Application of image recognition and machine learning technologies for payment data processing review and challenges

Suponenkovs, Artjoms; Sisojevs, Aleksandrs; Mosāns, Guntis; Kampars, Jānis; Pinka, Krišjānis; Grabis, Jānis; Locmelis, Audris; Taranovs, Romāns

doi:10.1109/aieee.2017.8270536

Cited by 13 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Invoices and documents contain a great deal of information, such as invoice items and payment terms. A software system learns to recognize and validate relevant data independently on the basis of deep learning and thousands of previous expert inputs [61,62]. Digital processes without paper reduce costs and improve efficiency.…”

Section: Financial Accountingmentioning

confidence: 99%

A Domain-Oriented Analysis of the Impact of Machine Learning—The Case of Retailing

Weber

Schütte

2019

BDCC

View full text Add to dashboard Cite

Information technologies in general and artifical intelligence (AI) in particular try to shift operational task away from a human actor. Machine learning (ML) is a discipline within AI that deals with learning improvement based on data. Subsequently, retailing and wholesaling, which are known for their high proportion of human work and at the same time low profit margins, can be regarded as a natural fit for the application of AI and ML tools. This article examines the current prevalence of the use of machine learning in the industry. The paper uses two disparate approaches to identify the scientific and practical state-of-the-art within the domain: a literature review on the major scientific databases and an empirical study of the 10 largest international retail companies and their adoption of ML technologies in the domain are combined with each other. This text does not present a prototype using machine learning techniques. Instead of a consideration and comparison of the particular algorythms and approaches, the underling problems and operational tasks that are elementary for the specific domain are identified. Based on a comprehensive literature review the main problem types that ML can serve, and the associated ML techniques, are evaluated. An empirical study of the 10 largest retail companies and their ML adoption shows that the practical market adoption is highly variable. The pioneers have extensively integrated applications into everyday business, while others only show a small set of early prototypes. However, some others show neither active use nor efforts to apply such a technology. Following this, a structured approach is taken to analyze the value-adding core processes of retail companies. The current scientific and practical application scenarios and possibilities are illustrated in detail. In summary, there are numerous possible applications in all areas. In particular, in areas where future forecasts and predictions are needed (like marketing or replenishment), the use of ML today is both scientifically and practically highly developed.

show abstract

Section: Financial Accountingmentioning

confidence: 99%

A Domain-Oriented Analysis of the Impact of Machine Learning—The Case of Retailing

Weber

Schütte

2019

BDCC

View full text Add to dashboard Cite

show abstract

“…A coherent DT is achieved by opening new possibilities from the perspective of users, not by imposing them on the strict use of some products. Thus, the entire business ecosystem is gradually transforming, moving from product orientation to consumer orientation and preferences [44,49]. The definition of strict ecosystems imposed by companies will change altogether through the pressure of customers, who will avoid the products that limit them only to their purchase.…”

Section: Dt Premise For the Development Of Smart And Efficient Technomentioning

confidence: 99%

"Technologies that through Synergic Development can support the Intelligent Automation of Business Processes"

Mazilescu¹,

Micu²

2019

EAI

View full text Add to dashboard Cite

Intelligent Automation (InA) activities using large and heterogeneous data and knowledge is an old concern in IT&C and computer science, being the next generation of Robotic Process Automation (RPA) at the enterprise level. Software systems and better solutions are developed to integrate business logic rules at the application level and to provide efficient work tools for accurate results. By designing such systems, the aim is to obtain better decisions as soon as possible in real time and make more efficient the process through which they can be made. InA is a holistic approach based on the variety of existing technologies based on Digital Transformation (DT) and automation of manual activities, using for this purpose digital workers, Artificial Intelligence (AI), cloud computing, Big Data. In this world of consumption, much of the technology we introduce into our daily lives is based on AI models and methods. Cognitive Technologies (CTs) are being developed using more and more specialized platforms. This is how different automation and intelligent capabilities are developed, which in turn adds a semantic connectivity between people and information systems [41]. The present paper analyzes the main important technologies that can effectively support the development, automation and robotization of business processes (BPA/R), identifying in a rational way how they can be applied for a synergic balance of tasks between people and computing systems, with a corresponding increase of the value added of business processes.

show abstract

“…In [3], four main steps are considered: ticket localization, character localization, character recognition using an LSTM network and finally text analysis using regular expressions. In [4], classical image processing tools are used to get character blocks before applying the Tesseract OCR. As a general rule, the provided performance levels of all these works are good but do not allow for comparisons.…”

Section: Related Workmentioning

confidence: 99%

“…Also, several online and commercial solutions are now available, for instance Taggun 1 , Expensify 2 , Tiketi 3 , or Wave for Business 4 . However, the methods behind remain black boxes and present some limitations.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Receipt automatic reader

Маслова¹,

Klein²,

Dabernat³

et al. 2019

2019 International Conference on Content-Based Multimedia Indexing (CBMI)

View full text Add to dashboard Cite

Smartphones bring a new way to scan and digitalize written documents by taking pictures. This enables new document analysis applications to emerge. As a counterpart, unsupervised document capturing brings new challenges mainly related to target document localization and high quality text recognition. In this context, this work addresses automatic sale receipt understanding in an industrial context. It relies on the extraction of accurate and essential consumption data even with low quality receipt captures. We propose a tool chain that combines Deep Neural Networks and traditional image processing to ensure accurate automatic data extraction. The proposed workflow is evaluated globally by the analysis of the quality of the text recognition at the end of the processing.

show abstract

Application of image recognition and machine learning technologies for payment data processing review and challenges

Cited by 13 publications

References 3 publications

A Domain-Oriented Analysis of the Impact of Machine Learning—The Case of Retailing

A Domain-Oriented Analysis of the Impact of Machine Learning—The Case of Retailing

"Technologies that through Synergic Development can support the Intelligent Automation of Business Processes"

Receipt automatic reader

Contact Info

Product

Resources

About