• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.173-180
• /
• 2014

Compressive sensing is a new signal acquisition paradigm that enables sparse/compressible signal to be sampled under the Nyquist-rate. To fully benefit from its much simplified acquisition process, huge efforts have been made on improving the performance of compressive sensing recovery. However, concerning color images, compressive sensing recovery lacks in addressing image characteristics like energy distribution or human visual system. In order to overcome the problem, this paper proposes a new group-sparsity hard thresholding process by preserving some RGB-grouped coefficients important in both terms of energy and perceptual sensitivity. Moreover, a smoothed group-sparsity iterative hard thresholding algorithm for compressive sensing of color images is proposed by incorporating a frame-based filter with group-sparsity hard thresholding process. In this way, our proposed method not only pursues sparsity of image in transform domain but also pursues smoothness of image in spatial domain. Experimental results show average PSNR gains up to 2.7dB over the state-of-the-art group-sparsity smoothed recovery method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.7
• /
• pp.205-215
• /
• 2013

In digital imaging system, Bayer pattern is widely used and the observed image is degraded by optical blur during image acquisition process. Generally, demosaicing and deblurring process are separately performed in order to convert a blurred Bayer image to a high resolution color image. However, the demosaicing process often generates visible artifacts such as zipper effect and Moire artifacts when performing interpolation across edge direction in Bayer pattern image. These artifacts are emphasized by the deblurring process. In order to solve this problem, this paper proposes a deblurring algorithm combined with edge directional color demosaicing method. The proposed method is consisted of interpolation step and region classification step. Interpolation and deblurring are simultaneously performed according to horizontal and vertical directions, respectively during the interpolation step. In the region classification step, characteristics of local regions are determined at each pixel position and the directionally obtained values are region adaptively fused. Also, the proposed method uses blur model based on wave optics and deblurring filter is calculated by using estimated characteristics of local regions. The simulation results show that the proposed deblurring algorithm prevents the boosting of artifacts and outperforms conventional approaches in both objective and subjective terms.

• Journal of the HCI Society of Korea
• /
• v.1 no.1
• /
• pp.73-80
• /
• 2006

Mitologia is about visualizing relations of information in user-oriented method. Most information given in life has invisible relations with each other. By analyzing the common characters and relations of information, we can not only measure the importance of the information but also grasp the overall properties of the information. Especially human relations are the major concerns of social network having several visualization methodologies shown by analyzing relations of each individual in society. We applied social network theory to grasp relationships between characters in Greek mythology representing a limited society. But the current tools of social network analysis have limits that they show the information one-sided way because of the ignorance of user-oriented design. Mitologia attempts to suggest the visual structure model more effective and easy to understand in analyzing data. We extracted connections among myth characters by evaluating classes, frequencies of appearance and emotional links they have. And we raised the understanding of users with furnishing the proper interaction to the information. The initial interface offers 4 kinds of indexes helping to access character nodes easily, while zoom-in function can be used for the detailed relations. The Zoom-in is quite different from usual filtering methods. It makes the irrelative information invisible so that users can find out the characters' relation more easily and quickly. This project suggests the layout to show overall information relationships and the appropriate interactions to present detailed information at the same time.

• Geophysics and Geophysical Exploration
• /
• v.2 no.4
• /
• pp.184-190
• /
• 1999

A study of gas hydrate is a worldwide popular interesting subject as a potential energy source. A seismic survey for gas hydrate have performed over the East sea by the KIGAM since 1997. General indicators of natural submarine gas hydrates in seismic data is commonly inferred from the BSR (Bottom Simulating Reflection) that occurred parallel to the see floor, amplitude decrease at the top of the BSR, amplitude Blanking at the bottom of the BSR, decrease of the interval velocity, and the reflection phase reversal at the BSR. So the seismic data processing for detecting gas hydrates indicators is required the true amplitude recovery processing, a accurate velocity analysis and the AVO (Amplitude Variation with Offset) analysis. In this paper, we had processed the field data to detect the gas hydrate indicators, which had been acquired over the East sea in 1998. Applied processing modules are spherical divergence, band pass filtering, CDP sorting and accurate velocity analysis. The AVO analysis was excluded, since this field data had too short offset to apply the AVO analysis. The accurate velocity analysis was performed by XVA (X-window based Velocity Analysis). This is the method which calculate the velocity spectrum by iterative and interactive. With XVA, we could determine accurate stacking velocity. Geobit 2.9.5 developed by the KIGAM was used for processing data. Processing results say that the BSR occurred parallel to the sea floor were shown at $367\~477m$ depths (two way travel time about 1800 ms) from the sea floor through shot point 1650-1900, the interval velocity decrease around BSR and the reflection phase reversal corresponding to the reflection at the sea floor.

• Composites Research
• /
• v.28 no.4
• /
• pp.232-238
• /
• 2015

As a new method to predict the degree of dispersion in carbon nanocomposites, the electrical resistance (ER) method has been evaluated. After CNT epoxy resin was dropped on CF tow, the change in electrical resistance of carbon fiber tow was measured to evaluate dispersion condition in CNT epoxy resin. Good dispersion of CNTs in carbon nanocomposite exhibited low change in ER due to wetted resin penetrated on CF tow. However, because CNT network was formed among CFs, non-uniform dispersion occurred due to nanoparticle filtering effect by CF tow. The change in ER for poor dispersion exhibited large ER signal change. The change in ER was used for the dispersion evaluation of CNT epoxy resin. Correlation between interlaminar shear strength (ILSS) and dispersion condition by ER method was established. Good CNT dispersion in nanocomposites led to good interfacial properties of fiberreinforced nanocomposites.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.2
• /
• pp.193-200
• /
• 2014

Due to the advent of ubiquitous computing environment, it is becoming a part of our common life style. And tremendous information is cumulated rapidly. In these trends, it is becoming a very important technology to find out exact information in a large data to present users. Collaborative filtering is the method based on other users' preferences, can not only reflect exact attributes of user but also still has the problem of sparsity and scalability, though it has been practically used to improve these defects. In this paper, we propose clustering method by user's features based on SOM for predicting purchase pattern in u-Commerce. it is necessary for us to make the cluster with similarity by user's features to be able to reflect attributes of the customer information in order to find the items with same propensity in the cluster rapidly. The proposed makes the task of clustering to apply the variable of featured vector for the user's information and RFM factors based on purchase history data. To verify improved performance of proposing system, we make experiments with dataset collected in a cosmetic internet shopping mall.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.51-58
• /
• 2022

Drivable area detection, one of the main functions of advanced driver assistance systems, means detecting an area where a vehicle can safely drive. The drivable area detection is closely related to the safety of the driver and it requires high accuracy with real-time operation. To satisfy these conditions, V-disparity-based method is widely used to detect a drivable area by calculating the road disparity value in each row of an image. However, the V-disparity-based method can falsely detect a non-road area as a road when the disparity value is not accurate or the disparity value of the object is equal to the disparity value of the road. In a road environment including vegetation, such as a highway and a country road, the vegetation area may be falsely detected as the drivable area because the disparity characteristics of the vegetation are similar to those of the road. Therefore, this paper proposes a drivable area detection method and hardware architecture with a high accuracy in road environments including vegetation areas by reducing the number of false detections caused by V-disparity characteristic. When 289 images provided by KITTI road dataset are used to evaluate the road detection performance of the proposed method, it shows an accuracy of 90.12% and a recall of 97.96%. In addition, when the proposed hardware architecture is implemented on the FPGA platform, it uses 8925 slice registers and 7066 slice LUTs.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.529-542
• /
• 2000

Recent years, the use of multimedia information is rapidly increasing, and the video media is the most rising one than any others, and this field Integrates all the media into a single data stream. Though the availability of digital video is raised largely, it is very difficult for users to make the effective video access, due to its length and unstructured video format. Thus, the minimal interaction of users and the explicit definition of video structure is a key requirement in the lately developing image and video management systems. This paper defines the terms and hierarchical video structure, and presents the system, which construct the clustering-based video hierarchy, which facilitate users by browsing the summary and do a random access to the video content. Instead of using a single feature and domain-specific thresholds, we use multiple features that have complementary relationship for each other and clustering-based methods that use normalization so as to interact with users minimally. The stage of shot boundary detection extracts multiple features, performs the adaptive filtering process for each features to enhance the performance by eliminating the false factors, and does k-means clustering with two classes. The shot list of a result after the proposed procedure is represented as the video hierarchy by the intelligent unsupervised clustering technique. We experimented the static and the dynamic movie videos that represent characteristics of various video types. In the result of shot boundary detection, we had almost more than 95% good performance, and had also rood result in the video hierarchy.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.4
• /
• pp.35-43
• /
• 2013

As texture images have become prevalent throughout a variety of industrial applications, copyright protection of these images has become important issues. For this reason, this paper proposes a color-texture image watermarking algorithm utilizing texture properties inherent in the image. The proposed algorithm selects suitable blocks to embed a watermark using the energy and homogeneity properties of the grey level co-occurrence matrices as inputs for the fuzzy c-means clustering algorithm. To embed the watermark, we first perform a discrete wavelet transform (DWT) on the selected blocks and choose one of DWT subbands. Then, we embed the watermark into discrete cosine transformed blocks with a gain factor. In this study, we also explore the effects of the DWT subbands and gain factors with respect to the imperceptibility and robustness against various watermarking attacks. Experimental results show that the proposed algorithm achieves higher peak signal-to-noise ratio values (47.66 dB to 48.04 dB) and lower M-SVD values (8.84 to 15.6) when we embedded a watermark into the HH band with a gain factor of 42, which means the proposed algorithm is good enough in terms of imperceptibility. In addition, the proposed algorithm guarantees robustness against various image processing attacks, such as noise addition, filtering, cropping, and JPEG compression yielding higher normalized correlation values (0.7193 to 1).