• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.6
• /
• pp.280-298
• /
• 2008

For efficient content-based image retrieval, diverse visual features such as color, texture, and shape have been widely used. In the case of leaf images, further improvement can be achieved based on the following observations. Most plants have unique shape of leaves that consist of one or more blades. Hence, blade-based matching can be more efficient than whole shape-based matching since the number and shape of blades are very effective to filtering out dissimilar leaves. Guaranteeing rotational invariance is critical for matching accuracy. In this paper, we propose a new shape representation, indexing and matching scheme for leaf image retrieval. For leaf shape representation, we generated a distance curve that is a sequence of distances between the leaf’s center and all the contour points. For matching, we developed a blade-based matching algorithm called rotation invariant - partial dynamic time warping (RI-PDTW). To speed up the matching, we suggest two additional techniques: i) priority queue-based pruning of unnecessary blade sequences for rotational invariance, and ii) lower bound-based pruning of unnecessary partial dynamic time warping (PDTW) calculations. We implemented a prototype system on the GEMINI framework [1][2]. Using experimental results, we showed that our scheme achieves excellent performance compared to competitive schemes.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.189-192
• /
• 2000

벡터양자화는 신호의 압축에 이용되는 일반적인 방법이다. 그러나 유클리드 거리 등을 이용한 거리 계산량이 많아서 코드북 크기나 압축율의 제한이 있게 된다. 따라서 PDS(partial distance search)와 같은 벡터양자화 부호화의 계산량을 줄이기 위한 많은 방법들이 제안되고 있다. 본 논문에서는 이웃한 음성신호는 급격히 변하지 않고 서서히 변해가는 성질에 착안하여 현재의 벡터 다음에 발생되는 벡터를 조사하여 인덱스를 저장한 후 이를 다음 벡터의 벡터양자화 때 참고함으로써 불필요한 계산을 줄이는 방법이다. 제안한 방법으로 음성신호에 대해 실험한 결과 전탐색의 결과와 비교하여 빠른 시간에 큰 오차없이 벡터양자화 부호화를 할 수 있었다. 이 방법은 PDS와 같은 이미 제안되어 있는 많은 방법들과 같이 이용하면 더욱 효과적인 벡터양자화 부호화를 할 수 있을 것이다.

• IE interfaces
• /
• v.19 no.4
• /
• pp.270-280
• /
• 2006

The shipping plan for an efficient augmentation of terminal is NP-hard problem which is subordinate to a shipping quantity. The load location problem and stowage planning problem are two important tactical problems for the efficient operations of container terminals. This paper is concerned with reduction of feasible region in constraints for stowage planning. After designing model which minimizes the number of shifting and the travel distance of the transfer crane, the simulated annealing algorithm is employed to search optimal solution quickly and accurately. In order to apply more realistic approach, the partial restriction through adding hatch is complemented to stowage planning decision problem applied in cluster. A variety of numerical experiments demonstrated that solutions by simulated annealing algorithm are useful and applicable in practice.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.3
• /
• pp.568-576
• /
• 2003

This paper proposes a moving object tracking algorithm by using hierarchical search method in dynamic scenes. Proposed algorithm is based on two main steps: generation step of initial model from different pictures, and tracking step of moving object under the time-yawing scenes. With a series of this procedure, tracking process is not only stable under far distance circumstance with respect to the previous frame but also reliable under shape variation from the 3-dimensional(3D) motion and camera sway, and consequently, by correcting position of moving object, tracking time is relatively reduced. Partial Hausdorff distance is also utilized as an estimation function to determine the similarity between model and moving object. In order to testify the performance of proposed method, the extraction and tracking performance have tested using some kinds of moving car in dynamic scenes. Experimental results showed that the proposed algorithm provides higher performance. Namely, matching order is 28.21 times on average, and considering the processing time per frame, it is 53.21ms/frame. Computation result between the tracking position and that of currently real with respect to the root-mean-square(rms) is 1.148. In the occasion of different vehicle in terms of size, color and shape, tracking performance is 98.66%. In such case as background-dependence due to the analogy to road is 95.33%, and total average is 97%.

• Animal cells and systems
• /
• v.4 no.3
• /
• pp.267-272
• /
• 2000

Partial sequence of the mitochondrial cytochrome b gene was analyzed to investigate genetic variation from 10 geographic populations of Granulilittorina exigua in Korea. The sequence of 282 base pairs was determined by PCR-directed silver sequencing method. The sequences of two species within the genus Littorina reserved in NIH blast search were utilized to determine geographic variations of species referred. The levels of mtDNA sequence differences were 0.00-2.54% within populations and 0.71-4.43% between populations. There were four amino acid differences between representative species of the genera Granulilittorina and Littorina, but no differences within populations of the genus Granulilittorina. The UPGMA and the N-J trees based on Tamura-Nei genetic distance matrix were constructed, which showed that the genus Granulilittorina was divided into three groups such as eastern (even exception for Tokdo population), southern, and western regional populations. The degrees of genetic divergence within populations of each group were p=0.021, p=0.019, and p=0.018, respectively. The divergence between the eastern and southern populations was p=0.032, showing closer relationship than with the western populations (p=0.052). Based on the diverged time estimation, the eastern and southern populations of Granulilittorina exigua in Korea diverged from the western populations about 2.1 MYBP, and the eastern and southern populations diverged from each other about 1.3 MYBP.

• KIISE Transactions on Computing Practices
• /
• v.20 no.12
• /
• pp.652-657
• /
• 2014

Given a starting point, destination point and various Points Of Interest (POIs), which contain a full or partial order, for a user to visit we wish to create, a sequenced route from the starting point to the destination point that includes one member of each POI type in a particular order. This paper proposes a method for finding the approximate shortest route between the start point, destination point and one member of each POI type. There are currently two algorithms that perform this task but they both have weaknesses. One of the algorithms only considers the distance between the visited POI (or starting point) and POI to visit next. The other algorithm chooses candidate points near the straight-line distance between the start point and destination but does not consider the order of visits on the corresponding network path. This paper outlines an algorithm that chooses the candidate points that are nearer to the network path between the start point and destination using network search. The algorithm looks for routes using the candidate points and finds the approximate shortest route by assigning an adaptive priority to the route that visits more POIs in a short amount of time.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.211-218
• /
• 2015

This paper introduces a 'divide-and-conquer' algorithm to the travelling salesman problem (TSP). Top 10n are selected beforehand from a pool of n(n-1) data which are sorted in the ascending order of each vertex's distance. The proposed algorithm then firstly selects partial paths that are interconnected with the shortest distance $r_1=d\{v_i,v_j\}$ of each vertex $v_i$ and assigns them as individual regions. For $r_2$, it connects all inter-vertex edges within the region and inter-region edges are connected in accordance with the connection rule. Finally for $r_3$, it connects only inter-region edges until one whole Hamiltonian cycle is constructed. When tested on TSP-1(n=26) and TSP-2(n=42) of real cities and on a randomly constructed TSP-3(n=50) of the Euclidean plane, the algorithm has obtained optimal solutions for the first two and an improved one from that of Valenzuela and Jones for the third. In contrast to the brute-force search algorithm which runs in n!, the proposed algorithm runs at most 10n times, with the time complexity of $O(n^2)$.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.562-569
• /
• 2019

Raman spectroscopy has been receiving increased attention as a standoff explosive detection technique. In addition, there is a growing need for a fast search method that can identify raman spectrum for measured chemical substances compared to known raman spectra in large database. By far the most simple and widely used method is to calculate and compare the Euclidean distance between the given spectrum and the spectra in a database. But it is non-trivial problem because of the inherent high dimensionality of the data. One of the most serious problems is the high computational complexity of searching for the closet spectra. To overcome this problem, we presented the MPS Sort with Sorted Variance+PDS method for the fast algorithm to search for the closet spectra in the last paper. the proposed algorithm uses two significant features of a vector, mean values and variance, to reject many unlikely spectra and save a great deal of computation time. In this paper, we present two new methods for the fast algorithm to search for the closet spectra. the PCA+PDS algorithm reduces the amount of computation by reducing the dimension of the data through PCA transformation with the same result as the distance calculation using the whole data. the Hierarchical Cluster Tree algorithm makes a binary hierarchical tree using PCA transformed spectra data. then it start searching from the clusters closest to the input spectrum and do not calculate many spectra that can not be candidates, which save a great deal of computation time. As the Experiment results, PCA+PDS shows about 60.06% performance improvement for the MPS Sort with Sorted Variance+PDS. also, Hierarchical Tree shows about 17.74% performance improvement for the PCA+PDS. The results obtained confirm the effectiveness of the proposed algorithm.

• The Journal of Information Systems
• /
• v.31 no.3
• /
• pp.47-65
• /
• 2022

Purpose With the recent development of Big Data and Artificial Intelligence technology, self-driving technology has developed into three stages (partial self-driving) or four stages (conditional self-driving), it is expected to bring a new paradigm to transportation in the city. Although many researchers are researching related technologies, there is no research on self-driving for disabled persons. In this study, the basic research was conducted based on the assumption that the shared self-driving car used by the disabled person is similar to the special transportation currently driving. Design In this study, data analysis and machine learning techniques were utilized to analyze the mobility patterns of disabled persons by type and to search for leading factors affecting the traffic volume of special transportation. Findings The study found that external physical disorders and developmental disorders often visit general welfare centers, internal organ disorders often visit general hospitals, and the elderly and mental disorders have various destinations. In addition, machine learning analysis showed that the main transportation routes for the disabled person use arterial roads and auxiliary arterial roads and that the ratio of building usage-related variables affecting the use of special transportation for a disabled person is high. In addition, the distance to the subway and bus stops was also mentioned as a meaningful variable. Based on these analysis results, it is expected that the necessary infrastructure for shared self-driving cars for disability person traffic will be used as meaningful research data in the future.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.3 s.303
• /
• pp.39-52
• /
• 2005

In this paper, a registration method is presented to register partial 3D point clouds, acquired from a multi-view camera, for 3D reconstruction of an indoor environment. In general, conventional registration methods require a high computational complexity and much time for registration. Moreover, these methods are not robust for 3D point cloud which has comparatively low precision. To overcome these drawbacks, a projection-based registration method is proposed. First, depth images are refined based on temporal property by excluding 3D points with a large variation, and spatial property by filling up holes referring neighboring 3D points. Second, 3D point clouds acquired from two views are projected onto the same image plane, and two-step integer mapping is applied to enable modified KLT (Kanade-Lucas-Tomasi) to find correspondences. Then, fine registration is carried out through minimizing distance errors based on adaptive search range. Finally, we calculate a final color referring colors of corresponding points and reconstruct an indoor environment by applying the above procedure to consecutive scenes. The proposed method not only reduces computational complexity by searching for correspondences on a 2D image plane, but also enables effective registration even for 3D points which have low precision. Furthermore, only a few color and depth images are needed to reconstruct an indoor environment.