• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.938-958
• /
• 2024

Unsupervised Video Object Segmentation (UVOS) is a highly challenging problem in computer vision as the annotation of the target object in the testing video is unknown at all. The main difficulty is to effectively handle the complicated and changeable motion state of the target object and the confusion of similar background objects in video sequence. In this paper, we propose a novel deep Dual-stream Co-enhanced Network (DC-Net) for UVOS via bidirectional motion cues refinement and multi-level feature aggregation, which can fully take advantage of motion cues and effectively integrate different level features to produce high-quality segmentation mask. DC-Net is a dual-stream architecture where the two streams are co-enhanced by each other. One is a motion stream with a Motion-cues Refine Module (MRM), which learns from bidirectional optical flow images and produces fine-grained and complete distinctive motion saliency map, and the other is an appearance stream with a Multi-level Feature Aggregation Module (MFAM) and a Context Attention Module (CAM) which are designed to integrate the different level features effectively. Specifically, the motion saliency map obtained by the motion stream is fused with each stage of the decoder in the appearance stream to improve the segmentation, and in turn the segmentation loss in the appearance stream feeds back into the motion stream to enhance the motion refinement. Experimental results on three datasets (Davis2016, VideoSD, SegTrack-v2) demonstrate that DC-Net has achieved comparable results with some state-of-the-art methods.

• Transactions of the Society of Information Storage Systems
• /
• v.8 no.2
• /
• pp.50-55
• /
• 2012

Optical disks are widely used in libraries and archives as digital data media due to their long-term storage stability. Though archive-grade optical disks are already available on the market, there is a relative less focusing on the reliable recording conditions. Commercial BD-R media were recorded at various recording speeds with the maximum speed of 6X, and tested at the acceleration aging conditions. Through the evaluation of long-term storage features by the data stability test, lower recording speed of 2x resulted in better long-term storage stability. In addition, degradation aspects of unstable long-term storage feature at outer region of disk were discussed.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.6
• /
• pp.1431-1438
• /
• 1995

In this paper, we present a multiple-view stereo matching method in case of moving in the direction of optical axis with stereo camera. Also we analyze the obtainable depth precision to show that multiple-view stereo increases the virtual baseline with single-view stereo. This method decides candidate points for correspondence in each image pair and then search for the correct combinations of correspondences among them using the geometrical consistency they must satisfy. Adantages of this method are capability in increasing the accuracy in matching by using the multiple stereo images and less computation due to local processing. This method computes 3-D depth by averaging the depth obtained in each multiple-view stereo. We show that the resulting depth has more precision than depth obtainable by each independent stereo when the position of image feature is uncertain due to image noise. This paper first defines a multipleview stereo agorithm in case of moving in the direction of optical axis with stereo camera and analyze the obtainable precision of computed depth. Then we represent the effect of removing the incorrect matching candidate and precision enhancement with experimental result.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.2
• /
• pp.38.1-38.1
• /
• 2013

We present the Yonsei evolutionary population synthesis (YEPS) models based on the high-resolution empirical spectral energy distributions (SEDs). We have adopted the MILES library in the optical wavelength, and our new models based on the MILES library show good agreements with our previous models presented in the YEPS I. The effect of hot horizontal-branch (HB) stars on the integrated properties of simple stellar populations (SSPs) is again confirmed by our models based on empirical SEDs. In addition, we have extended our empirical models to the near-IR wavelength and predicted the strengths of the calcium II triplet (CaT) and the Paschen triplet (PaT) based on the INDO-US and the Cenarro library. We find that the effect of HB stars and the age of SSPs on the CaT is almost negligible. On the other hands, the PaT models are very sensitive to the existence of hot stars, e.g., HB stars and young turn-off stars, and show very similar results with Balmer lines. Interestingly, the CaT distribution of GCs in NGC 1407, which is at odds with the optical (B-I) color distribution, can be explained by the unique feature of the CaT-[Fe/H] relations that show almost the same equivalent widths in the metal-rich regime. We will also discuss the impact of the second-generation populations on the strength of the CaT.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.9
• /
• pp.1290-1296
• /
• 2013

The light intensity which represents the relative amount of brightness and darkness is very important feature to discern the color hue and its relevant information. With this aim, we devise a new optical system and method to analyze the light intensity. Our suggested system including a phototransistor and white-high-brightness chip light-emitting diode intend estimate the contrast value utilizing Image Research Institute(I.R.I.) Hue & Tone samples which includes 120 color sheets arranged by the color hue and tone. As a result, we confirmed that the brightness of the color checker can be accurately estimated by a high-brightness light-emitting-diode optical system.

• Journal of Navigation and Port Research
• /
• v.32 no.9
• /
• pp.723-727
• /
• 2008

Sensing performances of evanescent field absorption (EFA) hetero-core fiber sensor has been presented based on EFA by changing the length and the core diameter of the single mode fiber. Experimental results have demonstrated a good feature in their relationship between the length and the core diameter of the single mode fiber. The sensor consists of 2 fiber optics which have the same cladding diameter of $125{\mu}m$ However one fiber optic used is single mode and has varying core diameter ranging from 3.3 to $5.6{\mu}m$. The other fiber is multimode type and has a thicker fixed core diameter of $62.5{\mu}m$. The 2 fiber optics are thermally spliced together. Experiments conducted to measure the resonance wavelength were carried out over a range of refractive index, to find the optimum sensing length Experiments show that core diameter of the single mode fiber and sensing length offects the linearity and sensitivity.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.735-739
• /
• 2005

This paper presents a new system to estimate the head pose of human in interactive indoor environment that has dynamic illumination change and large working space. The main idea of this system is to suggest a new morphological feature for estimating head angle from stereo disparity map. When a disparity map is obtained from stereo camera, the matching confidence value can be derived by measurements of correlation of the stereo images. Applying a threshold to the confidence value, we also obtain the specific morphology of the disparity map. Therefore, we can obtain the morphological shape of disparity map. Through the analysis of this morphological property, the head pose can be estimated. It is simple and fast algorithm in comparison with other algorithm which apply facial template, 2D, 3D models and optical flow method. Our system can automatically segment and estimate head pose in a wide range of head motion without manual initialization like other optical flow system. As the result of experiments, we obtained the reliable head orientation data under the real-time performance.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.1 s.256
• /
• pp.43-49
• /
• 2007

A new electric coil design methodology using the notion of topology optimization is developed. The specific design problem in consideration is to find optimal coil configuration that maximizes the Lorentz force under given magnetic field. Topology optimization is usually formulated using the finite element method, but the novel feature of this method is that no such partial differential equation solver is employed during the whole optimization process. The proposed methodology allows the determination of not only coil shape but also the number of coil turns which is not possible to determine by any existing topology optimization concept and to perform single coil strand identification algorithm. The specific applications are made in the design of two-dimensional fine-pattern focusing coils of an optical pickup actuator. In this method, the concept of equivalent magnetizing current is utilized to calculate the Lorentz force, and the optimal coil configuration is obtained without any initial layout. The method is capable of generating the location and shape of turns of coil. To confirm the effectiveness of the proposed method in optical pickup applications, design problems involving multipolar permanent magnets are considered.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1555-1560
• /
• 2000

Recently, optical pickup actuators have been designed to have structures that extruded lens to decrease their height, because they are used in very thin drive for notebook computers. However, because of discordant and undesirable of forces that are supposed to happen in this design feature, subsidiary resonance such as rolling and pitching mode exert bad influence on actuator. In this paper, we presented force constituents to clarify the cause of subsidiary resonance and proposed new finite element analysis method to calculate force precisely, and performed frequency response analysis to evaluate characteristics of actuators. As a result, we could find out design parameters to diminish the influence of subsidiary resonance. Sample actuators designed with appropriate parameters were fabricated and put to practical tests. Comparing analysis with experimental results, we verified the accuracy of the analysis and the effectiveness of the method presented.