Blur-resistant joint 1D and 2D barcode localization for smartphones

Abstract

With the proliferation of built-in cameras barcode scanning on smartphones has become widespread in both consumer and enterprise domains. To avoid making the user precisely align the barcode at a dedicated position and angle in the camera image, barcode localization algorithms are necessary that quickly scan the image for possible barcode locations and pass those to the actual barcode decoder. In this paper, we present a barcode localization approach that is orientation, scale, and symbology (1D and 2D) invariant and shows better blur invariance than existing approaches while it operates in real time on a smartphone. Previous approaches focused on selected aspects such as orientation invariance and speed for 1D codes or scale invariance for 2D codes. Our combined method relies on the structure matrix and the saturation from the HSV color system. The comparison with three other real-time barcode localization algorithms shows that our approach outperforms the state of the art with respect to symbology and blur invariance at the expense of a reduced speed.

GPU-accelerated joint 1D and 2D barcode localization on smartphones

“…Version 2.0 of OpenGL ES introduced the programmable graphics pipeline to mobile graphics hardware opening the doors for general purpose GPU computations on smartphones. There are certain limitations though compared to proprietary high-level parallel computing frameworks such as CUDA 3 , OpenCL 4 , or RenderScript 5 because OpenGL was primarily designed for rendering 3D scenes. This means one has to reformulate computing problems as rendering problems and carefully tune the algorithms to graphics features.…”

“…The selected barcode localization algorithm [3] consists of multiple stages that are illustrated in Figure 3. The captured color camera image is first converted to grayscale and the chroma value c = max(R, G, B) − min(R, G, B) of each pixel is also stored separately for later steps.…”

“…Previous approaches can be categorized by their image processing techniques. 1D localization has been presented using simple image filters [1,2,3], orientation histograms [4], line detection [5], morphology operators [6,7], Gabor filters [8], or harmonic analysis [9,10]. 2D localization has been implemented via image thresholding and scanning, via orientation maps, or via combinations of line/corner/square detection [11,12].…”

“…Existing algorithms often have difficulties with defocused or motion-blurred images because blur distorts the barcode structures. The author has recently published [3] a new, combined localization algorithm that addresses orientation, scale, symbology and blur invariance and runs close to real time on a smartphone CPU. This paper presents the implementation steps of the above barcode localization algorithm on the embedded graphics hardware.…”

Localization of Visual Codes in the DCT Domain Using Deep Rectifier Neural Networks

“…Image acquisition techniques and computer hardware have also improved significantly, that made automatic reading of QR codes available. State of the art algorithms [8,9] do not require human presence and assumptions on code orientation, position and coverage rate in the image any longer. However, image quality and acquisition techniques vary considerably and each application has its own requirements for detection speed and accuracy, making the task more complex.…”