A Robust Software Barcode Reader Using the Hough Transform . In this paper we present a method based on the Hough transform which. Published in: · Proceeding. ICIIS ’99 Proceedings of the International Conference on Information Intelligence and Systems. Page March 31 – April A Robust Software Barcode Reader Using the Hough Transform (Englisch). Muniz, R. / Junco, L. / Otero, A. / Institute of Electrical and Electronics Engineers.

Author: Zugal Nikora
Country: Dominican Republic
Language: English (Spanish)
Genre: Automotive
Published (Last): 17 March 2011
Pages: 491
PDF File Size: 9.16 Mb
ePub File Size: 5.73 Mb
ISBN: 945-4-47202-417-6
Downloads: 32728
Price: Free* [*Free Regsitration Required]
Uploader: Faushakar

We extensively tested our algorithm showing improved performance with respect to other state-of-the-art software and algorithms, especially for the most challenging images. It is important to note that our algorithm allows the user to take a shot of the scene without strong constraints on the location or distance of the barcode, as long as the resolution is sufficient for decoding. For instance, in the barcode shown in Fig. Once the barcode has been localized, decoding reaer place.

Implemented on a Nokia N95, the complete reading algorithm is executed in less than 0. The normalized distances can be calculated by dividing the distances between consecutive peaks and valleys by the minimum bar width. In Canny method it uses a filter which is narrow o as possible to provide suppression of high frequency noise and to provide good localization of the edges.

Suppose that the j -th digit takes value k j.

Reading 1-D Barcodes with Mobile Phones Using Deformable Templates

The green stars indicate o Lo Rthe original estimates for the endpoints of the scanline. Plots c — d show in red the sets of parallel lines corresponding to bars 2—4. A third online software, from QualitySoft, was considered by Tekin and Coughlan [ 10 ], but we neglected comparison with it since it gives very poor results. In order to allow other researchers to compare their results against ours, we provide a publicly accessible barcode image data set [ 2 ].


III-B successfully enforces global consistency and, thus, correct decoding green. Applications of hidden Markov models in bar code decoding. Decoding can be performed by simply finding ussing sequence of digits that best explains one or more binarized scanlines. The result is shown on the screen of the phone above the captured picture, in this case We also made the data sets public to allow other researchers to test and compare their methods.

The computational speed of the algorithm depends heavily softwqre the scanline width. Barcode reading needs to be robust to challenging conditions such as blur, noise, low resolution, or low quality camera lenses, all of which are extremely common.

The barcodes printed on commercial products have sizes typically ranging from 2.

The log-likelihood term D can be expressed as. We have presented a new algorithm for barcode decoding localization and reading that can deal with images that are blurred, noisy, and with usung resolution.

This device has autofocus capability, although not all images collected were properly in-focus whether because the focus was on the wrong object or because the focusing algorithm failedand some were affected by motion blur.

Since a web cam is a relatively inexpensive device, and most of the business applications already use computers, the cost of this barcode reader would be very much less than that of available barcode readers. Our model makes the simplifying initial assumption that the digit segments are equally spaced see Eq. zoftware

Reading 1-D Barcodes with Mobile Phones Using Deformable Templates

For each cell V jk tthe negative log-likelihood D t needs to be computed, which requires two additions and two multiplications per sample. Our algorithm is able to decode readet barcode without requiring the user to precisely frame it within the viewfinder. The illumination problem could be overcome by properly illuminating controlling of the light level the barcode image.


The matching of the stripe-to-stripe combinations in the consecutive domains and the value of the probability can be considered as the usinb for checking the consistency. These disadvantages includes that the barcode has to be manually oriented towards the laser beam to get the barcode value, high cost and the harmfulness for the user from the exposure to the laser beam.

Rather than computing the connected components of the thresholded map, we simply select the pixel n 0 that maximizes I s nunder the assumption that the correct blob, i. Each digit represents one symbol as a sequence transorm two spaces and two bars.

In our approach, as indicated in the figure, first original image is converted to edge image. Since a barcode is a set of bars or lines parallel Hough to each other, this method can be used to find the angle of rrobust bars of Transform at ion the barcode. This paper presents a new algorithm for 1-D barcode reading that produces excellent results even for images that are blurred, noisy, and with low resolution. Their method compares favorably with previous approaches although it was only implemented on laser-based barcode scanners.

Author manuscript; available in PMC Jun For the straight lines, the spline tends to introduce robusg ripple effect at the corners.