• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.99-105
• /
• 2017

Generally, stereo matching methods are used to estimate depth information based on color and spatial similarity. However, most depth estimation methods suffer from the occlusion region because occlusion regions cause inaccurate depth information. Moreover, they do not consider the temporal dimension when estimating the disparity. In this paper, we propose a temporal stereo matching method, considering occlusion and disregarding inaccurate temporal depth information. First, we apply a global stereo matching algorithm to estimate the depth information, we segment the image to occlusion and non-occlusion regions. After occlusion detection, we fill the occluded region with a reasonable disparity value that are obtained from neighboring pixels of the current pixel. Then, we apply a temporal disparity estimation method using the reliable information. Experimental results show that our method detects more accurate occlusion regions, compared to a conventional method. The proposed method increases the temporal consistency of estimated disparity maps and outperforms per-frame methods in noisy images.

• Journal of the Korea Concrete Institute
• /
• v.13 no.2
• /
• pp.146-152
• /
• 2001

The fractal geometry is a non-Euclidean geometry which discribes the naturally irregular or fragmented shaps, so that it can be applied to fracture behavior of materials to investigate the fracture process. Fractal curves have a characteristic that represents a self-similarity as an invariant based on the fractal dimension. This fractal geometry was applied to the crack growth of cementitious composites in order to correlate the fracture behavior to microstructures of cemposite composites. The purpose of this study was to find relationships between fractal dimensions and fracture energy. Fracture test was carried out in order to investigate the fracture behavior of plain and fiber reinforced cement composites. The load-CMOD curve and fracture energy of the beams were observed under the three point loading system. The crack profiles were obtained by the image processing system. Box counting method was used to determine the fractal dimension, D$_{f}$. It was known that the linear correlation exists between fractal dimension and fracture energy of the cement composites. The implications of the fractal nature for the crack growth behavior on the fracture energy, G$_{f}$ is appearent.ent.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.4C
• /
• pp.397-405
• /
• 2003

In this paper, we propose an efficient motion estimation algorithm which can reduce computational complexity by using characteristics of wavelet coefficient in each subband while keeping about the same image quality as in using MRME(multiresolution motion estimation). In general, because of the high similarity between consecutive frames, we first decide whether the motion exists or not by just comparing MAD(mean absolute difference) between blocks with threshold in the lowest subbands of consecutive two frames. If it turns out that there is no motion in the lowest subband, we can also decide no motion exists in the higher subband. This is due to the characteristics of wavelet transform. Conversely, if we find any motion in the lowest subband, we can reduce computational complexity by estimating high subband motion vectors selectively according to the amount of computational complexity by estimating high subband motion vectors selectively according to the amount of energy in that subband. Experimental results are shown that algorithm suggested in this paper maintains about the same PSNR as MRME. However, the processing time was reduced about 30-50% compared with the MRME.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.9
• /
• pp.1319-1324
• /
• 2013

The mean shift algorithm has achieved considerable success in object tracking due to its simplicity and robustness. It finds local minima of a similarity measure between the color histograms or kernel density estimates of the target and candidate image. However, it is sensitive to the noises due to objects or background having similar color distributions. In addition, occlusion by another object often causes a face region to change in size and position although a face region is a critical clue to perform face recognition or compute face orientation. We assume that depth and color are effective to separate a face from a background and a face from objects, respectively. From the assumption we devised a bilateral filter using color and depth and incorporate it into the mean-shift algorithm. We demonstrated the proposed method by some experiments.

• Journal of the Korean Geographical Society
• /
• v.39 no.2
• /
• pp.283-296
• /
• 2004

More than 0.5 percent of land in Korea is used for cemetery and the rate is growing in spite of the increase in cremation these days. The systematic management of tombs may be possible through the ‘Feature Extraction’ method which is applied to the high-resolution satellite imagery. For this reason, this research focused on finding out the radiometric characteristics of tombs and the classification of them. An IKONOS image of northwest areas of Seoul with 8km x 10km dimension was analyzed. After sampling 24 tombs in the study area, the statistical radiometric characteristics of tombs are analyzed. And tombs were classified based on the criteria such as landscape, NDVI, and cluster analysis. In addition, it was investigated if the aspect or slope of the terrain influenced to the classification of tombs. As a result of this research, authors find that there is similarity between the classification tv NDVI and the classification through cluster analysis. And aspect or slope didn't have much influence on the classification of tombs.

• Journal of Korea Multimedia Society
• /
• v.9 no.5
• /
• pp.576-584
• /
• 2006

Content-based video matching is measuring a similarity of video signature compared to the original clip and copies of media. Specially, it is very important to match the exact frame position, but it depends on frame rate, noise condition and compression format of video. Ordinal signature shows good performance than other video signatures under normal condition but the previous didn't try to find the uniqueness and robustness. Hua et al. performed a uniqueness test under compressed in different formats or frame size. However, they used other compression format image instead of noise in robustness test. This paper proposes robustness test method using several noise models and analyzes the performance of robustness and uniqueness.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.1010-1014
• /
• 2010

Article-related product recommender system is an emerging e-commerce service which recommends items based on association in contexts between items and articles. Current services recommend based on the similarity between tags of articles and items, which is deficient not only due to the high cost in manual tagging but also low accuracies in recommendation. As a component of novel article-related item recommender system, we propose a new method for tagging item images based on pre-defined categories. We suggest a hypernetwork-based algorithm for learning association between images, which is represented by visual words, and categories of products. Learned hypernetwork are used to assign multiple tags to unlabeled item images. We show the ability of our method with a product set of real-world online shopping-mall including 1,251 product images with 10 categories. Experimental results not only show that the proposed method has competitive tagging performance compared with other classifiers but also present that the proposed multi-tagging method based on hypernetworks improves the accuracy of tagging.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.3
• /
• pp.81-88
• /
• 1996

Cluster analysis is based on partitioning a collection of data points into a number of clusters, where the data points in side a cluster have a certain degree of similarity and it is a fundamental process of data analysis. So, it has been playing an important role in solving many problems in pattern recognition and image processing. For these many clustering algorithms depending on distance criteria have been developed and fuzzy set theory has been introduced to reflect the description of real data, where boundaries might be fuzzy. If fuzzy cluster analysis is tomake a significant contribution to engineering applications, much more attention must be paid to fundamental questions of cluster validity problem which is how well it has identified the structure that is present in the data. Several validity functionals such as partition coefficient, claasification entropy and proportion exponent, have been used for measuring validity mathematically. But the issue of cluster validity involves complex aspects, it is difficult to measure it with one measuring function as the conventional study. In this paper, we propose four performance indices and the way to measure the quality of clustering formed by given learning strategy.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.5
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.20-25
• /
• 2021

The target-object classification method was implemented using a deep-learning-based detection model in real-time images. The object detection model was a deep-learning-based detection model that allowed extensive data collection and machine learning processes to classify similar target-objects. The recognition model was implemented by changing the processing structure of the detection model and combining developed the vision-processing module. To classify the target-objects, the identity and similarity were defined and applied to the detection model. The use of the recognition model in industry was also considered by verifying the effectiveness of the recognition model using the real-time images of an actual soccer game. The detection model and the newly constructed recognition model were compared and verified using real-time images. Furthermore, research was conducted to optimize the recognition model in a real-time environment.