Barcode Decoding Research Articles

Vision System for Reading Serial Numbers of Hard Disk Drive Slider Bar and Barcode on Its Fixture

Part traceability is one of the inevitable requirements in most modern manufacturing processes. In a hard disk drive (HDD), magnetic head dictates the performance of read/write operations. A number of manufacturing processes are involved to transform a wafer disc to slider bars and finally gliding sliders of the head. In this work, we concentrate on reading serial numbers of slider bar and its attached fixture prior to a bar-lapping process. Since the serial numbers on a bar are in the scale of 18x30 microns and their reflectance nature is rather poor, special optics and lighting components are required. As nature of high optical magnification with limited depth of focus (DOF), conventional image acquisition system can not cover the bar attachment position variation due to wide tolerance of the slider bar fixture. We proposed a serial number reading system using autofocus module to cope with it. Liquid lens and image processing algorithms are introduced to evaluate and adjust the focus automatically. Since our system has to be augmented to an existing machine, footprint is also another main concern. We therefore designed a special rig so the system meets all the fore-mentioned requirements. The system was tested in the production line and had 98% and 90% accuracy for serial number and barcode decoding, respectively. The main cause of barcode reading inaccuracy was from many cycles of the fixture reuse and cleaning in the production line.

Bar Code Decoding in a Camera-Based Scanner: Analysis and Algorithm

The goal of this work is to provide a foundational understanding of the resolution requirement for camera-based bar code scanning systems and to develop an effective algorithm for decoding. The main theoretical question we wish to address is how well resolved must the bar code image be for the system to be able to decode it. To facilitate the analysis we consider the UPC bar code, which is widely used in retail and commerce. We further assume that the pixels of the camera are aligned with the bar code, making the problem one-dimensional. We find that if the narrowest bar in the bar code is larger than two-thirds the size of the camera pixel, it is possible to uniquely determine the encoded message in the bar code. The result, which exploits the symbology of the UPC bar code, shows that under-resolved bar code images can be decoded. To further gain insight into the robustness of the decoding process, we perform numerical experiments.

Pheniqs 2.0: accurate, high-performance Bayesian decoding and confidence estimation for combinatorial barcode indexing

BackgroundSystems biology increasingly relies on deep sequencing with combinatorial index tags to associate biological sequences with their sample, cell, or molecule of origin. Accurate data interpretation depends on the ability to classify sequences based on correct decoding of these combinatorial barcodes. The probability of correct decoding is influenced by both sequence quality and the number and arrangement of barcodes. The rising complexity of experimental designs calls for a probability model that accounts for both sequencing errors and random noise, generalizes to multiple combinatorial tags, and can handle any barcoding scheme. The needs for reproducibility and community benchmark standards demand a peer-reviewed tool that preserves decoding quality scores and provides tunable control over classification confidence that balances precision and recall. Moreover, continuous improvements in sequencing throughput require a fast, parallelized and scalable implementation.Results and discussionWe developed a flexible, robustly engineered software that performs probabilistic decoding and supports arbitrarily complex barcoding designs. Pheniqs computes the full posterior decoding error probability of observed barcodes by consulting basecalling quality scores and prior distributions, and reports sequences and confidence scores in Sequence Alignment/Map (SAM) fields. The product of posteriors for multiple independent barcodes provides an overall confidence score for each read. Pheniqs achieves greater accuracy than minimum edit distance or simple maximum likelihood estimation, and it scales linearly with core count to enable the classification of > 11 billion reads in 1 h 15 m using < 50 megabytes of memory. Pheniqs has been in production use for seven years in our genomics core facility.ConclusionWe introduce a computationally efficient software that implements both probabilistic and minimum distance decoders and show that decoding barcodes using posterior probabilities is more accurate than available methods. Pheniqs allows fine-tuning of decoding sensitivity using intuitive confidence thresholds and is extensible with alternative decoders and new error models. Any arbitrary arrangement of barcodes is easily configured, enabling computation of combinatorial confidence scores for any barcoding strategy. An optimized multithreaded implementation assures that Pheniqs is faster and scales better with complex barcode sets than existing tools. Support for POSIX streams and multiple sequencing formats enables easy integration with automated analysis pipelines.

Quantum-Enhanced Barcode Decoding and Pattern Recognition

Quantum hypothesis testing is one of the most fundamental problems in quantum information theory, with crucial implications in areas like quantum sensing, where it has been used to prove quantum advantage in a series of binary photonic protocols, e.g., for target detection or memory cell readout. In this work, we generalize this theoretical model to the multi-partite setting of barcode decoding and pattern recognition. We start by defining a digital image as an array or grid of pixels, each pixel corresponding to an ensemble of quantum channels. Specializing each pixel to a black and white alphabet, we naturally define an optical model of barcode. In this scenario, we show that the use of quantum entangled sources, combined with suitable measurements and data processing, greatly outperforms classical coherent-state strategies for the tasks of barcode data decoding and classification of black and white patterns. Moreover, introducing relevant bounds, we show that the problem of pattern recognition is significantly simpler than barcode decoding, as long as the minimum Hamming distance between images from different classes is large enough. Finally, we theoretically demonstrate the advantage of using quantum sensors for pattern recognition with the nearest neighbor classifier, a supervised learning algorithm, and numerically verify this prediction for handwritten digit classification.

The Bee-Identification Error Exponent With Absentee Bees

The “bee-identification problem” was formally defined by Tandon, Tan and Varshney [ IEEE Trans. Commun. , vol. 67, 2019], and the error exponent was studied. This work extends the results for the “absentee bees” scenario, where a fraction of the bees are absent in the beehive image used for identification. For this setting, we present an exact characterization of the bee-identification error exponent, and show that independent barcode decoding is optimal, i.e., joint decoding of the bee barcodes does not result in a better error exponent relative to independent decoding of each noisy barcode. This is in contrast to the result without absentee bees, where joint barcode decoding results in a significantly higher error exponent than independent barcode decoding. We also define and characterize the ‘capacity’ for the bee-identification problem with absentee bees, and prove a strong converse for the same.

Tiny-BDN: An Efficient and Compact Barcode Detection Network

This paper presents a novel approach for accurate barcodes detection in real and challenging environments using compact deep neural networks. Our approach is based on Convolutional Neural Network (CNN) and neural network compression, which can detect the four vertexes coordinates of a barcode accurately and quickly. Our approach consists of four stages: (i) feature extraction by a base network, (ii) region proposal network (RPN) training, (iii) barcode classification and coordinates regression, and (iv) weights pruning and recoding. The model is trained in the first three stages and then compressed in the fourth stage to reduce the size of the trained model. In order to remove the effect of geometric distortion during barcode decoding, we add a distortion removal module to the end of the trained model. In experiments, we validate our approach on a challenging large-scale dataset. Compared with previous methods, our method can locate the coordinates of a barcode accurately and quickly and enhance decoding rate through distortion removal. In addition, the storage and memory overheads of our model are reduced through model compression, which shows great potential in industrial applications.

Fine localization and distortion resistant detection of multi-class barcode in complex environments

Barcode, including one-dimensional (1D) barcode and two-dimensional (2D) barcode, can be seen almost anywhere in our lives. In many barcode-based mobile systems, different barcodes will appear simultaneously with different angles, shapes, and image quality. Barcode localization is a significant prerequisite for barcode decoding in these applications. In this paper, we propose a region-based end-to-end network to finely localize and classify 1D barcode and Quick Response (QR) code in complex environments. Two special layers are designed in our network. One is a quadrilateral regression layer to localize arbitrary quadrilateral bounding boxes, and another is a Multi-scale Spatial Pyramid Pooling (MSPP) layer to improve the detection accuracy of small-scale barcodes. Extensive experiments on existing public datasets and our own dataset have verified the effectiveness of proposed layers. We also demonstrate that our method can resist some distortions by simulating barcode images of different image qualities. What’s more, a human decoding experiment is also performed to prove the effectiveness of our method as a preprocessor for QR code decoding.

The Bee-Identification Problem: Bounds on the Error Exponent

Consider the problem of identifying a massive number of bees, uniquely labeled with barcodes, using noisy measurements. We formally introduce this “bee-identification problem”, define its error exponent, and derive efficiently computable upper and lower bounds for this exponent. We show that joint decoding of barcodes provides a significantly better exponent compared to separate decoding followed by permutation inference. For low rates, we prove that the lower bound on the bee-identification exponent obtained using typical random codes (TRC) is strictly better than the corresponding bound obtained using a random code ensemble (RCE). Further, as the rate approaches zero, we prove that the upper bound on the bee-identification exponent meets the lower bound obtained using TRC with joint barcode decoding.

Abstract 3523: A high-throughput screening strategy for the identification of novel lymphoproliferative elements

Abstract Introduction - Chimeric Antigen Receptor (CAR) T-cell therapy is effective against certain leukemias and lymphomas and shows promise for other incurable malignancies. Considerable challenges remain however to expand this platform technology beyond transplant-oriented hospital care. Centralized manufacturing of genetically modified T cells, lymphodepleting chemotherapy and patient management of current CAR-T therapies are associated with significant costs and treatment complexity. As a first step to reduce this treatment complexity, the present study describes a high throughput combinatorial domain library screening method to identify synthetic lymphoproliferative elements capable of driving in vivo expansion and survival of CAR-T cells in a lymphoreplete host without the homeostatic proliferation signals generated by lymphodepleting chemotherapy. Methods - High-diversity semi-rationally-designed combinatorial libraries of putative lymphoproliferative protein subdomains were DNA barcoded and assembled into a lentiviral vector co-expressing a ROR2-targeted CAR. Human PBMC were transduced with the library and cultured in vitro for several days. Purified cells were injected into mice bearing xenograft tumors modified to express the ROR2 antigen and compared to unmodified xenograft controls. The expansion rate of integrated cells was monitored weekly by quantitative PCR and, after 21 days of exposure, genomic DNA was isolated from blood, spleen and xenograft tumor tissues. Enriched barcodes were amplified using PCR and amplicons were subjected to HiSeq Next-Generation Sequencing. Barcode decoding was achieved using PacBio long read sequencing analysis to align full-length construct sequences with barcode quantitation. Results - Using this approach, putative CAR-T cell driver candidates and common key protein subdomains were identified that support selective in vivo expansion and survival of human lymphocytes in a tumor-bearing mouse model. Conclusion - Taken together, these results demonstrate that a high throughput combinatorial screening strategy with quantitative bioinformatics is a viable method for identifying protein domain combinations capable of selectively driving human CAR-T cells in vivo. These small synthetic combinatorial protein domains may facilitate lymphodepleting chemotherapy-free regimens and lower CAR-T cell doses in the future. Citation Format: Laurence Jadin, Hiba Shaban, Anirban Kundu, Gregory Schreiber, Scooter Willis, Farzad Haerizadeh, James Onuffer, Gregory Frost. A high-throughput screening strategy for the identification of novel lymphoproliferative elements [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 3523.

A Blind Restoration Approach for Defocused Barcode Images

Use of a mobile camera for barcode decoding provides high portability and availability but it requires that the recorded barcode image must be accurate representation of the barcode that is available on the product. Barcode scanning is challenging because images may be degraded due to out-of-focus blur at the time of image acquisition. Therefore, image restoration is essential in making image sharp and useful. In case of blind restoration of such barcode images accurate estimation of out-of-focus blur parameter is highly desirable. In this article, a robust method has been proposed for estimating the radius of out-of-focus blur. Finite discrete ridgelet transform has been used to find the features of the blurred image and a radial basis function neural network is utilized to estimate the radius of out-of-focus blur. The experimental results reveal that proposed method more robust than the existing methods.

QR Code Authentication with Embedded Message Authentication Code

Quick Response (QR) code is widely used nowadays but its authenticity is an open issue. Attackers can easily replace the original barcode by a modified one which is generated through the standard encoder. This paper proposes to embed the authentication data such as message authentication code and cryptographic signature for QR code authentication. The scheme utilizes the redundancy of the error correction codewords to store the authentication data while still maintaining the default error correction capability. The stego barcode can be decoded by common users with a standard barcode decoder. The embedded data can be extracted with the knowledge of the barcode structure and the embedding process. The authenticity of the QR codes can then be verified off-line by the authorized user as and when needed. In our experiment, 100 % of the embedded data and encoded information can be retrieved correctly in the decodable barcodes with the off-the-shelf cameras. Security analysis shows that the proposed scheme is secure against attacks in tampering the barcode content. Compared with the existing data hiding scheme, the proposed method has much higher embedding capacity under the same error correction level.

Barcode Localization and Decoding using a Modified ScanLine Approach for Industrial Nameplate Verification

Increased Automation in the manufacturing sector with the introduction of low cost embedded systems and servo drives has resulted in a substantial increase in the precision and speed of packaged goods output. This increase in speed has rendered manual verification incapable to keep up. Recent developments in the area of computer vision and embedded computing has allowed for replacement of traditional human verification by machine vision systems. This study aims to implement a robust solution for Barcode Localization and Decoding for an affordable, reliable and industrial solution for a general purpose automated product verification system. General Terms Algorithms, Pattern Recognition, Barcode Localization, Barcode Decoding, Nameplate.

Farm and environment information bidirectional acquisition system with individual tree identification using smartphones for orchard precision management

An orchard precision management system plays an important role in improvement at the management level and the enhancement of decision abilities. A single orchard tree or an orchard tree microcommunity is the basic management unit, and bidirectional information on the environment and plants is the important content for precision management. A type of RFID label was applied with a UHF chip in the core and a QR code in the surface for single tree identification. A bidirectional acquisition system for orchard production, which included farming information collection for the forward direction and environmental information acquisition for the backward direction, was designed with smart phones. In the farming information collection part, information collection flow that included QR code image acquisition, image preprocessing, barcode decoding and farming information collection was established. An improved local threshold method was adopted to improve the QR code identification rate in the smart phone platform. In the environment information acquisition part, a sensor search rule on the single tree position and a multi-point environment value model were designed. The orchard information bidirectional acquisition system was developed on an Android platform with the Java language, which has the function of QR decoding, farm record information collection, environment information acquisition, data uploading and statistical analysis. The system was tested in an apple orchard. A total of 144 trees were chosen to decode the QR codes in the tree label. The success rate was approximately 96.52%. The identification time of 85% of the trees was less than 4s for the 20 chosen trees. In taking the temperature, for example, the difference between the computed temperature value and the measured temperature value around each tree was small. The system could decrease the cost of the professional equipment, such as portable RFID readers and writers, which was a low-cost and high-efficiency solution for orchard production information collection.

Magnetofluidic platform for multidimensional magnetic and optical barcoding of droplets.

We present a concept of multidimensional magnetic and optical barcoding of droplets based on a magnetofluidic platform. The platform comprises multiple functional areas, such as an encoding area, an encoded droplet pool and a magnetic decoding area with integrated giant magnetoresistive (GMR) sensors. To prove this concept, penicillin functionalized with fluorescent dyes is coencapsulated with magnetic nanoparticles into droplets. While fluorescent dyes are used as conventional optical barcodes which are decoded with an optical decoding setup, an additional dimensionality of barcodes is created by using magnetic nanoparticles as magnetic barcodes for individual droplets and integrated micro-patterned GMR sensors as the corresponding magnetic decoding devices. The strategy of incorporating a magnetic encoding scheme provides a dynamic range of ~40 dB in addition to that of the optical method. When combined with magnetic barcodes, the encoding capacity can be increased by more than 1 order of magnitude compared with using only optical barcodes, that is, the magnetic platform provides more than 10 unique magnetic codes in addition to each optical barcode. Besides being a unique magnetic functional element for droplet microfluidics, the platform is capable of on-demand facile magnetic encoding and real-time decoding of droplets which paves the way for the development of novel non-optical encoding schemes for highly multiplexed droplet-based biological assays.

Analysis of Edge Detection in Bar Code Symbols: An Overview and Open Problems

Accurate edge localization is essential in bar code decoding. Since speckle noise is the most dominant form of noise in laser bar code scanners, it is important to fully understand its effects on edge detection. Starting with the basic statistical properties of speckle patterns, we present stochastic analysis of speckle noise. We derive the autocorrelation function and power spectral density (PSD) of the noise in terms of intensity distribution of the scanning beam. We then study the signal‐to‐noise ratio for signals that result from scanning different configurations of edges. Next, we consider statistical properties of edge localization error caused by speckle noise. We show that the standard deviation of the error is determined by the PSD of the noise and relative positions of edges in a bar code symbol. Based on the analysis presented here, we propose new criteria for system design.

A Comprehensive Ubiquitous Healthcare Solution on an Android™ Mobile Device

Provision of ubiquitous healthcare solutions which provide healthcare services at anytime anywhere has become more favorable nowadays due to the emphasis on healthcare awareness and also the growth of mobile wireless technologies. Following this approach, an Android™ smart phone device is proposed as a mobile monitoring terminal to observe and analyze ECG (electrocardiography) waveforms from wearable ECG devices in real time under the coverage of a wireless sensor network (WSN). The exploitation of WSN in healthcare is able to substitute the complicated wired technology, moving healthcare away from a fixed location setting. As an extension to the monitoring scheme, medicine care is taken into consideration by utilizing the mobile phone as a barcode decoder, to verify and assist out-patients in the medication administration process, providing a better and more comprehensive healthcare service.

스마트 폰 어플리케이션 적용을 위한 UPC-A Bar code 인식 알고리즘 개발

This paper is about a bar code decoding algorithm developed for smart phone applications. The algorithm consists of bar code data extraction procedure, bar code signal estimation procedure, and bar code decoding procedure. To detect the peak bar code module, a DSTW had been applied because of its outstanding performance in ECG peak detection. In order to minimize errors due to non-uniform light effect, the proposed algorithm was acted as a baseline wandering filter based on module peaks detection. The algorithm had been tested to evaluate the performance under the conditions of blurring, non-uniformed light and white noises. The algorithm had shown excellent performance in reconstruction of bar code decoding, compared to other conventional methods. In order to show the possibility of applying the algorithm to a smart phone, a real UPC-A type 150 bar code pictures obtained from a smart phone camera was applied to the algorithm, achieving the correct recognition rate of 97.33%.

Real-time automatic recognition of omnidirectional multiple barcodes and DSP implementation

Barcodes have been extensively adopted in daily life, such as in merchandise labels, inventory control, storage/retrieval systems and inspection. Computer-vision-based barcode recognition can definitely facilitate barcode reading, especially for multiple barcodes and free orientation and in complex scenarios. This work, presents an automatic barcode detection and recognition algorithm for multiple and rotation invariant barcode decoding. The proposed system comprises three stages. First, the barcode is extracted by coarse-to-fine segmentation in four steps: background small clutter reduction, candidate barcode segmentation, barcode verification and barcode rotation and regularization. To enhance the barcode region, thin and small background noise clusters are eliminated using Max–Min Differencing. The approach combines several image-processing schemes, namely Gaussian smoothing filtering, connected component analysis, orientation homogeneity, moment analysis and iterative thresholding. The second stage decodes the barcode by scanning multiple traversal lines, thus preventing decoding errors due to minor barcode defects. Finally, the proposed system is implemented and optimized on a DM6437 DSP EVM board. Experimental results indicate that the proposed approach can locate multiple and omnidirectional barcodes, even with a complex background and minor distortion. The recognition rates for 10,395 lottery barcodes and 388 merchandise barcodes are 99.74 and 90.7%, respectively. The proposed system is promising and has been successfully adopted in commercial applications of lottery reading and verification of winning numbers.

Sub-pixel edge location algorithm for bilevel images

Accurate edge localization of bilevel images is of primary importance in barcode decoding. In the sub-pixel edge location algorithm for bilevel images, the bilevel image (barcode) imaging process is modeled as a square wave convoluted with a Gaussian kernel and then sampled discretely by pixel arrays. Based on the gray levels of the pixels, assumed sub-pixel edge locations are set and adjusted so that the discrepancy of the theoretical gray level of pixels and the actual gray level of pixels reaches the minimum and then the best approximation of the actual sub-pixel edges of the bilevel image is obtained. Examples are presented to illustrate the techniques of the algorithm which can solve the problems of edge location or signal recovery of bilevel images in the case of the two features: one is that the support of the Gaussian kernel is comparable to the distance of the adjacent edges; the other is that the distance between the adjacent edges is comparable to the distance of the adjacent pixels.

‘On-the-fly’ optical encoding of combinatorial peptide libraries for profiling of protease specificity

Large solid-phase combinatorial libraries currently play an important role in areas such as infectious disease biomarker discovery, profiling of protease specificity and anticancer drug discovery. Because compounds on solid support beads are not positionally-encoded as they are in microarrays, innovative methods of encoding are required. There are many advantages associated with optical encoding and several strategies have been described in the literature to combine fluorescence encoding methods with solid-phase library synthesis. We have previously introduced an alternative fluorescence-based encoding method ("colloidal barcoding"), which involves encoding 10-20 mum support beads during a split-and-mix synthesis with smaller 0.6-0.8 mum silica colloids that contain specific and identifiable combinations of fluorescent dye. The power of this 'on-the-fly' encoding approach lies in the efficient use of a small number of fluorescent dyes to encode millions of compounds. Described herein, for the first time, is the use of a colloid-barcoded library in a biological assay (i.e., protease profiling) combined with the use of confocal microscopy to decode the colloidal barcode. In this proof-of-concept demonstration, a small focussed peptide library was optically-encoded during a combinatorial synthesis, incubated with a protease (trypsin), analysed by flow cytometry and decoded via confocal microscopy. During assay development, a range of parameters were investigated and optimised, including substrate (or probe) loading, barcode stability, characteristics of the peptide-tagging fluorophore, and spacer group configuration. Through successful decoding of the colloidal barcodes, it was confirmed that specific peptide sequences presenting one or two cleavage sites were recognised by trypsin while peptide sequences not cleavable by trypsin remained intact.