• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.6
• /
• pp.91-98
• /
• 2011

This paper proposes an efficient and accurate vision based recognition and tracking framework for texture free objects. We approached this problem with a two phased algorithm: detection phase and tracking phase. In the detection phase, the algorithm extracts shape context descriptors that used for classifying objects into predetermined interesting targets. Later on, the matching result is further refined by a minimization technique. In the tracking phase, we resorted to meanshift tracking algorithm based on Bhattacharyya coefficient measurement. In summary, the contributions of our methods for the underwater robot vision are four folds: 1) Our method can deal with camera motion and scale changes of objects in underwater environment; 2) It is inexpensive vision based recognition algorithm; 3) The advantage of shape based method compared to a distinct feature point based method (SIFT) in the underwater environment with possible turbidity variation; 4) We made a quantitative comparison of our method with a few other well-known methods. The result is quite promising for the map based underwater SLAM task which is the goal of our research.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1537-1549
• /
• 2020

The ground sample distance of KOMPSAT-3 is 0.7 m for panchromatic band, 2.8 m for multi-spectral band, and the swath width of KOMPSAT-3 is 16 km. Therefore, an image of an area wider than the swath width (16 km) cannot be acquired with a single scanning. Thus, after scanning multiple areas in units of swath width, the acquired images should be made into one image. At this time, the necessary algorithm is called image mosaicking or image stitching, and is used for cartography. Mosaic algorithm generally consists of the following 4 steps: (1) Feature extraction and matching, (2) Radiometric balancing, (3) Seamline estimation, and (4) Image blending. In this paper, we have studied an effective seamline estimation method for satellite images. As a result, we can estimate the seamline more accurately than the existing method, and the heterogeneity of the mosaiced images was minimized.

• Journal of KIISE:Software and Applications
• /
• v.37 no.8
• /
• pp.599-610
• /
• 2010

Color laser printers are nowadays abused to print or forge official documents and bills. Identifying color laser printers will be a step for media forensics. This paper presents a new method to identify color laser printers with printed color images. Since different printer companies use their own printing process, each of printed papers from different printers has a little different invisible noise. After the wiener-filter is used to analyze the invisible noises from each printer, we extract some features from these noises by calculating a gray level co-occurrence matrix. Then, these features are applied to train and classify the support vector machine for identifying the color laser printer. In the experiment, we use total 2,597 images from 7 color laser printers. The results prove that the presented identification method performs well using the noise features of color printed images.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.9-18
• /
• 2004

This paper proposes a new and simple stereo matching algorithm using the disparity space image (DSI) technique. First of all, we detect some salient feature points on each scan-line of the image pair and set the matching area using those points and define a simple cost matrix. And we take advantage of matching by pixel-by-pixel instead of using the matching window. While the pixel-by-pixel method boost up the speed of matching, because of no using neighbor information, the correctness of the matching may not be better. To cover this point, we expand the matching path using character of disparity-space-image for using neighbor information. In addition, we devise the compensated matching module using the volume of the disparity space image in order to improve the accuracy of the match. Consequently, we can reduce mismatches at the disparity discontinuities and can obtain the more detailed and correct disparity map.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.389-392
• /
• 2010

In this paper, it presents to detect location using structural information of hand from the input color images on Webcam and to recognize hand gestures. In this system, based on the skin color, the image changes a binary number and labels. Within each labeled area, we can find the Maximum Inscribed Circle using Voronoi Diagram. This circle can find the center of hand. And the circle extracts hand region from analyzing the ellipse elements to relate Maximum Inscribed Circle. We use the Maximum Inscribed Circle and the ellipse elements as characteristic of hand gesture recognition. In various environments, we cannot recognize the object that have similar colors like the background colors. But the proposed algorithm has the advantage that can be effectively eliminated about it.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.47-51
• /
• 2006

As the recent announcement of the functional cosmetics law, the need of studies on efficacy evaluation of skin related cosmetics and medical supplies has grown. Especially to identify skin improvement, we have to compare the exact parts of the skin, however up to now it is compared only by image matching that is appeared to the human eye. This study proposes the automatical image matching system for improving the accuracy of evaluation a skin improvement. Firstly we define the feature of the skin pores and wrinkles, and extract anticipation region from skin images. And then, we calculate moments for each extracted regions and classify them as pores and wrinkles. After that, we calculate the vector by computing centroids between each regions. Through this process, we compare the vector similarities and perform the matching between existing image and reference image. To verify the efficiency of the algorithm several experiments are conducted.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.2
• /
• pp.9-20
• /
• 1998

In this paper, a new distance relaying scheme is proposed. Artificial neural networks are applied to the distance relaying system composed of pattern recognition based. The proposed distance relaying scheme has two blocks of pattern recognition stages to estimate the fundamental frequency and to classify the fault types. In the first block, a filtering method using neural networks called a neural networks mapping filter(NMF) is presented to efficiently extract the features. And in the sec'ond block, the estimator called neural networks fault pattern estimator(NFPE) is also presented to classify the fault types by the extracted effective features obtained from NMF. Each block of these applied schemes is trained by back-propagation algorithm of multilayer perceptron and show the fast and accurate pattern recognition by ability of multilayer neural networks. The test result of this approach are obtained the good performance from the fault transient wave signals of EMTP(e1ectromagnetic transients program) in the various fault conditions of power systems.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.35-45
• /
• 2022

Even in recent years, treatment of first-aid patients is still often delayed due to a shortage of medical resources in marginalized areas. Research on automating the analysis of medical data to solve the problems of inaccessibility for medical services and shortage of medical personnel is ongoing. Computer vision-based medical inspection automation requires a lot of cost in data collection and labeling for training purposes. These problems stand out in the works of classifying lesion that are rare, or pathological features and pathogenesis that are difficult to clearly define visually. Anomaly detection is attracting as a method that can significantly reduce the cost of data collection by adopting an unsupervised learning strategy. In this paper, we propose methods for detecting abnormal images on chest X-RAY images as follows based on existing anomaly detection techniques. (1) Normalize the brightness range of medical images resampled as optimal resolution. (2) Some feature vectors with high representative power are selected in set of patch features extracted as intermediate-level from lesion-free images. (3) Measure the difference from the feature vectors of lesion-free data selected based on the nearest neighbor search algorithm. The proposed system can simultaneously perform anomaly classification and localization for each image. In this paper, the anomaly detection performance of the proposed system for chest X-RAY images of PA projection is measured and presented by detailed conditions. We demonstrate effect of anomaly detection for medical images by showing 0.705 classification AUROC for random subset extracted from the PadChest dataset. The proposed system can be usefully used to improve the clinical diagnosis workflow of medical institutions, and can effectively support early diagnosis in medically poor area.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.2
• /
• pp.29-33
• /
• 2010

The purpose of LiDAR ground classification is to archive both goals which are acquiring confident ground points with high precision and describing ground shape in detail. In spite of many studies about developing optimized algorithms to kick out this, it is very difficult to classify ground points and describing ground shape by airborne LiDAR data. Especially it is more difficult in a dense forested area like Korea. Principle misclassification was mainly caused by complex forest canopy hierarchy in Korea and relatively coarse LiDAR points density for ground classification. Unfortunately, a lot of LiDAR surveying performed in summer in South Korea. And by that reason, schematic LiDAR points distribution is very different from those of Europe. So, this study propose enhanced ground classification method considering Korean land cover characteristics. Firstly, this study designate highly confident candidated LiDAR points as a first ground points which is acquired by using big roller classification algorithm. Secondly, this study applied weighted gradient kernel(WGK) algorithm to find and include highly expected ground points from the remained candidate points. This study methods is very useful for reconstruct deformed terrain due to misclassification results by detecting and include important terrain model key points for describing ground shape at site. Especially in the case of deformed bank side of river area, this study showed highly enhanced classification and reconstruction results by using WGK algorithm.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.6
• /
• pp.645-651
• /
• 2012

In this paper, we propose a new method for stabilizing the image captured from a camera mounted on a buoy robot. In this study, in order to solve the problem of cumulative errors and noise produced by a general gyro sensor measuring the orientation angle of the buoy robot, we propose new method for stabilizing the image. In this method, image processing techniques are combined with a newly designed target mounting mechanism that adapts to wave fluctuations. New target extraction and angle estimation techniques are introduced, along with the new mounting mechanism used for the camera and the target, which produce a stabilized image even if the buoy robot is on fluctuating waves.