Handwritten Documents Validation Using Pattern Recognition and Transfer Learning

Handwritten Documents Validation Using Pattern Recognition and Transfer Learning

Jadli Aissam, Mustapha Hain, Adil Chergui
DOI: 10.4018/IJWLTT.20220901.oa1
Article PDF Download
Open access articles are freely available for download

Abstract

Handwritten documents in an Enterprise Resource Planning (ERP) system can come from different sources and usually have different designs, sizes, and subjects (i.e. bills, checks, invoices, etc.). Given these documents were filled manually, they have to be inspected to detect various kinds of issues (missing signature or stamp, missing name, etc.) before being saved in the ERP system or processed by an OCR engine. In this paper, the authors present a transfer learning approach to detect issues in scanned handwritten documents, using an award-winning deep convolutional neural network (InceptionV3) and different machine learning algorithms such as Logistic Regression (LR), Support Vector Machine (SVM) and Naive Bayes (NB). The experiment shows that the combination of InceptionV3 and LR got an accuracy of 91.8% for missing stamp detection. This can allow using this approach in an ERP system as an automatic verification procedure in a document processing flow.
Article Preview
Top

Paper Context

In this section, the authors present the basic concepts of this paper. Namely, defining ERP and its ecosystem (composed of different modules and systems), determining the boundaries of addressed problematic, and finally exploring related works to assess similar concepts and approaches that use deep learning and pattern recognition.

Enterprise Resources Planning (ERP)

In front of fierce competition for survival and expansion, companies shared the same ambitions of optimizing every step of their network of business processes by combining all activities, processes, and strategies into a single central computerized system called Enterprise Resource Planning (ERP). It includes all the business functions like planning, purchasing, capacity planning, production, quality control, inspection, maintenance, selling and distribution, finance, procurement, marketing, etc. The organization's entire data is stored in a unique database known as the manufacturing or central database (Addo-Tenkorang & Helo, 2011). ERP systems are built upon the concept of modules. Therefore, In addition to the Client Relationship Management (CRM) module which mission is to develop relationships with the organization's customers and the Supplier Relationship Management (SRM) module which support the company-supplier relationship during its entire lifecycle (Lang et al., 2002) (Huiping, 2009), different modules in the ERP ecosystem exist to address different needs for the organization, (e.g. MRP, WMS, etc.). Additionally, other functional modules can be implemented in ERP systems (e.g. document management module) to support this architecture.

Complete Article List

Search this Journal:
Reset
Volume 19: 1 Issue (2024)
Volume 18: 2 Issues (2023)
Volume 17: 8 Issues (2022)
Volume 16: 6 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing