• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.1-9
• /
• 2012

This paper presents an algorithm for depression diagnosis using the Neural Network with Weighted Fuzzy Membership functions (NEWFM) and heart rate variability (HRV). In the algorithm, 22 different features were initially extracted from the HRV signal by frequency domain, time domain, wavelet transformed, and Poincar$\acute{e}$ transformed feature extraction methods; of these 6 optimal features were selected by significance evaluation using Non-overlap Area Distribution Measurement (NADM) based on NEWFM. The proposed algorithm uses these 6 optimal features to diagnose depression with an accuracy of 95.83%.

• Journal of the Korean Society of Systems Engineering
• /
• v.20 no.spc1
• /
• pp.90-96
• /
• 2024

In this paper, we propose a technique to model high resolution seafloor topography with 1m intervals using actual water depth data near the east coast of the Korea with 1.6km distance intervals. Using a feature point extraction algorithm that harris corner based on deep learning, the location of the center of seafloor mountain was calculated and the surrounding topology was modeled. The modeled high-resolution seafloor topography based on deep learning was verified within 1.1m mean error between the actual warder dept data. And average error that result of calculating based on deep learning was reduced by 54.4% compared to the case that deep learning was not applied. The proposed algorithm is expected to generate high resolution underwater topology for the entire Korean peninsula and be used to establish a path plan for autonomous navigation of underwater vehicle.

• Journal of Korea Multimedia Society
• /
• v.14 no.3
• /
• pp.368-377
• /
• 2011

This paper explains the hardware structure of SURF(Speeded Up Robust Feature) based feature point extractor and its FPGA verification result. SURF algorithm produces novel scale- and rotation-invariant feature point and descriptor which can be used for object recognition, creation of panorama image, 3D Image restoration. But the feature point extraction processing takes approximately 7,200msec for VGA-resolution in embedded environment using ARM11(667Mhz) processor and 128Mbytes DDR memory, hence its real-time operation is not guaranteed. We analyzed integral image memory access pattern which is a key component of SURF algorithm to reduce memory access and memory usage to operate in c real-time. We assure feature extraction that using a Vertex-5 FPGA gives 60frame/sec of VGA image at 100Mhz.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.229-232
• /
• 2009

Shot change detection is an important technique for effective management of video data, so detection scheme requires adaptive detection techniques to be used actually in various video. In this paper, we propose an adaptive shot change detection algorithm using the mean of feature value on variable reference blocks. Our algorithm determines shot change detection by defining adaptive threshold values with the feature value extracted from video frames and comparing the feature value and the threshold value. We obtained better detection ratio than the conventional methods maximally by 15% in the experiment with the same test sequence. We also had good detection ratio for other several methods of feature extraction and could see real-time operation of shot change detection in the hardware platform with low performance was possible by implementing it in TVUS model of HOMECAST Company. Thus, our algorithm in the paper can be useful in PMP or other portable players.

• Journal of Broadcast Engineering
• /
• v.20 no.5
• /
• pp.728-737
• /
• 2015

Stitching algorithm obtain a descriptor of the feature points extracted from multiple images, and create a single image through the matching process between the each of the feature points. In this paper, a feature extraction and matching techniques for the creation of a high-speed panorama using video input is proposed. Features from Accelerated Segment Test(FAST) is used for the feature extraction at high speed. A new feature point matching process, different from the conventional method is proposed. In the matching process, by tracking region containing the feature point through the Mean shift vector required for matching is obtained. Obtained vector is used to match the extracted feature points. In order to remove the outlier, the RANdom Sample Consensus(RANSAC) method is used. By obtaining a homography transformation matrix of the two input images, a single panoramic image is generated. Through experimental results, we show that the proposed algorithm improve of speed panoramic image generation compared to than the existing method.

• Journal of Biosystems Engineering
• /
• v.22 no.2
• /
• pp.227-236
• /
• 1997

Manual grading and sorting of red-ginsengs are inherently unreliable due to its subjective nature. A computerized technique based on optical and geometrical characteristics was studied for the objective quality evalution. Spectral reflectance of three categories of red-ginsengs - "Chunsam", "Chisam", "Yangsam" - were measured and analyzed. Variation of reflectance among parts of a single ginseng was more significant than variation among the quality categories of ginsengs. A PC-based image processing algorithm was developed to extract geometrical features such as length and thickness of body, length and number of roots, position of head and branch point, etc. The algorithm consisted of image segmentation, calculation of Euclidean distance, skeletonization and feature extraction. Performance of the algorithm was evaluated using sample ginseng images and found to be mostly sussessful.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.7
• /
• pp.119-128
• /
• 1994

In this paper, we propose a method for facial feature extraction and recognition algorithm using neural networks. First we extract a face part from the background image based on the knowledge that it is located in the center of an input image and that the background is homogeneous. Then using vertical and horizontal projections. We extract features from the separated face image using knowledge base of human faces. In the recognition step we use the back propagation algorithm of the neural networks and in the learning step to reduce the computation time we vary learning and momentum rates. Our technique recognizes 6 women and 14 men correctly.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.260-270
• /
• 2023

We introduce a novel Visual Inertial Odometry (VIO) algorithm designed to improve the performance of thermal-inertial odometry. Thermal infrared image, though advantageous for feature extraction in low-light conditions, typically suffers from a high noise level and significant information loss during the 8-bit conversion. Our algorithm overcomes these limitations by approximating a 14-bit raw pixel histogram into a Gaussian mixture model. The conversion method effectively emphasizes image regions where texture for visual tracking is abundant while reduces unnecessary background information. We incorporate the robust learning-based feature extraction and matching methods, SuperPoint and SuperGlue, and zero velocity detection module to further reduce the uncertainty of visual odometry. Tested across various datasets, the proposed algorithm shows improved performance compared to other state-of-the-art VIO algorithms, paving the way for robust thermal-inertial odometry.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.3
• /
• pp.317-327
• /
• 2016

The extraction of significant feature points from a video is directly associated with the suggested method's function. In particular, the occlusion regions in trees or people, or feature points extracted from the background and not from objects such as the sky or mountains are insignificant and can become the cause of undermined matching or recognition function. This paper classifies the feature points required for building recognition by using multi-frames in order to improve the recognition function(algorithm). First, through SIFT(scale invariant feature transform), the primary feature points are extracted and the mismatching feature points are removed. To categorize the feature points in occlusion regions, RANSAC(random sample consensus) is applied. Since the classified feature points were acquired through the matching method, for one feature point there are multiple descriptors and therefore a process that compiles all of them is also suggested. Experiments have verified that the suggested method is competent in its algorithm.

• Journal of Korean Institute of Industrial Engineers
• /
• v.22 no.3
• /
• pp.441-458
• /
• 1996

Many researches on feature recognition have been performed up to now, but the general solution for recognizing arbitrary features has not been developed. The most popular research area in feature recognition is automatic extraction of 2.5 dimensional features, because they are frequently used in manufacturing field. In this paper, a faster and more convenient 2.5 dimensional feature recognition algorithm is proposed using a new strategy which is quite different from the existing ones. The proposed algorithm takes process planning into consideration. The algorithm is implemented in C++. By applying the algorithm to practical complicate examples, we verify that the algorithm is working very well.