• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.151-156
• /
• 2018

In this paper, a method to classify objects in outdoor CCTV images using Convolutional Neural Network(CNN) and background subtraction is proposed. Object candidates are extracted using background subtraction and they are classified with CNN to detect objects in the image. At the end, computation complexity is highly reduced in comparison to other object detection algorithms. A database is constructed by filming alleys and playgrounds, places where crime occurs mainly. In experiments, different image sizes and experimental settings are tested to construct a best classifier detecting person. And the final classification accuracy became 80% for same camera data and 67.5% for a different camera.

• Lingua Humanitatis
• /
• v.2 no.1
• /
• pp.259-284
• /
• 2002

In the history of cinema, Sergei Eisenstein is always considered as a pioneer to conceive of cinema primarily as a form of expressing thought rather than as a representation of reality. For him, montage is the indispensable method to construct an open totality of thought and image in movement. It functions as a basic thread running through two poles of filmic composition, that is, the organic and the pathetic. The organic is concerned with the composition of the film structure as a whole, while the pathetic is involved in an ongoing process of registering a leaping point in various filmic sequences. The ultimate goal of montage for Eisenstein is to create the cinema of ideas which can synthesize both emotional and intellectual elements in the filmic composition. In his system of intellectual cinema, the identity of image and thought externalizes the sensory-motor unity of nature and man along the ascending spiral of centrifugal force of the film. Indeed, in both theory and practice, Eisenstein firmly argues that nature not only provides basic laws for the organic composition of the film, but also expresses itself in the form of the whole which brings out the experience of totality in the film text, the audience, and surely Eisenstein himself.

• Journal of Korea Game Society
• /
• v.8 no.3
• /
• pp.69-76
• /
• 2008

This paper presents a novel rendering algorithm based on sperical coordinate representation of the object. The vertices of the object are transformed into the sperical coordinate system, and we construct additional maps: the centroid and index of the triangle, the memory access table. While OpenGL rendering pipeline touches all vertices of an object, the proposed method takes account of the only visible vertices by examining the visible triangles of the object. Simulation results demonstrated that the proposed method achieve an efficient rendering performace.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.4
• /
• pp.247-258
• /
• 2020

The study investigates the influences of different factors on revisit intention to Korea of Vietnamese tourists. A mixed-method including qualitative and quantitative methodologies were utilized. A focus group of 9 experts was carried out for reviewing and exploring different factors and the conceptual model. An in-depth interview with 19 participants was developed with an aim to develop and correct measurement items. The conceptual model was tested and developed using data collected by a questionnaire, from a sample of 473 respondents, who have visited Korea by both electronic and paper surveys with non-probability and convenience sampling techniques. The questionnaire in this research applied a 5-point Likert scale and was distributed both electronically using Google form and by questionnaire paper. The Bootstrap model was used for estimating the model parameters for retesting the reliability of the estimates. Factor analysis and Structural Equation Modelling are employed to analyze the data. Results showed that 427 tourists traveling by groups organized by travel companies and 46 tourists traveling on their own. The reliability, tangibility, empathy, and assurance had influences on tourists' intention to revisit a destination, especially through satisfaction mediating construct. Destination image, self-congruity, and the emergence of Hallyu had influences intension revisit through attitude and tourist motivation.

• Journal of Information Processing Systems
• /
• v.10 no.3
• /
• pp.443-458
• /
• 2014

An extreme learning machine (ELM) is a recently proposed learning algorithm for a single-layer feed forward neural network. In this paper we studied the ensemble of ELM by using a bagging algorithm for facial expression recognition (FER). Facial expression analysis is widely used in the behavior interpretation of emotions, for cognitive science, and social interactions. This paper presents a method for FER based on the histogram of orientation gradient (HOG) features using an ELM ensemble. First, the HOG features were extracted from the face image by dividing it into a number of small cells. A bagging algorithm was then used to construct many different bags of training data and each of them was trained by using separate ELMs. To recognize the expression of the input face image, HOG features were fed to each trained ELM and the results were combined by using a majority voting scheme. The ELM ensemble using bagging improves the generalized capability of the network significantly. The two available datasets (JAFFE and CK+) of facial expressions were used to evaluate the performance of the proposed classification system. Even the performance of individual ELM was smaller and the ELM ensemble using a bagging algorithm improved the recognition performance significantly.

• Journal of Sensor Science and Technology
• /
• v.10 no.5
• /
• pp.286-291
• /
• 2001

We propose a new saliency map model for selecting an attended location in an arbitrary visual scene, which is one of the most important characteristics of human vision system. In selecting an attended location, an edge information can be considered as a feature basis to construct the saliency map. Edge filters are obtained from the independent component analysis(ICA) that is the best way to find independent edges in natural gray scenes. In order to reflect the non-uniform density in our retina, we use a multi-scaled pyramid input image instead of using an original input image. Computer simulation results show that the proposed saliency map model with multi-scale property successfully generates the plausible attended locations.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.11 no.2
• /
• pp.41-47
• /
• 2007

A fine segmentation algorithm is proposed for extracting objects in an image, which have both weak boundaries and highly non-convex shapes. The image has simple background colors or simple object colors. Two concepts, geometric attraction-driven flow (GADF) and edge-regions are combined to detect boundaries of objects in a sub-pixel resolution. The main strategy to segment the boundaries is to construct initial curves close to objects by using edge-regions and then to make a curve evolution in GADF. Since the initial curves are close to objects regardless of shapes, highly non-convex shapes are easily detected and dependence on initial curves in boundary-based segmentation algorithms is naturally removed. Weak boundaries are also detected because the orientation of GADF is obtained regardless of the strength of boundaries. For a fine segmentation, we additionally propose a local region competition algorithm to detect perceptible boundaries which are used for the extraction of objects without visual loss of detailed shapes. We have successfully accomplished the fine segmentation of objects from images taken in the studio and aphids from images of soybean leaves.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4214-4230
• /
• 2020

This paper introduces a pilot allocation scheme for massive MIMO systems based on deep convolutional neural network (CNN) learning. This work is an extension of a prior work on the basic deep learning framework of the pilot assignment problem, the application of which to a high-user density nature is difficult owing to the factorial increase in both input features and output layers. To solve this problem, by adopting the advantages of CNN in learning image data, we design input features that represent users' locations in all the cells as image data with a two-dimensional fixed-size matrix. Furthermore, using a sorting mechanism for applying proper rule, we construct output layers with a linear space complexity according to the number of users. We also develop a theoretical framework for the network capacity model of the massive MIMO systems and apply it to the training process. Finally, we implement the proposed deep CNN-based pilot assignment scheme using a commercial vanilla CNN, which takes into account shift invariant characteristics. Through extensive simulation, we demonstrate that the proposed work realizes about a 98% theoretical upper-bound performance and an elapsed time of 0.842 ms with low complexity in the case of a high-user-density condition.

• Journal of Biomedical Engineering Research
• /
• v.30 no.3
• /
• pp.233-240
• /
• 2009

Using a spatial compound imaging technique in a medical ultrasound imaging system, the average speed of sound in a medium of interest is measured, and imaging of its distribution is implemented. When the brightness reaches the highest level in an ultrasonic image obtained as the speed of sound used in focusing is varied, it turns out that the focusing has been accomplished satisfactorily and that the speed of sound which has been adopted becomes the sought-after average speed of sound. Because spatial compound imaging provides many different views of the same object, the adverse effect of erroneous speed-of-sound estimation tends to be more severe in compound imaging than in plain B-mode imaging. Thus, in compound imaging, the average speed of sound even in the case of speckled images can be accurately estimated by observing the brightness change due to different speeds of sound employed. Using this new method that offers spatial diversity, we can construct an image of the speed of sound distribution in a phantom embedded with a 10-mm diameter plastic cylinder whose speed of sound is different from that of the background. The speed of sound in the cylinder is found to be different from that of the surrounding medium.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.647-650
• /
• 2002

The human faces do not have distinct features unlike other general objects. In general the features of eyes, nose and mouth which are first recognized when human being see the face are defined. These features have different characteristics depending on different human face. In this paper, We propose a face recognition algorithm using the hidden Markov model(HMM). In the preprocessing stage, we find edges of a face using the locally adaptive threshold scheme and extract features based on generic knowledge of a face, then construct a database with extracted features. In training stage, we generate HMM parameters for each person by using the forward-backward algorithm. In the recognition stage, we apply probability values calculated by the HMM to input data. Then the input face is recognized by the euclidean distance of face feature vector and the cross-correlation between the input image and the database image. Computer simulation shows that the proposed HMM algorithm gives higher recognition rate compared with conventional face recognition algorithms.