Reading Barcodes with Cameras
Can you tell the sequence of widths of the bars in this barcode?

Example of successfull decoding
Our algorithm can!

Project Synopsis
Reading barcodes with standard cameras, such as cellphone cameras, enables interesting opportunities for ubiquitous computing. Unfortunately, current camera-based barcode readers do not work well when the image has low resolution, is out of focus, or is blurred due to motion. One main reason for this poor performance is that virtually all existing algorithms perform some sort of binarization, either by gray scale thresholding or by finding the bar edges. We propose a new approach to barcode reading that never needs to binarize the image. Instead, we use deformable barcode digit models in a maximum likelihood setting. We show that the particular nature of these models enables efficient integration over the space of deformations. Global optimization over all digits is then performed using dynamic programming.

O. Gallo and R. Manduchi, Image-based barcode reader, patent pending, 2011.

Additional material:

This research was founded by NIH grant 1 R21 EY017003-01A1.


    author = {Orazio Gallo and Roberto Manduchi},
    title = {Reading 1-D Barcodes with Mobile Phones Using Deformable Templates},
    journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year = {2011},

    title = {Reading Challenging Barcodes with Cameras},
    author = {Gallo, O., and Manduchi, R.},
    journal = {IEEE Workshop on Applications of Computer Vision},
    year = {2009},
    month = {December}
last updated 08-14-2013