• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.202-210
• /
• 2002

During the last few years, the extraction and reconstruction of the blood vessels in the medical image has been actively researched and the analysis for the retinal vessel structure has provided important information for diagnosis and remedy of the retinopathy patients. In this research, we propose the algorithm that tracks automatically the entire retinal vessel in retinal image acquired by the ICG(IndoCyanine Green) technology. This algorithm extracts contours and centers by estimating the local maxima and processing directions and detects bifurcations and junctions by comparing direction components of the local maxima from the gradient magnitude profile of each blood vessel. We present experimental results that the entire blood vessel is automatically reconstructed and is excellent in accuracy and connectivity after applying our algorithm to the ICG retinal images of patients.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.2
• /
• pp.85-91
• /
• 2014

The objective of the research is to automatically recognize railway objects from MLS data in which 9 key objects including terrain, track, bed, vegetation, platform, barrier, posts, attachments, powerlines are targeted. The proposed method can be divided into two main sub-steps. First, multi-scale contextual features are extracted to take the advantage of characterizing objects of interest from different geometric levels such as point, line, volumetric and vertical profile. Second, by considering contextual interactions amongst object labels, a contextual classifier is utilized to make a prediction with local coherence. In here, the Conditional Random Field (CRF) is used to incorporate the object context. By maximizing the object label agreement in the local neighborhood, CRF model could compensate the local inconsistency prediction resulting from other local classifiers. The performance of proposed method was evaluated based on the analysis of commission and omission error and shows promising results for the practical use.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.11 no.2
• /
• pp.87-103
• /
• 2008

Despite its high level of symbolic and ecological values, BaigDooDaeGahn, about 684km long stretch of mountains in the eastern part of Korean peninsular, has been widely destroyed and barely recovered. While Korean government enacted a special law in 2005 to protect these areas and designated about 2,658 $km^2$ as the protection zone in 2007, there were a number of sites inside that had been disturbed by mining, illegal crop cultivations, stone quarry, development of resort facilities, construction of roads, and other human activities. To restore these damaged areas in a sustainable manner, the integrative system to categorize damaged areas for participatory restoration by local residents was suggested by this study. The most distinguished feature of the proposed system was to integrate the existing restoration approach focusing on biophysical conditions into the sustainability-building approach to reactivate socio-economic conditions of local society, called 'restoration of eco-cultural community'. As an entry stage to design the new restoration system including processes and procedures, the damaged areas had to be re-categorized by two characteristics, their physical conditions in terms of possibility of public participatory restoration and the readiness of local society required for pursuing endogenous development. More detailed considerations regarding these two characteristics and three different categories has been suggested and discussed.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.3
• /
• pp.205-208
• /
• 2013

Generally, binary pattern transforms have been used in the field of the face recognition and facial expression, since they are robust to illumination. Thus, this paper proposes an illumination-robust face recognition system combining an MLDP, which improves the texture component of the LDP, and a 2D-PCA algorithm. Unlike that binary pattern transforms such as LBP and LDP were used to extract histogram features, the proposed method directly uses the MLDP image for feature extraction by 2D-PCA. The performance evaluation of proposed method was carried out using various algorithms such as PCA, 2D-PCA and Gabor wavelets-based LBP on Yale B and CMU-PIE databases which were constructed under varying lighting condition. From the experimental results, we confirmed that the proposed method showed the best recognition accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.65-71
• /
• 2023

In this paper, we design and implement the Walking Life Festival application, which is based on the Android platform and provides information about domestic travel destinations and regional festivals in South Korea. This application utilizes various sensors found in smartphones, including the Step Counter sensor, Step Detector sensor, Acceleration sensor, and GPS sensor. Additionally, it makes use of Google Map API and Public Open API to offer information about domestic travel destinations and local festivals. The application also incorporates an automatic login feature using the Shared Preference API. When storing login information in the database, it encrypts the input plaintext data using a hash algorithm. For Google Maps integration, it creates objects using the Google.maps.LatLngBounds() method and extends the location information through the extends method. Furthermore, this application contributes to the activation of the domestic tourism industry by notifying users about the timing of local festivals related to domestic travel destinations, thus increasing their opportunities to participate in these festivals.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.27 no.6
• /
• pp.557-564
• /
• 2014

In this study, we present an algorithm that conducts an unique naming process for the bridge object through the solid object identification focused on 3D straight bridge model. For the recognition of 3D objects, the numerical algorithm utilizes centroid point, and solid object on the local coordination system. It classifies the object feature set by classifying the objects and members based on the bridge direction. By doing so, unique names, which contain the information about span, members and order of the object, were determined and the suitability of this naming algorithm was examined through a truss bridge model and a bridge model with different coordinate systems. Also, the naming process based on the object feature set was carried out for the real 3D bridge model and then was applied to the module on local server and mobile device for real bridge inspection work. From the comparison of the developed naming algorithm based on object identification and the conventional one based on field inspection, it was shown that the conventional field inspection work can be effectively improved.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.65-74
• /
• 2021

3D reconstruction means that reconstructing the 3D shape of the object in an image and a video. We proposed a progressive occupancy network architecture that can recover not only the overall shape of the object but also the local details. Unlike the original occupancy network, which uses a feature vector embedding information of the whole image, we extract and utilize the different levels of image features depending on the receptive field size. We also propose a novel network architecture that applies the image features sequentially to the decoder blocks in the decoder and improves the quality of the reconstructed 3D shape progressively. In addition, we design a novel decoder block structure that combines the different levels of image features properly and uses them for updating the input point feature. We trained our progressive occupancy network with ShapeNet. We compare its representation power with two prior methods, including prior occupancy network(ONet) and the recent work(DISN) that used different levels of image features like ours. From the perspective of evaluation metrics, our network shows better performance than ONet for all the metrics, and it achieved a little better or a compatible score with DISN. For visualization results, we found that our method successfully reconstructs the local details that ONet misses. Also, compare with DISN that fails to reconstruct the thin parts or occluded parts of the object, our progressive occupancy network successfully catches the parts. These results validate the usefulness of the proposed network architecture.

• Korea Science and Art Forum
• /
• v.23
• /
• pp.95-109
• /
• 2016

The background and objective of this study are as follows. Gwangheemun, one of the 4 small gates of Seoul Castle is a space to represent ordinary people and it is a valuable cultural heritage that shows the process of technical transition of fortification technology during Chosun Dynasty. It is a place that we can expect to play a role as a field where history and culture mix and communicate together. But currently, the environment and facilities around Gwangheemun have fallen behind and become old, so they need to be reorganized as their local feature is not shown distinctly. We need to vitalize the new traditional space that shows local feature. This study has drawn out the method, contents and the result of study like as follows. This study aims to establish an identity based on the historical and cultural backgrounds and suggest the contents to vitalize the space of Gwangheemun as a traditional cultural heritage. By this, this study aims to create a historical and cultural space where people can enjoy, eat and look around. Therefore, based on the historical and cultural feature, it gives an identity as moonlight street, and it has developed and suggested 5 contents to vitalize space: Gwangheemun maintenance, plan, castle restoration plan, village inside the castle, village outside the castle and fashion art street. Contents to vitalize space has a meaning as a specific developmen method of urban restoration, and we can expect to be used as a direction to develop the area to enhance the cultural quality of life of both inhabitants and visitors by forming the brand identity of surrounding area with traditional cultural heritage.

• Journal of KIISE:Software and Applications
• /
• v.29 no.8
• /
• pp.521-528
• /
• 2002

We propose a new approach to the feature selection for the classification of handwritten characters using two-dimensional(2D) wavelet packet bases. To extract key features of an image data, for the dimension reduction Principal Component Analysis(PCA) has been most frequently used. However PCA relies on the eigenvalue system, it is not only sensitive to outliers and perturbations, but has a tendency to select only global features. Since the important features for the image data are often characterized by local information such as edges and spikes, PCA does not provide good solutions to such problems. Also solving an eigenvalue system usually requires high cost in its computation. In this paper, the original data is transformed with 2D wavelet packet bases and the best discriminant basis is searched, from which relevant features are selected. In contrast to PCA solutions, the fast selection of detailed features as well as global features is possible by virtue of the good properties of wavelets. Experiment results on the recognition rates of PCA and our approach are compared to show the performance of the proposed method.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.187-197
• /
• 2005

In this paper, we propose a method to estimate camera motion parameter based on invariant point features, Typically, feature information of image has drawbacks, it is variable to camera viewpoint, and therefore information quantity increases after time, The LM(Levenberg-Marquardt) method using nonlinear minimum square evaluation for camera extrinsic parameter estimation also has a weak point, which has different iteration number for approaching the minimal point according to the initial values and convergence time increases if the process run into a local minimum, In order to complement these shortfalls, we, first proposed constructing feature models using invariant vector of geometry, Secondly, we proposed a two-stage calculation method to improve accuracy and convergence by using 2D homography and LM method, In the experiment, we compared and analyzed the proposed method with existing method to demonstrate the superiority of the proposed algorithms.