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: Kagacage Mashicage
Country: Trinidad & Tobago
Language: English (Spanish)
Genre: Marketing
Published (Last): 7 December 2008
Pages: 255
PDF File Size: 9.30 Mb
ePub File Size: 20.5 Mb
ISBN: 462-1-37574-301-1
Downloads: 85024
Price: Free* [*Free Regsitration Required]
Uploader: Dogul

The computation of the likelihood in Eq. We propose a simple and fast algorithm for localization that assumes that the bars are approximately vertical.

Surprisingly, even state-of-the-art barcode reading algorithms fail when some of these factors come into play. These approaches report high accuracy, but unfortunately do not present comparative tests nor make their data sets public. One important contribution of this work is to derive an algorithm to compute this integral exactly and in affordable computing time.

We then compute the total likelihood p k I by averaging p k I ow over such density:.

For example, when the scanline width is equal to pixels, then 25 cells are generated. In order to compute the likelihood of an observed scanline for given symbol, it is necessary to take the uncertainty about o and w into consideration. A possible strategy could be to search for the deformation parameters that maximize the likelihood, i.

Plots c — d show in red the sets of parallel lines corresponding to bars 2—4. Table 2 shows a part of houfh probabilities with the different normalized distances ranges. Although this algorithm relies on the assumption that the bars of the barcode are approximately vertical in the image, our studies show that the map I e n can be segmented even when this assumption is not satisfied.

Note how blur and low resolution affect the intensity profile. IV-A, would be computationally intensive. Hough Graph for the Edge Image Figure Decoding can be performed on one or more scanlines.


The localization method is based on detecting the areas with the maximum density difference in two normal reaedr. Robust recognition of 1-D barcodes using camera phones. Tekin E, Coughlan J.

Reading 1-D Barcodes with Mobile Phones Using Deformable Templates

It should be noted that there is an inherent problem with splines when representing straight lines. The choice of an incorrect value of usig due to single-digit analysis is likely to result in a supported segment that does not fit well together with the other segments see Fig.

However, in the case of a high resolution image of a barcode at a short distance, producing a scanline width of pixels, cells are generated. It is reqder of three functions: Note that block filtering can be implemented efficiently so that only few operations per pixel are required. Intuitively, if o 1w 1 and o 2w 2 fall within the same cell of plot athe conditional likelihoods p 2 I o 1w 1 and p 2 I o 2w 2 are identical.

We now describe in detail each of the steps of this procedure. Next, we show how to compute the terms in this sum. The size of the filter was chosen based on the range of the size of the input images and the minimum size of the barcode readable by our method. Commercial laser-based, hand-held barcode scanners achieve robust reading with a reasonable price tag.

Original Image Figure 9: Few cellphones have a flash and, therefore, motion blur and noise can be expected with low ambient light. The lateral guard bars are sided by a space of width equal to at least 9 reaader the base width quiet zonealthough this requirement is sometimes violated in real-world instances.

Barcode decoding Our decoding algorithm analyzes a single scanline extracted from the detected barcode area as described in Sec.

The localization algorithm is used to provide a single scanline segment together with its endpoints as the input to our reader. Hhe are proposing a real-time and autonomous system for the practical use. First the barcode region trnasform localized from a cluttered background, using a combination of gradient and morphological operators. A sample readre images correctly decoded by our algorithm is shown in Fig. This operation is facilitated by the fact that a barcode is bordered to the side by a quiet white area whose size is prescribed by the standard.

  ISA 62443 PDF

For each cell V jk tthe negative log-likelihood D t needs to be computed, which requires two additions and two multiplications per sample. In order to assess the performance of the system, we tested it on a variety of images.

Reading 1-D Barcodes with Mobile Phones Using Deformable Templates

Recall sofyware localization comprises two steps: A toolkit for bar-code recognition and resolving on camera houg starting the internet of things. In order to account for inaccuracy in the localization of the spatial extent of each digit, we allow these templates tobust shift and scale in the horizontal direction.

In addition, we propose an optimization procedure to enforce spatial coherence of the individual digits found by deformable template matching. Finally the barcode can be localized as shown in the figure 2. 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.

We also characterize the performance of the localization algorithm in terms of its accuracy. III-B successfully enforces global consistency and, thus, correct decoding green. The same can be said for edge extraction.

Imposing spatial coherence Our model makes the simplifying initial assumption that the digit segments are equally spaced see Eq. In the recent past several techniques and algorithms have been proposed for vision-based barcode reading.

Unfortunately, we could find only one barcode image database for comparative assessment 1. This method showed an improvement of over a factor of three, of the frame rate.