• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권2호
• /
• pp.131-139
• /
• 2016

Recognition of human motions has become a main area of computer vision due to its potential human-computer interface (HCI) and surveillance. Among those existing recognition techniques for human motions, head detection and tracking is basis for all human motion recognitions. Various approaches have been tried to detect and trace the position of human head in two-dimensional (2D) images precisely. However, it is still a challenging problem because the human appearance is too changeable by pose, and images are affected by illumination change. To enhance the performance of head detection and tracking, the real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor are recently used. In this paper, we propose an effective feature extraction method, called adaptive local binary pattern (ALBP), for depth image based applications. Contrasting to well-known conventional local binary pattern (LBP), the proposed ALBP cannot only extract shape information without texture in depth images, but also is invariant distance change in range images. We apply the proposed ALBP for head detection and tracking in depth images to show its effectiveness and its usefulness.

• 한국시뮬레이션학회논문지
• /
• 제14권2호
• /
• pp.35-43
• /
• 2005

Feedwater heaters of many nuclear power plants have recently experienced wall thinning damage, which will increase as operating time progresses. As it is judged that the wall thinning damages have generated due to local fluid behavior around the impingement baffle installed in downstream of the high pressure turbine extraction steam line to avoid colliding directly with the tubes, numerical analyses using PHOENICS code were performed for two models with original clogged impingement baffle and modified multi-hole impingement baffle. To identify the relation between wall thinning and fluid behavior, the local velocity components in x-, y-, and z-directions based on the numerical analysis for the model with the clogged impingement baffle were compared with the wall thickness data by ultrasonic test. From the comparison of the numerical analysis results and the wall thickness data, the local velocity component only in the y-direction, and not in the x- and z-direction, was analogous to the wall thinning configuration. From the result of the numerical analysis for the modified impingement baffle to mitigate the shell wall thinning, it was identified that the shell wall thinning may be controlled by the reduction of the local velocity in the y-direction.

• 한국군사과학기술학회지
• /
• 제20권1호
• /
• pp.40-47
• /
• 2017

To classify the vehicle targets automatically using thermal images, there are usually two main categories of feature extraction method, local and shape feature extraction methods. Since thermal images have less texture information than color images, the shape feature extraction method is useful when the segmentation results are correct. However, if there are some errors in target segmentation, the shape feature may contain some errors, then the classification accuracy can be decreased. To overcome these problems, in this paper, we propose the segmentation reliability estimation method for target classification. The segmentation reliability can be estimated by using the difference information of average intensities and edge energies between the target and the background area. The estimated segmentation reliability is applied in the decision level fusion method of classification results using both shape and local features. Experiment results using the thermal images of the vehicle targets (main battle tank, armored personnel carrier, military truck, and an estate car) show that the proposed classification method and the segmentation reliability estimation method have a good performance in classification accuracy.

• 한국측량학회지
• /
• 제35권6호
• /
• pp.485-494
• /
• 2017

본 연구는 단순 전처리 방법과 수정된 지역적 피쳐 추출기법을 이용하여 특성이 다른 적외선영상 자동 기하보정에 초점을 맞추고 있다. 입력영상은 히스토그램 평활화를 통해 중앙값과 절댓값을 이용하여 전처리를 수행하였으며, 추출 피쳐의 유사도를 거리가 아닌 각 개념으로 변경하여 적용함으로써, 영상간 밝기값 차이를 줄이는데 효과적으로 적용할 수 있도록 하였다. 기하보정 결과는 시각적인 방법과 Inverse RMSE 방식을 사용하여 평가하였으며, 영상의 특성 차이로 인해 기존의 지역적 피쳐 추출기법 적용으로 해결될 수 없었던 자동 기하보정이 본 알고리즘을 적용함으로써 높은 정합 신뢰도와 적용 편의성을 보임을 확인할 수 있었다. 이를 통해, 제안 방법이 특정 조건의 다중 센서 영상간 자동 기하보정 기법 중 하나로 사용될 수 있을 것으로 기대한다.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제27권6호
• /
• pp.556-559
• /
• 2001

The aim of the present study was to evaluate the influences of epinephrine and pain on the changes of blood pressure and pulse rates in mandibular 3rd molar extraction. A total of 80 patients(aged between 10 and 30) without systemically compromised conditions were selected and divided into two groups(I, II). 2% lidocaine with 1:100,000 epinephrine was administered in group I (male 20, female 20), and 2% lidocaine without epinephrine was administered in group II (male 20, female 20). Systolic blood pressure and pulse rates were checked by a digital monitor during the pre-local anesthesia state(stage 1), 5 minute later in the post-local anesthesia state(stage 2), the extraction state(during odontectomy, stage 3), and during the post-suture state(stage 4). The measurement of pain perceived by patients was made using a three-point visual analog scale. The results suggest that local anesthetic with epinephrine is better at decreasing pain preventing the severe elevation of systolic blood pressure than local anesthetic without epinephrine. However, these results should be confirmed by additional studies on cardiac patients.

• Journal of Dental Anesthesia and Pain Medicine
• /
• 제21권3호
• /
• pp.245-252
• /
• 2021

Background: The aim of this study was to compare the local anesthetic effect of tramadol with that of lignocaine in the extraction of immobile (grade 0) maxillary first molars. Methods: This was a randomized, double-blind, equally balanced, controlled trial conducted on a sample population of 116 patients. The patients were randomly divided into two groups: group A (control) and group B (study). Group A and group B participants received 1.8 ml of 2% lignocaine without adrenaline and 1.8 ml of 5% tramadol, respectively through the supra-periosteal infiltration technique before extraction. Intraoperative pain was recorded on the Visual Analog Scale (VAS) and was evaluated using two unpaired t-tests. Results: Intraoperative pain was evaluated in both the control and study groups. In the control group, the mean VAS score was 0.71 ± 0.81, while in the study group, the mean intraoperative VAS score was 1.21 ± 0.86, with the difference between the two mean values being statistically significant (P = 0.001). Conclusion: Tramadol has a less potent local anesthetic effect than lignocaine. As a higher dose of tramadol is required to obtain the desired anesthetic effect, it should be used as a supplement to lignocaine in extensive surgical procedures. It can also be used in patients allergic to lignocaine.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제45권6호
• /
• pp.343-350
• /
• 2019

Objectives: The aims of this study were to determine the effectiveness of local compression in patients presenting to the emergency room with intraoral bleeding and to identify when complex haemostatic measures may be required. Materials and Methods: Five hundred forty patients who had experienced intraoral haemorrhage were retrospectively reviewed. The outcome variable was the haemostasis method used, i.e., simple (local compression with gauze) or complex (an alternative method after local compression has failed). Predictor variables were sex, age, American Society of Anesthesiologists (ASA) class, hepatic cirrhosis, bleeding disorder, use of antithrombotic agents, and site/cause of haemorrhage. Results: The mean patient age was 48.9±23.9 years, 53.5% were male, 42.8% were ASA class II or higher, and 23.7% were taking antithrombotic agents. Local compression was used most often (68.1%), followed by local haemostatic agents, sutures, systemic tranexamic acid or blood products, and electrocautery. The most common site of bleeding was the gingiva (91.7%), and the most common cause was tooth extraction (45.7%). Risk factors for needing a complex haemostasis method were use of antithrombotic agents (odds ratio 2.047, P=0.009) and minor oral surgery (excluding extraction and implant procedures; odds ratio 6.081, P=0.001). Conclusion: A haemostasis method other than local compression may be needed in patients taking antithrombotic agents or having undergone minor oral surgery.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권10호
• /
• pp.2464-2478
• /
• 2013

Image stitching techniques produce an image with a wide field-of-view by aligning multiple images with a narrow field-of-view. While conventional algorithms successfully stitch images with a small parallax, structure misalignment may occur when input images contain a large parallax. This paper presents an image stitching algorithm that aligns images with a large parallax by regional linear warping. To this end, input images are first approximated as multiple planar surfaces, and different linear warping is applied to each planar surface. For approximating input images as multiple planar surfaces, the concept of dominant edges is introduced. Dominant edges are defined as conspicuous edges of lines in input images, and extracted dominant edges identify the boundaries of each planar surface. Dominant edge extraction is conducted by detecting distinct changes of local characteristics around strong edge pixels. Experimental results show that the proposed algorithm successfully stitches images with a large parallax without structure misalignment.

• 한국인터넷방송통신학회논문지
• /
• 제9권3호
• /
• pp.61-67
• /
• 2009

인터넷의 발달로 전자문서가 증가함에 따라, 정보검색기술의 중요성도 함께 증가하게 되었다. 본 연구는 비정형 텍스트 웹 문서로부터 사용자가 요구하는 핵심 의미 지식을 추출하기 위하여 LGG(Local Grammar Graph) 구축에 기반 하여 보다 효율적이고 정확한 지식구축을 가능하게 한다. 주가등락이라는 특정 분야의 패턴을 추출하여 만든 패턴 문법을 사용해서 OWL(Web Ontology Language) 기반의 온톨로지를 구축하였다. 특정 분야의 온톨로지를 구축함으로써 기존 검색에서 할 수 없었던 지식의 의미 검색이 가능하며 나아가 사용자가 원하는 질의에 대한 정보의 추론이 가능할 것이다.

• 반도체디스플레이기술학회지
• /
• 제14권4호
• /
• pp.56-60
• /
• 2015

Mobile devices like smartphones and tablets are becoming increasingly capable in terms of processing power. Although they are already used in computer vision, no comparable measurement experiments of the popular feature extraction algorithm have been made yet. That is, local feature descriptors are widely used in many computer vision applications, and recently various methods have been proposed. While there are many evaluations have focused on various aspects of local features, matching accuracy, however there are no comparisons considering on speed trade-offs of recent descriptors such as ORB, FAST and BRISK. In this paper, we try to provide a performance evaluation of feature descriptors, and compare their matching precision and speed in KD-Tree setup with efficient computation of Hamming distance. The experimental results show that the recently proposed real valued descriptors such as ORB and FAST outperform state-of-the-art descriptors such SIFT and SURF in both, speed-up efficiency and precision/recall.