• Journal of KIISE:Software and Applications
• /
• v.30 no.10
• /
• pp.973-982
• /
• 2003

This paper presents an efficient method for automatically detecting objects in a given image. The GHT is a robust template matching algorithm for automatic object detection in order to find objects of various shapes. Many different templates are applied by the GHT in order to find objects of various shapes and size. Every boundary detected by the GHT scan be used as an initial outline for more precise contour-finding techniques. The main weakness of the GHT is the excessive time and memory requirements. In order to overcome this drawback, the proposed algorithm uses a multiresolution search by scaling down the original image to half-sized and quarter-sized images. Using the information from the first iterative GHT on a quarter-sized image, the range of nuclear sizes is determined to limit the parameter space of the half-sized image. After the second iterative GHT on the half-sized image, nuclei are detected by the fine search and segmented with edge information which helps determine the exact boundary. The experimental results show that this method gives reduction in computation time and memory usage without loss of accuracy.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.2
• /
• pp.92-98
• /
• 2017

Data clustering determines a group of patterns using similarity measure in a dataset and is one of the most important and difficult technique in data mining. Clustering can be formally considered as a particular kind of NP-hard grouping problem. K-means algorithm which is popular and efficient, is sensitive for initialization and has the possibility to be stuck in local optimum because of hill climbing clustering method. This method is also not computationally feasible in practice, especially for large datasets and large number of clusters. Therefore, we need a robust and efficient clustering algorithm to find the global optimum (not local optimum) especially when much data is collected from many IoT (Internet of Things) devices in these days. The objective of this paper is to propose new Hybrid Simulated Annealing (HSA) which is combined simulated annealing with K-means for non-hierarchical clustering of big data. Simulated annealing (SA) is useful for diversified search in large search space and K-means is useful for converged search in predetermined search space. Our proposed method can balance the intensification and diversification to find the global optimal solution in big data clustering. The performance of HSA is validated using Iris, Wine, Glass, and Vowel UCI machine learning repository datasets comparing to previous studies by experiment and analysis. Our proposed KSAK (K-means+SA+K-means) and SAK (SA+K-means) are better than KSA(K-means+SA), SA, and K-means in our simulations. Our method has significantly improved accuracy and efficiency to find the global optimal data clustering solution for complex, real time, and costly data mining process.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.1
• /
• pp.67-72
• /
• 2000

Particularly based on the signal bias removal(SBR) algorithm for compensating the corrupted speech, this paper presents a new algorithm which is independent of environments, minimizes the amount of computation, and is readily applicable to the conventional recognition system. To this end, a multiple-bias algorithm and a partial codebook search algorithm have been added to the conventional SBR algorithm. The simulation results show that combining the two algorithms proposed in this paper provides a reduction of computation time to 1/8 times as well as an improvement of the recognition rate from 77.58% of the conventional system to 81.32%.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.101-106
• /
• 2023

With the recent surge in YouTube usage, there has been a proliferation of user-generated videos where individuals evaluate cosmetics. Consequently, many companies are increasingly utilizing evaluation videos for their product marketing and market research. However, a notable drawback is the manual classification of these product review videos incurring significant costs and time. Therefore, this paper proposes a deep learning-based cosmetics search algorithm to automate this task. The algorithm consists of two networks: One for detecting candidates in images using shape features such as circles, rectangles, etc and Another for filtering and categorizing these candidates. The reason for choosing a Two-Stage architecture over One-Stage is that, in videos containing background scenes, it is more robust to first detect cosmetic candidates before classifying them as specific objects. Although Two-Stage structures are generally known to outperform One-Stage structures in terms of model architecture, this study opts for Two-Stage to address issues related to the acquisition of training and validation data that arise when using One-Stage. Acquiring data for the algorithm that detects cosmetic candidates based on shape and the algorithm that classifies candidates into specific objects is cost-effective, ensuring the overall robustness of the algorithm.

• Journal of Korea Multimedia Society
• /
• v.11 no.3
• /
• pp.315-322
• /
• 2008

Searching a location of the copied video in video database, signatures should be robust to video reediting, channel noise, time variation of frame rate. Several kinds of signatures has been proposed. Ordinal signature, one of them, is difficult to describe the spatial characteristics of frame due to the site of fixed window, $N{\times}N$, which is compute the average gray value. In this paper, I studied an algorithm of sequence matching in video copy detection for the copyright protection, employing the R-tree index method for retrieval and suggesting a robust ordinal signatures for the original video clips and the same signatures of the pirated video. Robust ordinal has a 2-dimensional vector structures that has a strong to the noise and the variation of the frame rate. Also, it express as MBR form in search space of R-tree. Moreover, I focus on building a video copy detection method into which content publishers register their valuable digital content. The video copy detection algorithms compares the web content to the registered content and notifies the content owners of illegal copies. Experimental results show the proposed method is improve the video matching rate and it has a characteristics of signature suitable to the large video databases.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.294-297
• /
• 2005

Time series are comprehensively appeared and developed in many applications, ranging from science and technology to business and entertainrilent. Similarity search under time warping has attracted much interest between the time series in the large sequence databases. DTW (Dynamic Time Warping) is a robust distance measure and is superior to Euclidean distance for time series, allowing similarity matching although one of the sequences can elastic shift along the time axis. Nevertheless, it is more unfortunate that DTW has a quadratic time. Simultaneously the false dismissals are come forth since DTW distance does not satisfy the triangular inequality. In this paper, we propose an efficient range query algorithmbased on a new similarity search method under time warping. When our range query applies for this method, it can remove the significant non-qualify time series as early as possible before computing the accuracy DTW distance. Hence, it speeds up the calculation time and reduces the number of scanning the time series. Guaranteeing no false dismissals, the lower bounding function is advised that consistently underestimate the DTW distance and satisfy the triangular inequality. Through the experimental result, our range query algorithm outperforms the existing others.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5624-5638
• /
• 2016

A novel method based on Surf points is proposed to detect and lock-track single ground target in aerial videos. Videos captured by moving cameras contain complex motions, which bring difficulty in moving object detection. Our approach contains three parts: moving target template detection, search area estimation and target tracking. Global motion estimation and compensation are first made by grids-sampling Surf points selecting and matching. And then, the single ground target is detected by joint spatial-temporal information processing. The temporal process is made by calculating difference between compensated reference and current image and the spatial process is implementing morphological operations and adaptive binarization. The second part improves KALMAN filter with surf points scale information to predict target position and search area adaptively. Lastly, the local Surf points of target template are matched in this search region to realize target tracking. The long-term tracking is updated following target scaling, occlusion and large deformation. Experimental results show that the algorithm can correctly detect small moving target in dynamic scenes with complex motions. It is robust to vehicle dithering and target scale changing, rotation, especially partial occlusion or temporal complete occlusion. Comparing with traditional algorithms, our method enables real time operation, processing $520{\times}390$ frames at around 15fps.

• Journal of Advanced Marine Engineering and Technology
• /
• v.29 no.1
• /
• pp.116-123
• /
• 2005

The PID controllers have been widely accepted in many industrial systems due to their robust performance in a wide range of operating conditions and their functional simplicity To implement a PID controller, its three parameters must be determined for the given plant. Conventional tuning methods are mainly based on experience and experiment and are lack of systematic procedure Recently. to overcome drawbacks of conventional tuning methods, genetic algorithms have been used, In this paper a real-coded genetic algorithm is employed to search for the optimal parameters of the PID controller for speed control of marine gas turbine engines. Simulation results show the effectiveness of the proposed scheme.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.20 no.41
• /
• pp.1-14
• /
• 1997

This study proposes a genetic algorithm using Pr(equation omitted)fer number for the traveling salesman problem(PNGATSP). Nearest neighbor nodes are mixed with randomly selected nodes at the stage of generating initial solutions. Proposed PNGATSP adopts a few ideas which are different from traditional genetic algorithms. For instance, an exponential fitness function and elitism are used and Pr(equation omitted)fer number is used for encoding TSP. Genetic operators are selected by experiments, which make a good solution among four combinations of conventional genetic operators and new genetic operators. For respective combinations, robust set of parameters is determined by the experimental designing approach. The feature of Pr(equation omitted)fer number code for TSP and the search power of GA using Pr(equation omitted)fer number is analysed. The best is a combination of OX(order crossover) and swap, which is superior to the other experimented combinations of genetic operators by 1.0%∼12.8% deviation.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.729-737
• /
• 1996

Laminated composite plates have been applied to aircraft structures because their properties are superior to the conventional materials and the laminates have anisortropic elastic properties. However, it tis diffcult to determine stacking structures using actual design variables for the lack of searching capability of existing optimization technique. GA(generic algorithms) are robust search algorithms based on the mechanics of natural selection and natural genetics. Therefore, this study presents an application of IGA to stiffness and weight optimization design and gives the various stacking structures suitable to constraint conditions.