QR (quick response) Codes are one of the most popular types of two-dimensional (2D) matrix codes currently used in a wide variety of fields. Two-dimensional matrix codes, compared to 1D bar codes, can encode significantly more data in the same area. We have compared algorithms capable of localizing multiple QR Codes in an image using typical finder patterns, which are present in three corners of a QR Code. Finally, we present a novel approach to identify perspective distortion by analyzing the direction of horizontal and vertical edges and by maximizing the standard deviation of horizontal and vertical projections of these edges. This algorithm is computationally efficient, works well for low-resolution images, and is also suited to real-time processing.

QR (Quick Response) codes are one of the most famous types of two-dimensional (2D) matrix barcodes, which are the descendants of well-known 1D barcodes. The mobile robots which move in certain operational space can use information and landmarks from environment for navigation and such information may be provided by QR Codes. We have proposed algorithm, which localizes a QR Code in an image in a few sequential steps. We start with image binarization, then we continue with QR Code localization, where we utilize characteristic Finder Patterns, which are located in three corners of a QR Code, and finally we identify perspective distortion. The presented algorithm is able to deal with a damaged Finder Pattern, works well for low-resolution images and is computationally efficient.

Artificial neural networks can solve various tasks in computer vision, such as image classification, object detection, and general recognition. Our comparative study deals with four types of artificial neural networks—multilayer perceptrons, probabilistic neural networks, radial basis function neural networks, and convolutional neural networks—and investigates their ability to classify 2D matrix codes (Data Matrix codes, QR codes, and Aztec codes) as well as their rotation. The paper presents the basic building blocks of these artificial neural networks and their architecture and compares the classification accuracy of 2D matrix codes under different configurations of these neural networks. A dataset of 3000 synthetic code samples was used to train and test the neural networks. When the neural networks were trained on the full dataset, the convolutional neural network showed its superiority, followed by the RBF neural network and the multilayer perceptron.

We provide a comprehensive and in-depth overview of the various approaches applicable to the recognition of Data Matrix codes in arbitrary images. All presented methods use the typical “L” shaped Finder Pattern to locate the Data Matrix code in the image. Well-known image processing techniques such as edge detection, adaptive thresholding, or connected component labeling are used to identify the Finder Pattern. The recognition rate of the compared methods was tested on a set of images with Data Matrix codes, which is published together with the article. The experimental results show that methods based on adaptive thresholding achieved a better recognition rate than methods based on edge detection.

Data Matrix codes can be a significant factor in increasing productivity and efficiency in production processes. An important point in deploying Data Matrix codes is their recognition and decoding. In this paper is presented a computationally efficient algorithm for locating Data Matrix codes in the images. Image areas that may contain the Data Matrix code are to be identified firstly. To identify these areas, the thresholding, connected components labelling and examining outer bounding-box of the continuous regions is used. Subsequently, to determine the boundaries of the Data Matrix code more precisely, we work with the difference of adjacent projections around the Finder Pattern. The dimensions of the Data Matrix code are determined by analyzing the local extremes around the Timing Pattern. We verified the proposed method on a testing set of synthetic and real scene images and compared it with the results of other open-source and commercial solutions. The proposed method has achieved better results than competitive commercial solutions.

Data Matrix codes belong to the group of 2-D bar codes, which are widely used in marking the products in storing, production, distribution and sales processes. Their compact matrix structure enables to store big amount of information in a very small area compared to conventional 1-D bar codes. In following paper we compare several methods for detection of Data Matrix codes in images. When locating the position of the code we start from typical bordering of Data Matrix code - which forms “L” so called Finder Pattern and to it the parallel dotting so called Timing Pattern. On the first stage we try to locate Finder Pattern using the edge detection or adaptive thresholding, then continuing with connecting the points into the continuous regions, we are searching for the regions, which could represent the Finder Pattern. On the second stage we verify Timing Pattern where the number of crossing between the background and foreground must be even.