• Journal of the Korea Society of Computer and Information
• /
• v.21 no.10
• /
• pp.11-19
• /
• 2016

The size of a display is large, The form becoming various of that do not apply to previous methods of gaze tracking and if setup gaze-track-camera above display, can solve the problem of size or height of display. However, This method can not use of infrared illumination information of reflected cornea using previous methods. In this paper, Robust pupil detecting method for eye's occlusion, corner point of inner eye and center of pupil, and using the face pose information proposes a method for calculating the simply position of the gaze. In the proposed method, capture the frame for gaze tracking that according to position of person transform camera mode of wide or narrow angle. If detect the face exist in field of view(FOV) in wide mode of camera, transform narrow mode of camera calculating position of face. The frame captured in narrow mode of camera include gaze direction information of person in long distance. The method for calculating the gaze direction consist of face pose estimation and gaze direction calculating step. Face pose estimation is estimated by mapping between feature point of detected face and 3D model. To calculate gaze direction the first, perform ellipse detect using splitting from iris edge information of pupil and if occlusion of pupil, estimate position of pupil with deformable template. Then using center of pupil and corner point of inner eye, face pose information calculate gaze position at display. In the experiment, proposed gaze tracking algorithm in this paper solve the constraints that form of a display, to calculate effectively gaze direction of person in the long distance using single camera, demonstrate in experiments by distance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.3
• /
• pp.139-147
• /
• 2007

In military transportation, the use of wide trailer for transporting the large and heavy weight equipments such as tank, armoured vehicle, and mobile gunnery is quite common. So, the vulnerability of causing traffic accidents for these wide military trailer to bump or collide with another car in adjacent lane is very high due to its broad width in excess of its own lane's width. Also, the possibility of these strayed accidents can be increased especially by the careless driver. In this paper, the recognition system of lane and vehicle headway direction is developed to detect the possible collision and warn the driver to prevent the fatal accident. In the system development, Kalman filtering is used first to extract the border of driving lane from the video images supplied by the CCD camera attached to the vehicle and the driving lane detection is completed with regression analysis. Next, the vehicle headway direction is recognized by using neural network scheme with the extracted parameters of the detected driving lane feature. The practical experiments for the developed system are also carried out in the real traffic road of Seoul city area and the results show us the more than 90% accuracy in recognizing the driving lane and vehicle headway direction.

• The Journal of the Korea Contents Association
• /
• v.10 no.8
• /
• pp.18-25
• /
• 2010

The study has proposed a method that simultaneously takes advantage of each projection matrix acquired by using column-directional two-dimensional PCA(C2DPCA) and row-directional two-dimensional LDA(R2DLDA). The proposed method can acquire a great secure recognition rate, with no relation to the number of training images, with acquired low-dimensional feature matrixes including both the horizontal and the vertical features of a face. Besides, in the alternate experiment of PCA and LDA to row-direction and column-direction respectively(C2DPCA & R2DLDA, C2DLDA & R2DPCA), we could make sure the system of 2 dimensional LDA with row-directional feature(C2DPCA & R2DLDA) obtain higher recognition rate with low dimension than opposite case. As a result of experimenting that, the proposed method has showed a greater recognition rate of 99.4% than the existing methods such as 2DPCA and 2DLDA, etc. Also, it was proved that its recognition processing is over three times as fast as that of 2DPCA or 2DLDA.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.2
• /
• pp.98-105
• /
• 2007

In this paper, we propose the method and system which determines the condition for safe and unsafe lane changing. To determine the condition, first, the system sets up the Region of Interest(ROI) on the neighboring lane. Second, a dangerous vehicle is extracted during the line changing. Third, the condition is determined to wm or not by calculating the moving direction, relative distance md relative velocity. To set up the ROI, the only one side lane is detected and the interested region is expanded. Using the coordinate transformation method, the accuracy of the ROI raised. To correctly extract the vehicle on the neighboring lane, the Adaptive Background Update method and Image Segmentation method which uses the feature of the travelling road are used. The object which is extracted by the dangerous vehicle is calculated the relative distance, the relative velocity and the moving average. And then in order to ring, the direction of the vehicle and the condition for safe and unsafe is determined. As minimizes the interested region and uses the feature of the travelling road, the computational quantity is reduced and the accuracy is raised and a stable result on a travelling road images which demands a high speed calculation is showed.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.1
• /
• pp.60-66
• /
• 2002

In this paper, an efficient content-based rotation-invariant retrieval of the trademarks is proposed using the edge-direction histogram for a principal symmetry axis and the moment invariants. Rotation invariant retrieval of trademarks is difficult for the conventional retrieval systems because their feature vectors are not rotation-invariant. In this paper, to obtain rotation invariant feature vectors, in addition to invariant moments, the edge-direction histogram for a principal symmetry axis is introduced and is used to solve the bin shift problem of the histogram resulted from the rotated trademark. Performance evaluation has been carried out for a database of 300 kinds of trademarks including 20 kinds of typical trademarks which are reported to be difficult to retrieve when rotated, and the proposed scheme is proved to retrieve trademarks more efficiently, especially for the rotated trademarks, than the conventional methods.

• Nuclear Engineering and Technology
• /
• v.43 no.2
• /
• pp.133-140
• /
• 2011

In this paper, a deformation measurement technology for nuclear fuel rods is proposed. The deformation measurement system includes a high-definition CMOS image sensor, a lens, a semiconductor laser line beam marker, and optical and mechanical accessories. The basic idea of the proposed deformation measurement system is to illuminate the outer surface of a fuel rod with a collimated laser line beam at an angle of 45 degrees or higher. For this method, it is assumed that a nuclear fuel rod and the optical axis of the image sensor for observing the rod are vertically composed. The relative motion of the fuel rod in the horizontal direction causes the illuminated laser line beam to move vertically along the surface of the fuel rod. The resulting change of the laser line beam position on the surface of the fuel rod is imaged as a parabolic beam in the high-definition CMOS image sensor. An ellipse model is then extracted from the parabolic beam pattern. The center coordinates of the ellipse model are taken as the feature of the deformed fuel rod. The vertical offset of the feature point of the nuclear fuel rod is derived based on the displacement of the offset in the horizontal direction. Based on the experimental results for a nuclear fuel rod sample with a formation of surface crud, an inspection resolution of 50 ${\mu}m$ is achieved using the proposed method. In terms of the degree of precision, this inspection resolution is an improvement of more than 300% from a 150 ${\mu}m$ resolution, which is the conventional measurement criteria required for the deformation of neutron irradiated fuel rods.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.609-616
• /
• 2017

In this paper, we propose an algorithm to obtain more stable and high recognition rate by using left and right rotation information of input image in order to obtain a stable recognition rate in face recognition. The proposed algorithm uses the facial image as the input information in the web camera environment to reduce the size of the image and normalize the information about the brightness and color to obtain the improved recognition rate. We apply Principal Component Analysis (PCA) to the detected candidate regions to obtain feature vectors and classify faces. Also, In order to reduce the error rate range of the recognition rate, a set of data with the left and right $45^{\circ}$ rotation information is constructed considering the directionality of the input face image, and each feature vector is obtained with PCA. In order to obtain a stable recognition rate with the obtained feature vector, it is after scattered in the eigenspace and the final face is recognized by comparing euclidean distant distances to each feature. The PCA-based feature vector is low-dimensional data, but there is no problem in expressing the face, and the recognition speed can be fast because of the small amount of calculation. The method proposed in this paper can improve the safety and accuracy of recognition and recognition rate faster than other algorithms, and can be used for real-time recognition system.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.6
• /
• pp.307-312
• /
• 2016

Markerless tracking for augmented reality using Homography can augment virtual objects correctly and naturally on live view of real-world environment by using correct pose and direction of camera. The RANSAC algorithm is widely used for estimating Homography. CS-RANSAC algorithm is one of the novel algorithm which cooperates a constraint satisfaction problem(CSP) into RANSAC algorithm for increasing accuracy and decreasing processing time. However, CS-RANSAC algorithm can be degraded performance of calculating Homography that is caused by selecting feature points which estimate low accuracy Homography in the sampling step. In this paper, we propose feature point filtering method based on CS-RANSAC for efficient planar Homography estimating the proposed algorithm evaluate which feature points estimate high accuracy Homography for removing unnecessary feature point from the next sampling step using Symmetric Transfer Error to increase accuracy and decrease processing time. To evaluate our proposed method we have compared our algorithm with the bagic CS-RANSAC algorithm, and basic RANSAC algorithm in terms of processing time, error rate(Symmetric Transfer Error), and inlier rate. The experiment shows that the proposed method produces 5% decrease in processing time, 14% decrease in Symmetric Transfer Error, and higher accurate homography by comparing the basic CS-RANSAC algorithm.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.325-345
• /
• 2023

In the rapidly evolving domain of e-commerce, our study presents a cohesive approach to enhance customer satisfaction prediction from online reviews, aligning methodological innovation with practical insights. We integrate the RFE-SHAP feature selection with LDA topic modeling to streamline predictive analytics in e-commerce. This integration facilitates the identification of key features-specifically, narrowing down from an initial set of 28 to an optimal subset of 14 features for the Random Forest algorithm. Our approach strategically mitigates the common issue of overfitting in models with an excess of features, leading to an improved accuracy rate of 84% in our Random Forest model. Central to our analysis is the understanding that certain aspects in review content, such as quality, fit, and durability, play a pivotal role in influencing customer satisfaction, especially in the clothing sector. We delve into explaining how each of these selected features impacts customer satisfaction, providing a comprehensive view of the elements most appreciated by customers. Our research makes significant contributions in two key areas. First, it enhances predictive modeling within the realm of e-commerce analytics by introducing a streamlined, feature-centric approach. This refinement in methodology not only bolsters the accuracy of customer satisfaction predictions but also sets a new standard for handling feature selection in predictive models. Second, the study provides actionable insights for e-commerce platforms, especially those in the clothing sector. By highlighting which aspects of customer reviews-like quality, fit, and durability-most influence satisfaction, we offer a strategic direction for businesses to tailor their products and services.