• Journal of Korea Multimedia Society
• /
• v.15 no.10
• /
• pp.1196-1204
• /
• 2012

In this paper, a series of algorithms are proposed for controlling different kinds of multimedia contents and realizing interact between human and computer by using single input device. Human gesture recognition based on NUI is presented firstly in my paper. Since the image information we get it from camera is not sensitive for further processing, we transform it to YCbCr color space, and then morphological processing algorithm is used to delete unuseful noise. Boundary Energy and depth information is extracted for hand detection. After we receive the image of hand detection, PCA algorithm is used to recognize hand posture, difference image and moment method are used to detect hand centroid and extract trajectory of hand movement. 8 direction codes are defined for quantifying gesture trajectory, so the symbol value will be affirmed. Furthermore, HMM algorithm is used for hand gesture recognition based on the symbol value. According to series of methods we presented, we can control multimedia contents by using human gesture recognition. Through large numbers of experiments, the algorithms we presented have satisfying performance, hand detection rate is up to 94.25%, gesture recognition rate exceed 92.6%, hand posture recognition rate can achieve 85.86%, and face detection rate is up to 89.58%. According to these experiment results, we can control many kinds of multimedia contents on computer effectively, such as video player, MP3, e-book and so on.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.556-565
• /
• 2009

In this paper, we propose a CAD software framework to automatically generate a shop drawing. Shop drawing is to draw the geometric figures representing an arrangement of steel bars for a concrete building on its structural design, based on its construction specifications and the design rules, and its well-formed process lead to be automated. A key point of the design automation is to minimize the user interactions by automatically recognizing the design specifications and to finally generate the shape of the geometric figures. The graphic pipeline of the proposed framework consists of four stages; a specification DB, specification extraction, binding, and rendering. To effectively extract all specifications only for a figure from the DB and bind them to its shape, we use a hierarchical approach; the specifications are classified into three common, structural, and figure classes, and each attribute is extracted in design phases. Based on our framework, we implemented a specialized CAD for shop drawing using AutoCAD and could easily update it according to user's demands.

• Korean Journal of Remote Sensing
• /
• v.24 no.2
• /
• pp.117-124
• /
• 2008

This paper introduces a novel approach for automated mapping of a map feature that is vinyl green house in high spatial resolution imagery Some map features have their unique spatial patterns. These patterns are normally detected in high spatial resolution remotely sensed data by human recognition system. When spatial patterns can be applied to map feature identification, it will improve image classification accuracy and will be contributed a lot to feature identification. In this study, an automated feature identification approach using spatial aucorrelation is developed, specifically for the vinyl green house that has distinctive spatial pattern in its array. The algorithm aimed to develop the method without any human intervention such as digitizing. The method can investigate the characteristics of repeated spatial pattern of vinyl green house. The repeated spatial pattern comes from the orderly array of vinyl green house. For this, object-based approaches are essential because the pattern is recognized when the shapes that are consists of the groups of pixels are involved. The experimental result shows very effective vinyl house extraction. The targeted three vinyl green houses were exactly identified in the IKONOS image for a part of Jeju area.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.29-37
• /
• 2021

In this paper, we propose a deep learning-based retinal vessel segmentation model for handling multi-scale information of fundus images. we integrate the selective kernel convolution into U-Net-based convolutional neural network. The proposed model extracts and segment features information with various shapes and sizes of retinal blood vessels, which is important information for diagnosing eye-related diseases from fundus images. The proposed model consists of standard convolutions and selective kernel convolutions. While the standard convolutional layer extracts information through the same size kernel size, The selective kernel convolution extracts information from branches with various kernel sizes and combines them by adaptively adjusting them through split-attention. To evaluate the performance of the proposed model, we used the DRIVE and CHASE DB1 datasets and the proposed model showed F1 score of 82.91% and 81.71% on both datasets respectively, confirming that the proposed model is effective in segmenting retinal blood vessels.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.450-460
• /
• 2005

Today, multimedia information is used on the internet and various social areas by rapid development of computer and communication technology. Therefor, the usage is growing dramatically. Multimedia information analysis system is basically based on text. So, there are many difficult problems like expressing ambiguity of multimedia information, excessive burden of works in appending notes and a lack of objectivity. In this study, we suggest a method which uses color and shape information of multimedia image partitions efficiently analyze a large amount of multimedia information. Partitions use field growth and union method. To extract color information, we use distinctive information which matches with a representative color from converting process from RGB(Red Green Blue) to HSI(Hue Saturation Intensity). Also, we use IMI(Improved Moment Invariants) which target to only outline pixels of an object and execute computing as shape information.

• Journal of Satellite, Information and Communications
• /
• v.9 no.1
• /
• pp.57-64
• /
• 2014

Recently, many human-friendly communication methods have been studied for human-machine interface(HMI) without using any physical devices. One of them is the vision-based gesture recognition that this paper deals with. In this paper, we define some gestures for interaction with objects in a predefined virtual world, and propose an efficient method to recognize them. For preprocessing, we detect and track the both hands, and extract their silhouettes from the low-resolution hand images captured by a webcam. We modeled skin color by two Gaussian distributions in RGB color space and use blob-matching method to detect and track the hands. Applying the foodfill algorithm we extracted hand silhouettes and recognize the hand shapes of Thumb-Up, Palm and Cross by detecting and analyzing their modes. Then, with analyzing the context of hand movement, we recognized five predefined one-hand or both-hand gestures. Assuming that one main user shows up for accurate hand detection, the proposed gesture recognition method has been proved its efficiency and accuracy in many real-time demos.

• Journal of the Korea Computer Graphics Society
• /
• v.7 no.2
• /
• pp.11-19
• /
• 2001

This paper proposes a colored paper mosaic rendering technique based on image segmentation that can automatically generate torn and tagged colored paper mosaic effect. and 3D effect that come about in human-made mosaic work can be represented by generating shadow using difference of paper thickness. Previous method did not produce satisfactory results due to the ineffectiveness of having to use pieces of the same size. The proposed two methods for determination of paper shape and location that are based on segmentation can subdivide image area by considering characteristics of image. The first method is to generate Voronoi polygon after subdividing the segmented image again using quad tree. And the second method is to apply the Voronoi diagram on each segmentation layer. Through these methods, the characteristic of the image is expressed in more detail than previous colored paper mosaic rendering method and these methods enable to produce image that is closer to human-made mosaic work.

• Journal of Digital Contents Society
• /
• v.13 no.3
• /
• pp.343-352
• /
• 2012

In this paper, we implemented a touchless interface for DID(Digital Information Display) system using gesture recognition technique which includes both hand motion and hand shape recognition. Especially this touchless interface without extra attachments gives user both easier usage and spatial convenience. For hand motion recognition, two hand-motion's parameters such as a slope and a velocity were measured as a direction-based recognition way. And extraction of hand area image utilizing YCbCr color model and several image processing methods were adopted to recognize a hand shape recognition. These recognition methods are combined to generate various commands, such as, next-page, previous-page, screen-up, screen-down and mouse -click in oder to control DID system. Finally, experimental results showed the performance of 93% command recognition rate which is enough to confirm the possible application to commercial products.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.4
• /
• pp.9-16
• /
• 2020

Pronunciation recognition systems that use only video information and ignore voice information can be applied to various customized services. In this paper, we develop a system that applies a Bayesian classifier to distinguish Korean vowels via lip shapes in images. We extract feature vectors from the lip shapes of facial images and apply them to the designed machine learning model. Our experiments show that the system's recognition rate is 94% for the pronunciation of 'A', and the system's average recognition rate is approximately 84%, which is higher than that of the CNN tested for comparison. Our results show that our Bayesian classification method with feature values from lip region landmarks is efficient on a small training set. Therefore, it can be used for application development on limited hardware such as mobile devices.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.4
• /
• pp.239-245
• /
• 2010

Previous painterly rendering techniques normally use image gradients for stroke generation. Although image gradients are useful for expressing object shapes, it is difficult to express the flow or movements of objects of objects. In real painting, the use of brush strokes corresponding to the actual movement of objects allows viewers to recognize objects’ motion better and express the liveliness of the objects much more. In this paper, we propose a novel painterly stroke generation algorithm to express dynamic objects based on their motion information. We first extract motion information (magnitude, direction) of a scene from a set of image sequences from the same view. Then the motion directions are used for determining stroke orientations in the regions with significant motions. Where little motion is observed, image gradients are used for determining stroke orientations. Our algorithm is useful for realistically and dynamically representing moving objects.