• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.542-549
• /
• 2007

Recently, many research activities in the image processing area are concentrated on developing new algorithms by finding the solution of the 'diffusion equation'. The diffusion algorithms are expected to be utilized in numerous applications including noise removal and image restoration, edge detection, segmentation, etc. In this paper, at first, it will be shown that the anisotropic diffusion algorithms have the similar structure with the adaptive FIR filters with cross-shaped 5-tap kernel, and this relatively small-sized kernel causes many iterating procedure for satisfactory filtering effects. Moreover, it will also be shown that lots of modifications which are adopted to the conventional Gaussian diffusion method in order to weaken the edge blurring nature of the linear filtering process increases another computational burden. We propose a new Median diffusion scheme by replacing the adaptive linear filters in the diffusion process with the AWM (Adaptive Weighted Median) filters. A diffusion-equation-based adaptation scheme is also proposed. With the proposed scheme, the size of the diffusion kernel can be increased, and thus diffusion speed greatly increases. Simulation results shows that the proposed Median diffusion scheme outperforms in noise removal (especially impulsive noise), and edge preservation.

• Spatial Information Research
• /
• v.13 no.2 s.33
• /
• pp.129-138
• /
• 2005

In this paper, a 3D position tracking algorithm for a moving objects using a stereo CCD cameras was proposed. This paper purposed the method to extract the coordinates of the moving objects. That is improve the operating and data processing efficiency. We were applied the relative orientation far the stereo CCD cameras and image coordinates extraction in the left and right images after the moving object segmentation. Also, it is decided on 3D position far moving objects using an acquired image coordinates in the left and right images. We were used independent relative orientation to decide the relative location and attitude of the stereo CCD cameras and RGB pixel values to segment the moving objects. To calculate the coordinates of the moving objects by space intersection. And, We conducted the experiment the system and compared the accuracy of the results.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.563-570
• /
• 2002

Robust extraction of 3D facial features and global motion information from 2D image sequence for the MPEG-4 SNHC face model encoding is described. The facial regions are detected from image sequence using multi-modal fusion technique that combines range, color and motion information. 23 facial features among the MPEG-4 FDP (Face Definition Parameters) are extracted automatically inside the facial region using color transform (GSCD, BWCD) and morphological processing. The extracted facial features are used to recover the 3D shape and global motion of the object using paraperspective camera model and SVD (Singular Value Decomposition) factorization method. A 3D synthetic object is designed and tested to show the performance of proposed algorithm. The recovered 3D motion information is transformed into global motion parameters of FAP (Face Animation Parameters) of the MPEG-4 to synchronize a generic face model with a real face.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.5
• /
• pp.259-266
• /
• 2022

In this study, we developed a deep learning and vision sensor-based assembly performance evaluation method isfor prefabricated steel structures. The assembly parts were segmented using a modified version of the receptive field block convolution module inspired by the eccentric function of the human visual system. The quality of the assembly was evaluated by detecting the bolt holes in the segmented assembly part and calculating the bolt hole positions. To validate the performance of the evaluation, models of standard and defective assembly parts were produced using a 3D printer. The assembly part segmentation network was trained based on the 3D model images captured from a vision sensor. The sbolt hole positions in the segmented assembly image were calculated using image processing techniques, and the assembly performance evaluation using the k-nearest neighbor algorithm was verified. The experimental results show that the assembly parts were segmented with high precision, and the assembly performance based on the positions of the bolt holes in the detected assembly part was evaluated with a classification error of less than 5%.

• Journal of Drive and Control
• /
• v.21 no.2
• /
• pp.53-64
• /
• 2024

Global population growth has resulted in an increased demand for food production. Simultaneously, aging rural communities have led to a decrease in the workforce, thereby increasing the demand for automation in agriculture. Drones are particularly useful for unmanned pest control fields. However, the current method of uniform spraying leads to environmental damage due to overuse of pesticides and drift by wind. To address this issue, it is necessary to enhance spraying performance through precise performance evaluation. Therefore, as a foundational study aimed at optimizing drone-based pest control technologies, this research evaluated water-sensitive paper (WSP) via density map estimation using convolutional neural networks (CNN) with a encoder-decoder structure. To achieve more accurate estimation, this study implemented multi-task learning, incorporating an additional classifier for image segmentation alongside the density map estimation classifier. The proposed model in this study resulted in a R-squared (R²) of 0.976 for coverage area in the evaluation data set, demonstrating satisfactory performance in evaluating WSP at various density levels. Further research is needed to improve the accuracy of spray result estimations and develop a real-time assessment technology in the field.

• Journal of Biomedical Engineering Research
• /
• v.36 no.2
• /
• pp.43-47
• /
• 2015

Osteoarthritis is the most common chronic joint disease in the world. With its progression, cartilage thickness tends to diminish, which causes severe pain to human being. One way to examine the stage of osteoarthritis is to measure the cartilage thickness. When it comes to inter-subject study, however, it is not easy task to compare cartilage thickness since every human being has different cartilage structure. In this paper, we propose a method to assess cartilage defect using MRI inter-subject thickness comparison. First, we used manual segmentation method to build accurate atlas images and each segmented image was labeled as articular surface and bone-cartilage interface in order to measure the thickness. Secondly, each point in the bone-cartilage interface was assigned the measured thickness so that the thickness does not change after registration. We used affine transformation and SyGN to get deformation fields which were then applied to thickness images to have cartilage thickness atlas. In this way, it is possible to investigate pixel-by-pixel thickness comparison. Lastly, the atlas images were made according to their osteoarthritis grade which indicates the degree of its progression. The result atlas images were compared using the analysis of variance in order to verify the validity of our method. The result shows that a significant difference is existed among them with p < 0.001.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.192-198
• /
• 2010

With the popularization of the mobile phone with a built-in camera, there are a lot of effort to provide useful information to users by detecting and recognizing the text in the video which is captured by the camera in mobile phone, and there is a need to detect the text regions in such mobile phone video. In this paper, we propose a method to detect the text regions in the mobile phone video. We employ morphological operation as a preprocessing and obtain binarized image using modified k-means clustering. After that, candidate text regions are obtained by applying connected component analysis and general text characteristic analysis. In addition, we increase the precision of the text detection by examining the frequency of the candidate regions. Experimental results show that the proposed method detects the text regions in the mobile phone video with high precision and recall.

• Journal of the Korean Society of Radiology
• /
• v.1 no.2
• /
• pp.23-30
• /
• 2007

This paper presents a method of generating 3-dimensional images by preprocessing 2-dimensional abdominal images obtained using CT (computed tomography) and MRI (magnetic resonance imaging) through segmentation, threshold technique, etc. and apply the method to virtual endoscopy. Three-dimensional images were visualized using indirect volume rendering, which can render at high speed using a general-purpose graphic accelerator used in personal computers. The algorithm used in the rendering is Marching Cubes, which has only a small volume of calculation. In addition, we suggested a method of producing 3-dimensional images in VRML (virtual reality modeling language) running on the Web browser without a workstation or an exclusive program. The number of nodes, the number of triangles and the size of a 3-dimensional image file from CT were 85,367, 174,150 and 10,124, respectively, and those from MRI were 34,029, 67,824 and 3,804, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.1-9
• /
• 2020

In this paper, we propose a model that performs more natural facial attribute editing by utilizing mask information in the hair and hat region. STGAN, one of state-of-the-art research of facial attribute editing, has shown results of naturally editing multiple facial attributes. However, editing hair-related attributes can produce unnatural results. The key idea of the proposed method is to additionally utilize information on the face regions that was lacking in the existing model. To do this, we apply three ideas. First, hair information is supplemented by adding hair ratio attributes through masks. Second, unnecessary changes in the image are suppressed by adding cycle consistency loss. Third, a hat segmentation network is added to prevent hat region distortion. Through qualitative evaluation, the effectiveness of the proposed method is evaluated and analyzed. The method proposed in the experimental results generated hair and face regions more naturally and successfully prevented the distortion of the hat region.

• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1332-1344
• /
• 2004

Upon development of information super-highway and multimedia-related technoiogies in recent years, more efficient technologies to transmit, store and retrieve the multimedia data are required. Among such technologies, firstly, it is common that the semantic-based image retrieval is annotated separately in order to give certain meanings to the image data and the low-level property information that include information about color, texture, and shape Despite the fact that the semantic-based information retrieval has been made by utilizing such vocabulary dictionary as the key words that given, however it brings about a problem that has not yet freed from the limit of the existing keyword-based text information retrieval. The second problem is that it reveals a decreased retrieval performance in the content-based image retrieval system, and is difficult to separate the object from the image that has complex background, and also is difficult to extract an area due to excessive division of those regions. Further, it is difficult to separate the objects from the image that possesses multiple objects in complex scene. To solve the problems, in this paper, I established a content-based retrieval system that can be processed in 5 different steps. The most critical process of those 5 steps is that among RGB images, the one that has the largest and the smallest background are to be extracted. Particularly. I propose the method that extracts the subject as well as the background by using an Image, which has the largest background. Also, to solve the second problem, I propose the method in which multiple objects are separated using RGB channel selection techniques having optimized the excessive division of area by utilizing Watermerge's threshold value with the object separation using the method of RGB channels separation. The tests proved that the methods proposed by me were superior to the existing methods in terms of retrieval performances insomuch as to replace those methods that developed for the purpose of retrieving those complex objects that used to be difficult to retrieve up until now.