR) process. While a number of such models have been proposed, the contention that they produce the desired result is typically argued in an ad hoc and informal way. We introduce a rigorous and more pragmatic definition of when a model is accurate: we say a defect model is validated if the OCR errors induced by the model are effectively indistinguishable from the errors encountered when using real scanned documents. We present two measures to quantify this similarity: the Vector Space methodmore » and the Coin Bias method. The former adapts an approach used in information retrieval, the latter simulates an observer attempting to do better than a {open_quotes}random{close_quotes} guesser. We compare and contrast the two techniques based on experimental data; both seem to work well, suggesting this is an appropriate formalism for the development and evaluation of document image defect models.« less