• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.8
• /
• pp.1031-1036
• /
• 1999

A Hierarchical vector Quantization scheme is implemented and an optimal thresholding technique of quadtree segmentation for performing high quality low bit rate image compression is proposes. A mathematical model is constructed under the assumption that the standard deviations of sub-blocks are larger than or equal to the standard deviation of the upper level block which is generated by merging of sub-blocks. This thresholding technique based on the mathematical modeling allows producing about 1 dB improved performance in terms of PSNR at most ranges of bit rates over the quadtree coder, which is based on MSE for quadtree segmentation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.295-298
• /
• 2018

The proposed paper proposes an algorithm that automatically extracts the region of interest using image processing techniques for medical images. In general, the robust boundary segmentation technique provides robust and accurate segmentation results in object boundaries with various noise and direction generated during image acquisition through optimal segmentation of the edges considering noise characteristics and directionality in noise images. In this paper, it is possible to apply adaptive filter type and size to the structural information of the image object and apply it to the boundary division of various object objects. In addition, it is possible to divide the boundary between various noise images such as an ultrasound image and an optical image.

• Land and Housing Review
• /
• v.14 no.4
• /
• pp.95-102
• /
• 2023

Numerous investigations have explored the integration of machine leaning algorithms with high-resolution drone image for object detection in urban settings. However, a prevalent limitation in vehicle extraction studies involves the reliance on bounding boxes rather than instance segmentation. This limitation hinders the precise determination of vehicle direction and exact boundaries. Instance segmentation, while providing detailed object boundaries, necessitates labour intensive labelling for individual objects, prompting the need for research on automating unsupervised instance segmentation in vehicle extraction. In this study, a novel approach was proposed for vehicle extraction utilizing unsupervised SVM classification applied to vehicle bounding boxes in drone images. The method aims to address the challenges associated with bounding box-based approaches and provide a more accurate representation of vehicle boundaries. The study showed promising results, demonstrating an 89% accuracy in vehicle extraction. Notably, the proposed technique proved effective even when dealing with significant variations in spectral characteristics within the vehicles. This research contributes to advancing the field by offering a viable solution for automatic and unsupervised instance segmentation in the context of vehicle extraction from image.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1222-1225
• /
• 2018

This paper proposes an image detection algorithm to implement gesture. By using a camera sensor, the performance of the extracted image algorithm based on the gesture pattern was verified through experiments. In addition, through the experiments, we confirmed the proposed method's possibility of the implementation. For efficient image detection, we applied a segmentation technique based on image transition which divides into small units. To improve gesture recognition, the proposed method not only has high recognition rate and low false acceptance rate in real gesture environment, but also designed an algorithm that efficiently finds optimal thresholds that can be applied.

• Journal of the Korea Society for Simulation
• /
• v.17 no.4
• /
• pp.167-174
• /
• 2008

The introduction of confocal microscopy makes it possible to observe the structural change of live neuronal cell. Neuro-degenerative disease, such as Alzheimer;s and Parkinson’s diseases are especially related to the morphological change of dendrite spine. That’s the reason for the study of segmentation and extraction from confocal microscope image. The difficulty comes from uneven intensity distribution and blurred boundary. Therefore, the image processing technique which can overcome these problems and extract the structural information should be suggested. In this paper, we propose robust structural information extracting technique with confocal microscopy images of dendrite in brain neurons. First, we apply the nonlinear diffusion filtering that enhance the boundary recognition. Second, we segment region of interest using iterative threshold selection. Third, we perform skeletonization based on Fast Marching Method that extracts centerline and boundary for analysing segmented structure. The result of the proposed method has been less sensitive to noise and has not been affected by rough boundary condition. Using this method shows more accurate and objective results.

• Journal of Internet Computing and Services
• /
• v.20 no.3
• /
• pp.33-41
• /
• 2019

In this paper, we propose a method to learn the redesigned class with background and object for semantic segmentation of indoor scene image. Semantic image segmentation is a technique that divides meaningful parts of an image, such as walls and beds, into pixels. Previous work of semantic image segmentation has proposed methods of learning various object classes of images through neural networks, and it has been pointed out that there is insufficient accuracy compared to long learning time. However, in the problem of separating objects and backgrounds, there is no need to learn various object classes. So we concentrate on separating objects and backgrounds, and propose method to learn after class simplification. The accuracy of the proposed learning method is about 5 ~ 12% higher than the existing methods. In addition, the learning time is reduced by about 14 ~ 60 minutes when the class is configured differently In the same environment, and it shows that it is possible to efficiently learn about the problem of separating the object and the background.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.450-453
• /
• 2000

In this paper, an automated segmentation algorithm is proposed for MR brain images using T1-weighted, T2-weighted, and PD images complementarily. The proposed segmentation algorithm is composed of 3 steps. In the first step, cerebrum images are extracted by putting a cerebrum mask upon the three input images. In the second step, outstanding clusters that represent inner tissues of the cerebrum are chosen among 3-dimensional (3D) clusters. 3D clusters are determined by intersecting densely distributed parts of 2D histogram in the 3D space formed with three optimal scale images. Optimal scale image best describes the shape of densely distributed parts of pixels in 2D histogram. In the final step, cerebrum images are segmented using FCM algorithm with it’s initial centroid value as the outstanding cluster’s centroid value. The proposed segmentation algorithm complements the defect of FCM algorithm, being influenced upon initial centroid, by calculating cluster’s centroid accurately And also can get better segmentation results from the proposed segmentation algorithm with multi spectral analysis than the results of single spectral analysis.

• The KIPS Transactions:PartA
• /
• v.13A no.5 s.102
• /
• pp.465-472
• /
• 2006

Recently, many suggestions have been made in image segmentation methods for extracting human organs or disease affected area from huge amounts of medical image datasets. However, images from some areas, such as brain, which have multiple structures with ambiruous structural borders, have limitations in their structural segmentation. To address this problem, clustering technique which classifies voxels into finite number of clusters is often employed. This, however, has its drawback, the influence from noise, which is caused from voxel by voxel operations. Therefore, applying image enhancing method to minimize the influence from noise and to make clearer image borders would allow more robust structural segmentation. This research proposes an efficient structural segmentation method by filtering based clustering to extract detail structures such as white matter, gray matter and cerebrospinal fluid from brain MR. First, coherence enhancing diffusion filtering is adopted to make clearer borders between structures and to reduce the noises in them. To the enhanced images from this process, fuzzy c-means clustering method was applied, conducting structural segmentation by assigning corresponding cluster index to the structure containing each voxel. The suggested structural segmentation method, in comparison with existing ones with clustering using Gaussian or general anisotropic diffusion filtering, showed enhanced accuracy which was determined by how much it agreed with the manual segmentation results. Moreover, by suggesting fine segmentation method on the border area with reproducible results and minimized manual task, it provides efficient diagnostic support for morphological abnormalities in brain.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.2
• /
• pp.81-87
• /
• 1999

In this research, we propose a field mismatch compensation method for interlaced scan image and a image restoration technique for removing motion blur. In order to compensate field mismatch, the edge classification-based linear interpolation technique and the method using the object-based motion compensation are described. We also propose an edge estimation method and an motion-based image segmentation algorithm. For removing motion blur, we adopt an adaptive iterative image restoration method using the motion-based segmentation result to improve the quality of restored image.