We present a novel approach to edge detection in barcode signals using a hidden Markov model (HMM). We also present an algorithm for selection of an optimal filter scale used in smoothing the data. Experimental resul...
详细信息
We present a novel approach to edge detection in barcode signals using a hidden Markov model (HMM). We also present an algorithm for selection of an optimal filter scale used in smoothing the data. Experimental results show that the proposed HMM is superior in performance compared with existing algorithms in commercial scanners. (c) 2006 Elsevier B.V. All rights reserved.
The ubiquitous supermarket checkout scanner is indeed a well engineered and effective device, There is, nevertheless, demand for better devices. Existing scanners rely on simple and indeed low-cost signal processing t...
详细信息
The ubiquitous supermarket checkout scanner is indeed a well engineered and effective device, There is, nevertheless, demand for better devices. Existing scanners rely on simple and indeed low-cost signal processing to interpret barcode signals, These methods, nevertheless, fundamentally limit label reading and cannot be extended, A new method based on the deterministic EM algorithm Is described here, First results show a substantial improvement in label reading depth of field, which is an important performance parameter for barcode readers.
作者：
Kresic-Juric, SUniv Split
Div Math Fac Elect Engn Mech Engn & Naval Architecture Split 21000 Croatia
Accurate edge localization is of primary importance in bar code decoding. In this paper we investigate statistical properties of edge localization error when a barcode signal is corrupted by additive noise which is a...
详细信息
Accurate edge localization is of primary importance in bar code decoding. In this paper we investigate statistical properties of edge localization error when a barcode signal is corrupted by additive noise which is a weakly stationary random process. We derive a first order approximation for the expected value and standard deviation of the error in terms of the power spectral density (PSD) of the noise. This result is used to estimate the edge localization error caused by speckle noise. We show that the standard deviation of the error is determined by the intensity distribution of a scanning beam and the positions of neighboring edges. We discuss how the error analysis determines the detection rates of a scanning system, and how it can be used in the system design. Analytical examples are provided for UPCA barcode symbols and a scanning beam with Gaussian distribution. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
We investigate the problem of decoding a barcode from a signal measured with a hand-held laser-based scanner. Rather than formulating the inverse problem as one of binary image reconstruction, we instead incorporate ...
详细信息
We investigate the problem of decoding a barcode from a signal measured with a hand-held laser-based scanner. Rather than formulating the inverse problem as one of binary image reconstruction, we instead incorporate the symbology of the barcode into the reconstruction algorithm directly, and search for a sparse representation of the Universal Product codebarcode with respect to this known dictionary. Our approach significantly reduces the degrees of freedom in the problem, allowing for accurate reconstruction that is robust to noise and unknown parameters in the scanning device. We propose a greedy reconstruction algorithm and provide robust reconstruction guarantees. Numerical examples illustrate the insensitivity of our symbology-based reconstruction to both imprecise model parameters and noise on the scanned measurements.
暂无评论