QR Code Recognition based on Principal Components Analysis Method

Abstract

Abstract-QR (Quick Response) code recognition systems (based on computer vision) have always been challenging to be accurately devised due to two main constraints: (1) QR code recognition system must be able to localize QR codes from an acquired image even in case of unfavorable conditions (illumination variations, perspective distortions) and (2) The system must be adapted to embedded system platforms in terms of processing complexity and resources requirement. Most of the earlier proposed QR code recognition systems implemented complex feature descriptors such as (Harris features, Hough transform which aim at extracting QR code pattern features and subsequently estimating their positions. This process is reinforced by pattern classifiers e.g. (Random forests, SVM) which are used to remove false detected patterns. Those approaches are very computationally expensive. Thus, they are not able to be run in real-time systems.In this paper, a streamlined QR code recognition approach is proposed to be efficiently operable in systems characterized by a limited performance. The evoked approach is conducted as follows: the captured image is segmented in order to reduce searching space and extract the regions of interest. Afterwards a horizontal and vertical scans are performed to localize preliminarily QR code patterns, followed by Principal Component Analysis (PCA) method which allows removing false positives. Thereafter, the remaining patterns are assembled according to a constraint so as to localize the corresponding QR codes. Experimental results show that the incorporation of PCA decreases notably the processing time and increase QR code recognition accuracy (96%).

QR Code Patterns Localization based on Hu Invariant Moments

“…The provided characteristics of the proposed technique meet notably our needs, since it allows representing each pattern by only seven coefficients (which are unchangeable under rotation, scale change and translation) instead of its original structure (whole pattern image). The incorporation of the discussed technique has decreased dramatically the processing time, the limitations that we envisaged previously in our earlier proposed papers [5], [6] have been outperformed. A throughout overview of the proposed system is shown in Fig.…”

“…These features are then used to feed Support Vector Machine (SVM) classifiers, which indeed allow filtering out the false detected QRC patterns. Likewise, in [6] we used the well-known statistical procedure named Principal Components Analysis (PCA). The latter has been used to convert the pattern image to a set of correlated coefficients.…”

Barcode Recognition Using Principal Component Analysis and Support Vector Machine

“…Barcode are utilised by packaging products to store production code, identity number, and company license [1]. Nowadays, barcode recognition technology is not only for labeling an item but also developed in many application such as identification [2], tracking [3], inventory of goods [4] and others. Some commonly barcode used are Code 128, Code 39, UPC, EAN etc [1] Basically, the method used to read barcode is scanline that works by scanning barcode lines using utilising laser light [2].…”

“…PCA analysed the feature of each QR-code characteristics component to distinguish identical image. The method of distinguishing is measured using the entire QR-Code position and angle to identification [3], Noce et al used mobile devices with Hough transform algorithms to detect barcode areas with average detection time of 270 seconds [10] Based on the reserch that has been done by Asraf et al [7], the classification problem was a problem that often encountered in daily life, which is to determine an object whether a type of particular object or not. Based on the problem, this research aims to build a barcode classification method using Support Vector Machine (SVM) with Principal Component Analysis (PCA) feature extraction.…”

“…PCA is a dimensional reduction technique for simplifying data by transforming data linearly to form small dimensionless data that does not correlate each other without losing the data characteristics. PCA works by finding the principal component value by calculating eigenvalues and eigenvectors of the covariance matrix by performing Eigen Value Decomposition (EVD) [3]. The general PCA method is known as the Karhunen-Loven method, which attempts projection from the high dimensional image space to the characteristic space with lower dimensions.…”