• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.205-212
• /
• 2018

In this paper, we propose a method for more accurate fake discrimination using time information in CNN-based signature recognition. To easily use the time information and not to be influenced by the speed of signature writing, we acquire the signature as a movie and divide the total time of the signature into equal numbers of equally spaced intervals to obtain each image and synthesize them to create signature data. In order to compare the method using the proposed signature image and the method using only the last signature image, various signature recognition methods based on CNN have been experimented in this paper. As a result of experiment with 25 signature data, we found that the method using time information improves performance in fake discrimination compared to the existing method at all experiments.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.352-359
• /
• 2021

The purpose of this study is to design and build fake news discrimination systems and methods using fact-checking guidelines. In other words, the main content of this study is the system for identifying fake news using Artificial Intelligence -based Fact-checking guidelines. Specifically planned guidelines are needed to determine fake news that is prevalent these days, and the purpose of these guidelines is fact-checking. Identifying fake news immediately after seeing a huge amount of news is inefficient in handling and ineffective in handling. For this reason, we would like to design a fake news identification system using the fact-checking guidelines to create guidelines based on pattern analysis against fake news and real news data. The model will monitor the fact-checking guideline model modeled to determine the Fact-checking target within the news article and news articles shared on social networking service sites. Through this, the model is reflected in the fact-checking guideline model by analyzing news monitoring devices that select suspicious news articles based on their user responses. The core of this research model is a fake news identification device that determines the authenticity of this suspected news article. So, we propose news article identification methods with fact-checking guideline on Artificial Intelligence & Bigdata. This study will help news subscribers determine news that is unclear in its authenticity.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.33-39
• /
• 2018

In this paper, we propose a describes how to detect a false iris image by inserting watermark into a iris image. The existing method, which inserts the watermark into the entire iris image to detect a fake iris, has a problem that can evade it by segmenting iris region of an iris image. The purpose of overcoming the problem, this paper proposes a new fake iris detection technique based on digital watermark. It first searches a central point of an iris image, divide the image into blocks with respect to the point. executes Discrete Cosine Transform, inserts watermark into the blocks, and then verifies an iris image using NC(Normalized Correlation). In the experiments, we confirm the robustness for attacks - crop and JPEG.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.07a
• /
• pp.293-294
• /
• 2017

본 논문에서는 CNN 기반 서명인식에서 시간정보를 이용하여 위조서명을 보다 정확하게 판별하는 방법을 제안한다. 시간정보를 이용하는 첫 번째 방법은 서명하는 전체 시간을 동일한 개수의 등 간격으로 나누어 각각의 이미지를 얻고 이를 합성하여 이용하는 방법이다. 두 번째 방법은 동일한 개수의 등 간격으로 나누어진 각각의 이미지를 CNN-LSTM 으로 판별하는 방법이다. 동일한 개수의 등 간격으로 나누어진 이미지들에는 서명의 속도에 따른 모양의 차이가 발생하기 때문에 비록 최종 서명의 모양이 원본과 매우 유사하다고 하더라도 속도가 다른 경우 위조임을 판별할 수 있다. 두 명의 서명에 대하여 실험을 한 결과 최종 서명이 매우 유사하더라도 속도가 다른 경우 위조로 판별할 수 있음을 보였다. 다만 이미지 합성 과정에 만들어진 새로운 정보로 인하여 진짜 서명을 가짜로 판별할 수 있는 가능성도 늘어날 수 있음을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.411-412
• /
• 2022

본 논문에서는 코로나19 뉴스와 코로나19 가짜뉴스의 데이터셋을 활용하여 입력 받은 뉴스가 가짜뉴스일 확률을 예측한다. 가짜 뉴스 본문에는 코로나19, 대통령, 정부, 가짜, 언론 등의 키워드의 빈도가 높았다. 위의 키워드를 토대로 나이브 베이즈 모델링을 하여 이를 적용해 가짜 뉴스를 가려내는 웹페이지를 개발하였다.

• The Journal of the Korea Contents Association
• /
• v.22 no.6
• /
• pp.125-134
• /
• 2022

This study aims to critically discuss the problems that need to be solved from a humanities perspective in order to utilize big data. It identifies and discusses three research problems that may arise from collecting, processing, and using big data. First, it looks at the fake information circulating with regard to problems with the data itself, specifically looking at article-type advertisements and fake news related to politics. Second, discrimination by the algorithm was cited as a problem with big data processing and its results. This discrimination was seen while searching for engineers on the portal site. Finally, problems related to the invasion of personal related information were seen in three categories: the right to privacy, the right to self-determination of information, and the right to be forgotten. This study is meaningful in that it points out the problems facing in the aspect of big data utilization from the humanities perspective in the era of big data and discusses possible problems in the collection, processing, and use of big data, respectively.

• Korean Journal of Agricultural Science
• /
• v.49 no.3
• /
• pp.495-510
• /
• 2022

In this study, fluorescence hyperspectral imaging (FHSI) was used for the rapid, non-destructive detection of fake, manmade eggs from real eggs. To identify fake eggs, protoporphyrin IX (PpIX)-a natural pigment present in real eggshells-was utilized as the main indicator due to its strong fluorescence emission effect. The fluorescence images of real and fake eggs were acquired using a line-scan-based FHSI system, and their fluorescence features were analyzed based on spectroscopic techniques. To improve the detection performance and accuracy, an optimal waveband combination was investigated with analysis of variance (ANOVA), and its fluorescence ratio images (588/645 nm) were created for visualization of the real eggs between two different egg groups. In addition, real and fake eggs were scanned using a one-waveband (645 nm) handheld fluorescence imager that can perform real-time scanning for on-site applications. Then, the results of the two methods were compared with one another. The outcome clearly shows that the newly developed FHSI system and the fluorescence handheld imager were both able to distinguish real eggs from fake eggs. Consequently, FHSI showed a better performance (clearer images) compared to the fluorescence handheld imager, and the outcome provided valuable information about the feasibility of using FHSI imaging with ANOVA for the discrimination of real and fake eggs.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.2
• /
• pp.71-75
• /
• 2017

In this paper, a smart optical fingerprint sensor technology that is robust against faked fingerprints. A new lens and prism accurately detect fingerprint ridges and valleys that are needed to express a fingerprint's intrinsic characteristics well. The proposed technology includes light path configuration and an optical fingerprint sensor that can effectively identify faked fingerprint features. Results of simulation show the smart optical fingerprint sensor classifies the characteristics of faked fingerprints made from silicone, gelatin, paper, and rubber, and show that the proposed technology has superior detection performance with faked fingerprints, compared to the existing infrared discrimination method.

• Nuclear Engineering and Technology
• /
• v.55 no.11
• /
• pp.3925-3934
• /
• 2023

The importance of fast neutron detection for nuclear safeguards purposes has increased due to its potential advantages such as reasonable cost and higher precision for larger sample masses of nuclear materials. Pulse-shape discrimination (PSD) is inevitably used to discriminate neutron- and gamma-ray- induced signals from organic scintillators of very high gamma sensitivity. The light output (LO) threshold corresponding to several MeV of recoiled proton energy could be necessary to achieve fine PSD performance. However, this leads to neutron count losses and possible distortion of results obtained by neutron multiplicity counting (NMC)-based nuclear material accountancy (NMA). Moreover, conventional PSD techniques are not effective for counting of neutrons in a high-gamma-ray environment, even under a sufficiently high LO threshold. In the present work, PSD performance (figure-of-merit, FOM) according to LO bands was confirmed using a conventional charge comparison method (CCM) and compared with results obtained by convolution neural network (CNN)-based PSD algorithms. Also, it was attempted, for the first time ever, to reject fake neutron signals from distorted PSD regions where neutron-induced signals are normally detected. The overall results indicated that higher neutron detection efficiency with better accuracy could be achieved via CNN-based PSD algorithms.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.345-351
• /
• 2021

This study is designed to determine how to identify misleading news articles based on natural language processing on Artificial Intelligence & Bigdata. A misleading news discrimination system and method on natural language processing is initiated according to an embodiment of this study. The natural language processing-based misleading news identification system, which monitors the misleading vocabulary database, Internet news articles, collects misleading news articles, extracts them from the titles of the collected misleading news articles, and stores them in the misleading vocabulary database. Therefore, the use of the misleading news article identification system and methods in this study does not take much time to judge because only relatively short news titles are morphed analyzed, and the use of a misleading vocabulary database provides an effect on identifying misleading articles that attract readers with exaggerated or suggestive phrases. For the aim of our study, we propose news article identification methods in natural language processing on Artificial Intelligence & Bigdata.