• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.1
• /
• pp.50-59
• /
• 2007

In this paper, an anchor shot detection method, which is a basic technology for managing news videos for index and retrieval purposes is proposed. To do that, two most popular news program such as 'KBS 9 Hour News' and 'MBC 9 Hour News' are analyzed and 4-step rule based detection method is proposed First, in the preprocessing, video shot boundaries are detected and the 1st frame of each shot is extracted as a key frame. Then, the detected shot is declared as an anchor shot, if all the following 4 conditions are satisfied. 1) There is an anchor face in the key frame of a shot. 2) Spatial distribution of edges in the key frame is adequate. 3) Background color information of the key frame is similar to the color information of an anchor model. 4) Motion rate in the shot is low. In order to show the validity of the proposed method, three 'KBS 9 Hour News' and three 'MBC 9 Hour News', which have total running time of 108 in minute and are broadcasted at different days, are used for experiments. Average detection rates showed 0.97 in precision, 1.0 in recall, and 0.98 in F-measure.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.123-132
• /
• 2021

Malicious activities of Botnets are responsible for huge financial losses to Internet Service Providers, companies, governments and even home users. In this paper, we try to confirm the possibility of detecting botnet traffic by applying the deep learning model Convolutional Neural Network (CNN) using the CTU-13 botnet traffic dataset. In particular, we classify three classes, such as the C&C traffic between bots and C&C servers to detect C&C servers, traffic generated by bots other than C&C communication to detect bots, and normal traffic. Performance metrics were presented by accuracy, precision, recall, and F1 score on classifying both known and unknown botnet traffic. Moreover, we propose a stackable botnet detection system that can load modules for each botnet type considering scalability and operability on the real field.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.35-40
• /
• 2021

People counting data is crucial for most business owners, since they can derive meaningful information about customers movement within their businesses. For example, owners of the supermarkets can increase or decrease the number of checkouts counters depending on number of occupants. Also, it has many applications in smart buildings, too. Where it can be used as a smart controller to control heating and cooling systems depending on a number of occupants in each room. There are advanced technologies like camera-based people counting system, which can give more accurate counting result. But they are expensive, hard to deploy and privacy invasive. In this paper, we propose a method and a hardware sensor for counting people passing through a passage or an entrance using IR Infrared sensors. Proposed sensor operates at low voltage, so low power consumption ensure long duration on batteries. Moreover, we propose a new method that distinguishes human body and other objects. Proposed method is inexpensive, easy to install and most importantly, it is real-time. The evaluation of our proposed method showed that when counting people passing one by one without overlapping, recall was 96% and when people carrying handbag like objects, the precision was 88%. Our proposed method outperforms IR Infrared based people counting systems in term of counting accuracy.

• Journal of Korean Society of Archives and Records Management
• /
• v.23 no.2
• /
• pp.117-135
• /
• 2023

The National Archives of Korea (NAK) operates the NAK Portal as a record search system. However, user search satisfaction is too low, and the number of visitors to the portal is gradually decreasing. This study identifies the portal's issues, proposes feasible improvements, and constructs a pilot system to validate the solutions. The preliminary assessment revealed six major issues, such as poor search tool performance and the lack of consistency in search results. After clarifying the improvement measures, a pilot system was established and compared with the National Records Portal. The evaluation showed significant performance improvements in the pilot system, such as Precision, Recall, and Mean Reciprocal Rank (MRR).

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.771-780
• /
• 2024

In this study, we implemented a real-time pest detection and prediction system for a strawberry farm using a computer vision model based on the YOLOv5 architecture and an Isolation Forest Classifier. The model performance evaluation showed that the YOLOv5 model achieved a mean average precision (mAP 0.5) of 78.7%, an accuracy of 92.8%, a recall of 90.0%, and an F1-score of 76%, indicating high predictive performance. This system was designed to be applicable not only to strawberry farms but also to other crops and various environments. Based on data collected from a tomato farm, a new AI model was trained, resulting in a prediction accuracy of over 85% for major diseases such as late blight and yellow leaf curl virus. Compared to the previous model, this represented an improvement of more than 10% in prediction accuracy.

• Journal of Korea Multimedia Society
• /
• v.14 no.1
• /
• pp.1-14
• /
• 2011

While the circulation of images become active, various requirements to manage increasing database are raised. The content-based technology is one of methods to satisfy these requirements. The image is represented by feature vectors extracted by various methods in the content-based technology. The global feature method insures fast matching speed because the feature vector extracted by the global feature method is formed into a standard shape. The global feature extraction methods are classified into two categories, the spatial feature extraction and statistical feature extraction. And each group is divided by what kind of information is used, color feature or gray scale feature. In this paper, we introduce various global feature extraction technologies and compare their performance by accuracy, recall-precision graph, ANMRR, feature vector size and matching time. According to the experiments, the spatial features show good performance in non-geometrical modifications, and the extraction technologies that use color and histogram feature show the best performance.

• The Journal of the Korea Contents Association
• /
• v.17 no.4
• /
• pp.576-584
• /
• 2017

Unknown nouns which are not in a dictionary make problems not only morphological analysis but also almost all natural language processing area. This paper describes a recognition method for Korean unknown nouns using strings following nouns such as postposition, suffix and postposition, suffix and eomi, etc. We collect and sort words including nouns from documents and divide a word including unknown noun into two parts, candidate noun and string following the noun, by finding same prefix morphemes from more than two unknown words. We use information of strings following nouns extracted from Sejong corpus and decide unknown noun finally. We obtain 99.64% precision and 99.46% recall for unknown nouns occurred more than two forms in news of two portal sites.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.449-463
• /
• 2015

Video object tracking is important for variety of applications, such as security, video indexing and retrieval, video surveillance, communication, and compression. This paper proposes an object tracking method in HEVC bitstreams. Without pixel reconstruction, motion vector (MV) and size of prediction unit in the bitstream are employed in an Spatio-Temporal Markov Random Fields (ST-MRF) model which represents the spatial and temporal aspects of the object's motion. Coefficient-based object shape adjustment is proposed to solve the over-segmentation and the error propagation problems caused in other methods. In the experimental results, the proposed method provides on average precision of 86.4%, recall of 79.8% and F-measure of 81.1%. The proposed method achieves an F-measure improvement of up to 9% for over-segmented results in the other method even though it provides only average F-measure improvement of 0.2% with respect to the other method. The total processing time is 5.4ms per frame, allowing the algorithm to be applied in real-time applications.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.2
• /
• pp.690-696
• /
• 2016

Search engines that rely on morphological matching of user query and web document content do not support individual interests. This research proposes a personalized web search scheme that returns the results that reflect the users' query intent and personal preferences. The performance of the personalized search depends on using an effective user profiling strategy to accurately capture the users' personal interests. In this study, the user profiles are the databases of topic words and customized weights based on the recent user queries and the frequency of topic words in click history. To determine the precise meaning of ambiguous queries and topic words, this strategy uses WordNet to calculate the semantic relatedness to words in the user profile. The experiments were conducted by installing a query expansion and re-ranking modules on the general web search systems. The results showed that this method has 92% precision and 82% recall in the top 10 search results, proving the enhanced performance.

• Journal of KIISE:Software and Applications
• /
• v.26 no.10
• /
• pp.1237-1246
• /
• 1999

최근 모든 분야에서 외국과의 교류가 증대됨에 따라서 한국어 문서에는 점점 더 많은 외국어 음차 표기가 사용되는 경향이 있다. 하지만 같은 외국어에 대한 음차 표기에 개인차가 심하여 이들 음차 표기를 포함한 문서들에 대한 검색을 어렵게 만드는 원인이 되고 있다. 한 가지 해결 방법은 색인 시에 같은 외국어에서 온 음차 표기들을 등가부류로 묶어서 색인해 놓았다가 질의 시에 확장하는 방법이다. 본 논문에서는 외국어 음차 표기들의 등가부류를 만드는데 필요한 음차 표기의 음성적 유사도 비교 알고리즘인 Kodex를 제안한다. Kodex 방법은 기존의 스트링 비교 방법인 비음성적 방법에 비해 음차 표기들을 등가부류로 클러스터링하는데 있어 더 나은 성능을 보이면서도, 계산이 간단하여 훨씬 효율적으로 구현될 수 있는 장점이 있다.Abstract With the advent of digital communication technologies, as Koreans communicate with foreigners more frequently, more foreign word transliterations are being used in Korean documents more than ever before. The transliterations of foreign words are very various among individuals. This makes text retrieval tasks about these documents very difficult. In this paper we propose a new method, called Kodex, of measuring the phonetic similarity among foreign word transliterations. Kodex can be used to generate the equivalence classes of the transliterations while indexing and conflate the equivalent transliterations at the querying stage. We show that Kodex gives higher precision at the similar recall level and is more efficient in computation than non-phonetic methods based on string similarity measure.