• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.3
• /
• pp.161-166
• /
• 2023

In recent years, new and variant hacking of binary codes has increased, and the limitations of techniques for detecting malicious codes in source programs and defending against attacks are often exposed. Advanced software security vulnerability detection technology using machine learning and deep learning technology for binary code and defense and response capabilities against attacks are required. In this paper, we propose a malware clustering method that groups malware based on the characteristics of the taint information after entering dynamic taint information by tracing the execution path of binary code. Malware vulnerability detection was applied to a three-layered Few-shot learning model, and F1-scores were calculated for each layer's CPU and GPU. We obtained 97~98% performance in the learning process and 80~81% detection performance in the test process.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.5
• /
• pp.58-64
• /
• 2001

Recently many informations are transmitted ,md stored as video data, and they are on the rapid increase because of popularization of high performance computer and internet. In this paper, to retrieve video data, shots are found through analysis of video stream and the method of detection of key frame is studied. Finally users can retrieve the video efficiently. This Paper suggests a new feature that is robust to object movement in a shot and is not sensitive to change of color in boundary detection of shots, and proposes the characterizing value that reflects the characteristic of kind of video (movie, drama, news, music video etc,). The key frames are pulled out from many frames by using the local minima and maxima of differential of the value. After original frame(not de image) are reconstructed for key frame, indexing process is performed through computing parameters. Key frames that arc similar to user's query image arc retrieved through computing parameters. It is proved that the proposed methods are better than conventional method from experiments. The retrieval accuracy rate is so high in experiments.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.29-34
• /
• 2022

We propose a novel network architecture and build dataset for recognizing clickable objects on mobile device screens. The data was collected based on clickable objects on the mobile device screen that have numerous resolution, and a total of 24,937 annotation data were subdivided into seven categories: text, edit text, image, button, region, status bar, and navigation bar. We use the Deconvolution Single Shot Detector as a baseline, the backbone network with Squeeze-and-Excitation blocks, the Single Shot Detector layer structure to derive inference results and the Feature pyramid networks structure. Also we efficiently extract features by changing the input resolution of the existing 1:1 ratio of the network to a 1:2 ratio similar to the mobile device screen. As a result of experimenting with the dataset we have built, the mean average precision was improved by up to 101% compared to baseline.

• Journal of Korea Multimedia Society
• /
• v.6 no.5
• /
• pp.797-804
• /
• 2003

Scene change detection algorithm, which is very important preprocessing technique for video indexing and retrieval and determines the performance of video database system, is being studied widely. In this paper, we propose a more effective abrupt scene change detection, which is robust to large motion, sudden change of light and successive abrupt shot transitions rapidly. And we also propose a new gradual scene change detection algorithm, which can detect dissolve, and fade in/out precisely. Furthermore, we also propose a representative frame extraction algorithm which performs content-based video summary by novel DCT DC image buffering technique and accumulative histogram intersection measure (AHIM).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.2
• /
• pp.74-81
• /
• 2005

As the multimedia data increases, various scene change detection algorithms for video indexing and sequence matching have been proposed to efficiently manage and utilize digital media. In this paper, we propose a robust scene change detection algorithm for video sequences with abrupt luminance variations. To improve the accuracy and to reduce the computational complexity of video indexing with abrupt luminance variations, the proposed algorithm utilizes edge features as well as color features, which yields a remarkably better performance than conventional algorithms. In the proposed algorithm first we extract the candidate shot boundaries using color histograms and then determine using edge matching and luminance compensation if they are shot boundaries or luminance changes. If the scene contains trivial brightness variations, the edge matching and luminance compensation are performed only for shot boundaries. In experimental results, the proposed method gives remarkably a high performance and efficiency than the conventional methods with the similar computational complexity.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.4
• /
• pp.381-387
• /
• 2002

In this paper, an efficient method to find shot boundaries in the MPEG video stream data is proposed. For this purpose, we first assume that the histogram difference value(HDV) and pixel difference value(PDV) as an one dimensional signal and apply the median filter to these signals. The output of the median filter is subtracted from the original signal to produce the median filtered difference(MFD). The MFD is a criterion of shot boundary. In addition a neural network is employed and trained to find exactly cut boundary. The proposed algorithm shows that the cut boundaries are well extracted, especially in a dynamic video.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.712-720
• /
• 2001

In this paper, we propose an efficient method to detect abrupt shot changes in a video sequence using an unsupervised clustering. Conventional clustering-based shot change detection algorithms use multiple features in order to overcome the shortcomings of a single feature. In such methods it is very important to determine the appropriate initial cluster centers well. In this paper we propose a modified k-means clustering algorithm which estimates the initial cluster center adaptively. Experimental results show that the proposed algorithm works well.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1507-1510
• /
• 2003

We propose UPGMA(Unweighted Pair Group Method using Average distance) as hierarchical clustering to detect abrupt shot changes using multiple features such as pixel-by-pixel difference, global and local histogram difference. Conventional $\kappa$-means algorithm which is a method of the partitional clustering, has to select an efficient initial cluster center adaptively UPGMA that we propose, does not need initial cluster center because of agglomerative algorithm that it starts from each sample for clusters. And UPGMA results in stable performance. Experiment results show that the proposed algorithm works not only well but also stably.