Algorithms and Software for Recognition of Address Structures

The article is devoted to the problem of recognizing mail addresses from an arbitrary format string. The purpose of the research is a developing software for automatic mail address recognition in two forms: as a library and as a web server. As an approach to development, object-oriented programming paradigm was used. Preference is given to the C# programming language version 8.0 and ASP.NET Core 3.1 and Entity Framework Core 3.1. Address recognition software has been developed. It can be used as a programming library and as a separate web server with open HTTP REST API. The paper substantiates the need to create software for automating the recognition of address structures from a string of arbitrary format. According to the rules for the contruction of addresses, their basic patterns and nuances are analyzed. During development, fundamentally new mail address recognition algorithms were invented in the C# programming language.

Address Recognition System for Postal Service Using Neural Networks

While most of the Indian industries are in the process of automation, it is a bitter truth that the Indian Postal System is still using manual intervention for its mail sorting and processing. Although for postal automation there are many pieces of work towards street name recognition in non-Indian languages, to the best of our knowledge there is no work on street name recognition in Indian languages. The Automatic Mail Processor (AMP), which we have designed, scans a mail and interprets the imperative fields of the destination address such as the Pin Code, City name, Locality name and the Street name. The interpreted address is subsequently converted into a QR code. The code is reprinted onto the mail which can be read by a low-cost machine. By converting the destination address into a barcode, all of the future sorting processes can be accomplished by using a mechanical machine sorter, which can sort the mails according to the barcode present on them. We used two main approaches to accomplish this task: classifying words directly and character segmentation. For the former, we use Convolutional Neural Network (CNN) with various architectures to train a model that can precisely classify words. We then pass the segmented characters to a R ecurrent Neural Network (RNN) for classification and then reconstruct each word according to the results of classification and segmentation.

Tracking Outfield Employees using GPS in Web Applications

This paper presents e-Track, a web-based tracking system for outfield employees in order to cater for various business activities as demanded by the business owners. Such demands may range from a simple task assignment, to employee location tracking and remote observation of the employees’ task progress. The objective of the proposed system is two-fold. First, the employees to access the application and clocks-in work. Second, a standalone web system for the employers to determine the approximate location of the staff assigned with outfield duties. The IP address recognition will ensure no buddy punching takes place. e-Track is hoped to increase efficiency among employees by saving time travelling between branches during outfield duties. In the future, e-Track will be integrated with claim and payment modules to support arrangement for outfield duties.