• Ocean Systems Engineering
• /
• v.6 no.3
• /
• pp.217-231
• /
• 2016

This paper presents a new approach for underwater image analysis using the bi-dimensional empirical mode decomposition (BEMD) technique and the phase congruency information. The BEMD algorithm, fully unsupervised, it is mainly applied to texture extraction and image filtering, which are widely recognized as a difficult and challenging machine vision problem. The phase information is the very stability feature of image. Recent developments in analysis methods on the phase congruency information have received large attention by the image researchers. In this paper, the proposed method is called the EP model that inherits the advantages of the first two algorithms, so this model is suitable for processing underwater image. Moreover, the receiver operating characteristic (ROC) curve is presented in this paper to solve the problem that the threshold is greatly affected by personal experience when underwater image edge detection is performed using the EP model. The EP images are computed using combinations of the Canny detector parameters, and the binaryzation image results are generated accordingly. The ideal EP edge feature extractive maps are estimated using correspondence threshold which is optimized by ROC analysis. The experimental results show that the proposed algorithm is able to avoid the operation error caused by manual setting of the detection threshold, and to adaptively set the image feature detection threshold. The proposed method has been proved to be accuracy and effectiveness by the underwater image processing examples.

• Journal of the Korean Mathematical Society
• /
• v.55 no.3
• /
• pp.719-734
• /
• 2018

An image restoration problem with Poisson noise arises in many applications of medical imaging, astronomy, and microscopy. To overcome ill-posedness, Total Variation (TV) model is commonly used owing to edge preserving property. Since staircase artifacts are observed in restored smooth regions, higher-order TV regularization is introduced. However, sharpness of edges in the image is also attenuated. To compromise benefits of TV and higher-order TV, the weighted sum of the non-convex TV and non-convex higher order TV is used as a regularizer in the proposed variational model. The proposed model is non-convex and non-smooth, and so it is very challenging to solve the model. We propose an iterative reweighted algorithm with the proximal linearized alternating direction method of multipliers to solve the proposed model and study convergence properties of the algorithm.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.5
• /
• pp.697-704
• /
• 2003

In this paper, the visual tracking system for arbitrary shaped moving object is proposed. The established tracking system can be divided into model based method that needs previous model for target object and image based method that uses image feature. In the model based method, the reliable tracking is possible, but simplification of the shape is necessary and the application is restricted to definite target mod el. On the other hand, in the image based method, the process speed can be increased, but the shape information is lost and the tracking system is sensitive to image noise. The proposed tracking system is composed of the extraction process that recognizes the existence of moving object and tracking process that extracts dynamic characteristics and shape information of the target objects. Specially, active contour model is used to effectively track the object that is undergoing shape change. In initializatio n process of the contour model, the semi-automatic operation can be avoided and the convergence speed of the contour can be increased by the proposed effective initialization method. Also, for the efficient solution of the correspondence problem in multiple objects tracking, the variation function that uses the variation of position structure in image frame and snake energy level is proposed. In order to verify the validity and effectiveness of the proposed tracking system, real time tracking experiment for multiple moving objects is implemented.

• Journal of the Korean Wood Science and Technology
• /
• v.33 no.5 s.133
• /
• pp.29-37
• /
• 2005

A previous study verified that the SIRT (simultaneous iterative reconstruction technique) method is more efficient than the back-projection method as a CT algorithm for wood. However, it was expected that the determination of the initial model function of the SIRT method would influence the quality of CT image. Therefore, in this study, we intended to develop a technique that could be used to determine an adequate initial model function. For this purpose, we proposed several techniques, and for each technique we examined the effects of the initial model function on the average errors and the CT image at each iteration. Through this study, it was shown that the average error was decreased and the image quality was improved using the proposed techniques. This tendency was most pronounced when the back-projection method was used to determine the initial model function. From the results of this study, we drew the following conclusions: 1) The initial model function of the SIRT method should be determined with careful attention, and 2) the back-projection method efficiently determines the initial model function of the SIRT method.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2006.11a
• /
• pp.476-479
• /
• 2006

The purpose of this study is to evaluate and analyse the characteristics and images of interior environment design in the living rooms, bed rooms and kitchen of the apartment, using the e-model houses of the apartments that will be constructed by 10 construction companies and be occupied after 2006. The 29 defined terms were used in this study to describe the interior image trend. They were systematized by a 5-point scale for the SD evaluation, and were used as a tool to analyse the images. The images were evaluated by methods, such as monitoring the image photos showing the individual rooms in their e-model houses and making their slide film, and reediting them to understand interior atmospheres completely. The image evaluation was performed by the group of 2nd and 3rd year students in the Housing & Interior Design of D University on December 9, 2005, and the data were analysed using SPSS Statistical Program 12.0 for Windows.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.479-486
• /
• 2016

In this paper, the algorithm which can convert a 2D image into a 3D Model will be discussed. The 2D picture drawn by a user is scanned for image processing. The Canny algorithm is employed to find the contour. The waterfront algorithm is proposed to find foreground image area. The foreground area is segmented to decompose the complex shapes into simple shapes. Then, simple segmented foreground image is converted into 3D model to become a complex 3D model. The 3D conversion formular used in this paper is also discussed. The generated 3D model data will be useful for 3D animation and other 3D contents creation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.825-829
• /
• 2009

In this paper, we examine the fundamental performance of image coding schemes based on multipulse model. First, we introduce several kinds of pulse search methods (i.e., correlation method, pulse overlap search method and pulse amplitude optimization method) for the model. These pulse search methods are derived from auto-correlation function of impulse responses and cross-correlation function between host signals and impulse responses. Next, we explain the basic procedure of multipulse image coding scheme, which uses the above pulse search methods in order to encode the high frequency component of an original image. Finally, by means of computer simulation for some test images, we examine the PSNR(Peak Signal-to-Noise Ratio) and computational complexity of these methods.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.229-233
• /
• 2007

This study is to test the applicability of QuickBird image for non-point source pollution assessment. SWAT (Soil and Water Assessment Tool) model was adopted and the model was calibrated for a stream watershed of 255.4 $km^2$ Landsat land use data. For model application with QuickBird image, a precise agricultural land use map of 1.16 $km^2$ area located in the upstream watershed was produced by field investigation. The model was run with the combination of land use and soil map scales (1:5,000, 1:25,000 and 1:50,000). The results were compared and analyzed for the contribution of non-point source pollution by the land use scale and contents.

• Journal of the Semiconductor & Display Technology
• /
• v.10 no.3
• /
• pp.75-81
• /
• 2011

This paper presents a novel method for image classification based on a hybrid genetic algorithm (GA) and support vector machine (SVM) approach which can significantly improve the classification performance for content-based image retrieval (CBIR). Though SVM has been widely applied to CBIR, it has some problems such as the kernel parameters setting and feature subset selection of SVM which impact the classification accuracy in the learning process. This study aims at simultaneously optimizing the parameters of SVM and feature subset without degrading the classification accuracy of SVM using GA for CBIR. Using the hybrid GA and SVM model, we can classify more images in the database effectively. Experiments were carried out on a large-size database of images and experiment results show that the classification accuracy of conventional SVM may be improved significantly by using the proposed model. We also found that the proposed model outperformed all the other models such as neural network and typical SVM models.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.370-373
• /
• 2022

Recently, various deep learning framework models such as Tensorflow, Pytorch, Keras, etc. have appeared. In addition, CNN (Convolutional Neural Network) is applied to image recognition using frameworks such as Tensorflow, Pytorch, and Keras, and the optimization model in image classification is mainly used. In this paper, based on the results of training the CNN model with the Paitotchi and tensor flow frameworks most often used in the field of deep learning image recognition, the two frameworks are compared and analyzed for image analysis. Derived an optimized framework.