Automatic Registration of the Nascence and Propagation of Cracks in Electrically Conductive Materials

A correlation is established between the length of the propagating crack in electrically conductive flat specimens and the change in the field of electric potentials over the surface of the specimen when an electric current is passed through it. The experimental data correspond to the analytical solution in a two-dimensional formulation obtained by means of a conformal mapping. Work can be attributed to the field of converting mechanical values into electrical ones. This transformation simplifies the process of recording mechanical processes and provides a convenient form of their control. The work is aimed at automatic control of the process of fracture of electrically conductive materials.

Training dataset generation for automatic registration of a duplicate bridge game

This paper presents a method for automatic generation of a training dataset for a deep convolutional neural network used for playing card detection. The solution allows to skip the time-consuming processes of manual image collecting and labelling recognised objects. The YOLOv4 network trained on the generated dataset achieved an efficiency of 99.8% in the cards detection task. The proposed method is a part of a project that aims to automate the process of broadcasting duplicate bridge competitions using a vision system and neural networks.

Training dataset generation for automatic registration of a duplicate bridge game

This paper presents a method for automatic generation of a training dataset for a deep convolutional neural network used for playing card detection. The solution allows to skip the time-consuming processes of manual image collecting and labelling recognised objects. The YOLOv4 network trained on the generated dataset achieved an efficiency of 99.8% in the cards detection task. The proposed method is a part of a project that aims to automate the process of broadcasting duplicate bridge competitions using a vision system and neural networks.

UAV Remote Sensing Image Automatic Registration Based on Deep Residual Features

With the rapid development of unmanned aerial vehicle (UAV) technology, UAV remote sensing images are increasing sharply. However, due to the limitation of the perspective of UAV remote sensing, the UAV images obtained from different viewpoints of a same scene need to be stitched together for further applications. Therefore, an automatic registration method of UAV remote sensing images based on deep residual features is proposed in this work. It needs no additional training and does not depend on image features, such as points, lines and shapes, or on specific image contents. This registration framework is built as follows: Aimed at the problem that most of traditional registration methods only use low-level features for registration, we adopted deep residual neural network features extracted by an excellent deep neural network, ResNet-50. Then, a tensor product was employed to construct feature description vectors through exacted high-level abstract features. At last, the progressive consistency algorithm (PROSAC) was exploited to remove false matches and fit a geometric transform model so as to enhance registration accuracy. The experimental results for different typical scene images with different resolutions acquired by different UAV image sensors indicate that the improved algorithm can achieve higher registration accuracy than a state-of-the-art deep learning registration algorithm and other popular registration algorithms.

Design and Implementation of a Software-Based Advance Electronic Voting Machine Using Automatic Registration and Fingerprint Identification

In democratic countries, free and fair elections are required to quantify the populace's sentiments to form a government of representatives. It is challenging to maneuver due to the procedural variation from country to country and complexity. As paper-based electoral systems are slow and prone to error that take hours and ample manpower to announce the results, thus a secure efficient electoral system is always preferred. In this paper, we have proposed a secure implementation of auto-registration fingerprint identification-based electronic voting systems to overcome the aspect of accuracy and transparency. We have included a novel feature of automated registration to authenticate the user through identity before the vote casting. Moreover, credentials of voters are collected in a database including fingerprints, and communication of encrypted data between server and machine with secured Secure Socket Layer (SSL). Additionally, the voter can cast their votes through a touch screen Graphical User Interface (GUI), and once the voting time end, the screen can automatically disappear by authorizing admin to print Form-45. Conclusively, the proposed system count votes automatically that is much faster and accurate than the traditional voting techniques. Moreover, the results will be available to the general public in 1-2 hours which ensures fair elections.

CAPTCHA Design: A Novel Security Method using Sindhi Language

CAPTCHA is one of the most widely used security on internet now a day’s. This CAPTCHA test is used against the Bots that creep into website and perform automatic registration. Among different type of CAPTCHAs one of oldest and easiest method is text based. Text based CAPTCHAs are available in the market in different languages i.e. English, Arabic, Urdu. This paper focuses on design of text based CAPTCHA as security. The proposed design of the CAPTCHA uses Sindhi which is an Arabic scripting language named as CaSN i.e CAPTCHA as Sindhi Numbers. CaSN focuses on the Sindhi Language numbers to generate a CAPTCHAimage for the users. An algorithm is used to generate the CaSN image. In this regard, the evaluation was performed on 290 participants from local areas of Sindh, Pakistan. The study produced prominent results after performing CaSN test among participants of the study. The study was limited among local areas of Sindh, Pakistan. The limitation of the study is to provide a new context in CAPTCHA especially for Sindhi speaking people.

A DC Scheme to Maximize the Benefits of the Public Sector Employees Based on Behavioral Finance

This paper introduces DB and DC pension plans, reviews the literature of DC pension plans, and puts forward three application strategies: automatic registration default contribution rate and annual automatic growth contribution rate, the risk tolerance level of different employees was evaluated by questionnaire survey, and individual investment choice of employees with different risk tolerance.