• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.5
• /
• pp.990-995
• /
• 2010

Harris corner detector is commonly used to detect feature points for recognizing 2-D or 3-D objects. However, the feature points calculated from both of query and target objects need to be same positions to guarantee accurate recognitions. In order to check the positions of calculated feature points, we generate a Huffman tree which is based on adjacent feature values as inputs. However, the structures of two Huffman trees will be same as long as both of a query and targets have same feature values no matter how different their positions are. In this paper, we sort feature values and calculate the Euclidean distances of coordinates between two adjacent feature values. The Huffman Tree is generated with these Euclidean distances. As a result, the information of point locations can be included in the generated Huffman tree. This is the main strategy for accurate recognitions. We call this system as the HRM(Hybrid Retrieval Machine). This system works very well even when artificial random noises are added to original data. HRM can be used to recognize biological data such as proteins, and it will curtail the costs which are required to biological experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.8
• /
• pp.1843-1859
• /
• 2013

The continuous increase of the spatial resolution of remote sensing images brings great challenge to image analysis and processing. Traditional prior knowledge-based region detection and target recognition algorithms for processing high resolution remote sensing images generally employ a global searching solution, which results in prohibitive computational complexity. In this paper, a more efficient region of interest (ROI) detection algorithm based on visual attention and threshold segmentation (VA-TS) is proposed, wherein a visual attention mechanism is used to eliminate image segmentation and feature detection to the entire image. The input image is subsampled to decrease the amount of data and the discrete moment transform (DMT) feature is extracted to provide a finer description of the edges. The feature maps are combined with weights according to the amount of the "strong points" and the "salient points". A threshold segmentation strategy is employed to obtain more accurate region of interest shape information with the very low computational complexity. Experimental statistics have shown that the proposed algorithm is computational efficient and provide more visually accurate detection results. The calculation time is only about 0.7% of the traditional Itti's model.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.2
• /
• pp.167-175
• /
• 2003

In document classification, target of analysis is not document itself but words appeared in the document. Word information, therefore, is a significant factor in document classification. In this study, we are dealing with the classification of Korean document based on words and feature vectors. First, we present the performance of document classification using nouns and keywords. Second, we compare to the results for the size of feature vectors.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1375-1385
• /
• 2022

In this paper, we propose a semi-supervised domain adaptation solution to deal with practical face recognition (FR) scenarios where a single face image for each target identity (to be recognized) is only available in the training phase. Main goal of the proposed method is to reduce the discrepancy between the target and the source domain face images, which ultimately improves FR performances. The proposed method is based on the Domain Adatation network (DAN) using an MMD loss function to reduce the discrepancy between domains. In order to train more effectively, we develop a novel loss function learning strategy in which MMD loss and cross-entropy loss functions are adopted by using different weights according to the progress of each epoch during the learning. The proposed weight adoptation focuses on the training of the source domain in the initial learning phase to learn facial feature information such as eyes, nose, and mouth. After the initial learning is completed, the resulting feature information is used to training a deep network using the target domain images. To evaluate the effectiveness of the proposed method, FR performances were evaluated with pretrained model trained only with CASIA-webface (source images) and fine-tuned model trained only with FERET's gallery (target images) under the same FR scenarios. The experimental results showed that the proposed semi-supervised domain adaptation can be improved by 24.78% compared to the pre-trained model and 28.42% compared to the fine-tuned model. In addition, the proposed method outperformed other state-of-the-arts domain adaptation approaches by 9.41%.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.8
• /
• pp.571-578
• /
• 2013

The IHO S-100 is a standard on the universal hydorgraphic data model for supporting information services that integrate various data in maritime and provide proper information for safety of vessels. The S-100 is used to develop S-10x product specifications which are standards on guideline for creation and delivery of specific data set in maritime. The product specification for feature-based data such as ENC(Electronic Navigational Chart) data includes a feature catalogue that describes characteristics of features in that feature-based data. The feature catalogue is developed by domain experts with knowledge on data of the target domain. However, it is not feasible to develop a feature catalogue according to the XML schema by manual. In the IHO TSMAD committee meeting, needs of developing technology on building feature catalogue has been discussed. Therefore, we present a feature catalogue builder that is a GUI(Graphic User Interface) system supporting domain experts to build feature catalogues in XML. The feature catalogue builder is developed to connect with the FCD(Feature Concept Dictionary) register in the IHO(International Hydrographic Organization) GI(Geographic Information) registry. Also, it supports domain experts to select proper feature items based on the relationships between register items.

• Journal of Internet Computing and Services
• /
• v.11 no.4
• /
• pp.107-117
• /
• 2010

The feature models representing the common and variable concepts among the software products and the feature configurations generated by selecting the features to be included in the target product are the essential components in the software product lines methodology. Although the researches on the formal semantics and reasoning of the feature models and feature configurations are in progress, the researches on feature model ontologies and feature configuration validation using the semantic web technologies are yet insufficient. This paper defines the formal semantics of the feature models and proposes a feature configuration validation technique based on ontology and semantic web technologies. OWL(Web Ontology Language), a semantic web standard language, is used to represent the knowledge in the feature models and the feature configurations. SWRL(Semantic Web Rule Language), a semantic web rule languages, is used to define the rules to validate the feature configurations. The approach in this paper provides the formal semantic of the feature models, automates the validation of feature configurations, and enables the application of various semantic web technologies, such as SQWRL.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.43-49
• /
• 2019

The wired and wireless Internet is a useful window to easily acquire various types of media data. On the other hand, the public can easily get the media data including the object to which the personal information is exposed, which is a social problem. In this paper, we propose a method to robustly detect a target object that has exposed personal information using a learning algorithm and effectively block the detected target object area. In the proposed method, only the target object containing the personal information is detected using a neural network-based learning algorithm. Then, a grid-like mosaic is created and overlapped on the target object area detected in the previous step, thereby effectively blocking the object area containing the personal information. Experimental results show that the proposed algorithm robustly detects the object area in which personal information is exposed and effectively blocks the detected area through mosaic processing. The object blocking method presented in this paper is expected to be useful in many applications related to computer vision.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.11
• /
• pp.911-920
• /
• 2018

In this study, we performed a study to track the angle between the guided weapon and the target by using the strap-down image seeker, and constructed a test bed that can simulate it visually. This paper describes a method to maintain high-performance feature distribution in the implementation of sparse feature tracking algorithm such as Lucas Kanade's optical flow algorithm for target tracking using image information. We have extended the feature tracking problem to the concept of feature management. To realize this, we constructed visual environment using Unity3D engine and developed image processing simulation using OpenCV. For the co-simulation, dynamic system modeling was performed with Matlab Simulink, the visual environment using Unity3D was constructed, and computer vision work using OpenCV was performed.

• Journal of Biomedical Engineering Research
• /
• v.26 no.3
• /
• pp.129-132
• /
• 2005

It is one of the most important issues to determine a target brain image that gives a common coordinate system for a constructing population-based brain atlas. The purpose of this study is to provide a simple and reliable procedure that determines the target brain image among the group based on the inherent structural information of three-dimensional magnetic resonance (MR) images. It uses only 11 lines defined automatically as a feature vector representing structural variations based on the Talairach coordinate system. Average characteristic vector of the group and the difference vectors of each one from the average vector were obtained. Finally, the individual data that had the minimum difference vector was determined as the target. We determined the target brain image by both our algorithm and conventional visual inspection for 20 healthy young volunteers. Eighteen fiducial points were marked independently for each data to evaluate the similarity. Target brain image obtained by our algorithm showed the best result, and the visual inspection determined the second one. We concluded that our method could be used to determine an appropriate target brain image in constructing brain atlases such as disease-specific ones.

• Journal of Korea Multimedia Society
• /
• v.24 no.6
• /
• pp.796-804
• /
• 2021

In computer vision, visual tracking method addresses the problem of localizing an specific object in video sequence according to the bounding box. In this paper, we propose a tracking method by introducing the feature correlation comparison into the siamese network to increase its matching identification. We propose a way to compute location of object to improve matching performance by a correlation operation, which locates parts for solving the searching problem. The higher layer in the network can extract a lot of object information. The lower layer has many location information. To reduce error rate of the object center point, we built a siamese network that extracts the distribution and location information of target objects. As a result of the experiment, the average center error rate was less than 25%.