• 반도체디스플레이기술학회지
• /
• 제10권2호
• /
• pp.31-38
• /
• 2011

This paper introduces a video based traffic monitoring system for detecting vehicles and obstacles on the road. To segment moving objects from image sequence, we adopt the background subtraction algorithm based on the local binary patterns (LBP). Recently, LBP based texture analysis techniques are becoming popular tools for various machine vision applications such as face recognition, object classification and so on. In this paper, we adopt an extension of LBP, called the Diagonal LBP (DLBP), to handle the background subtraction problem arise in vision-based autonomous parking systems. It reduces the code length of LBP by half and improves the computation complexity drastically. An edge based shadow removal and blob merging procedure are also applied to the foreground blobs, and a pose estimation technique is utilized for calculating the position and heading angle of the moving object precisely. Experimental results revealed that our system works well for real-time vehicle localization and tracking applications.

• 대한치주과학회:학술대회논문집
• /
• 대한치주과학회 2000년도 제40회 종합학술대회 연제초록
• /
• pp.130-131
• /
• 2000

• 한국광학회:학술대회논문집
• /
• 한국광학회 1988년도 광학 및 양자전자학 워크샵
• /
• pp.68-75
• /
• 1988

The imporance and technique of sudtrating the background intensity of the interferogram in digital interferometry is discussed. Also the way of determinating the polynomial and its degree to fit the wavefront is discussed.

• 전자공학회논문지 IE
• /
• 제49권2호
• /
• pp.9-17
• /
• 2012

음성 인식 시스템의 용용에서 실제 문제점의 하나는 음성신호의 왜곡에 의한 인식성능의 저하이다. 음성신호의 왜곡에 가장 중요한 원인은 부가적인 잡음이다. 이 논문은 잡음에 강인한 음성인식을 위하여, 스펙트럼 피크 향상 기법과 효과적인 잡음 차감 기법에 기초한 스펙트럼 보상 방법을 기술한다. 제안한 방법은 음성 스펙트럼의 포먼트 구조를 향상시키고 스펙트럼 기울기를 보상하면서도 광 대역폭 스펙트럼 요소는 그대로 유지한다. 백색 가우스 잡음, 자동차 잡음, 음성 잡음 또는 지하철 잡음에 의해 왜곡된 음성을 이용한 인식실험을 수행한 결과, 새로운 방법은 스펙트럼 보상을 하지 않은 경우에 비해, 높은 SNR(Signal to Noise Ratio) 환경에서는 평균 오인식율을 약간 줄였으며, 낮은 SNR(10 dB) 환경에서는 평균 오인식율을 1/2로 크게 줄였다.

• Imaging Science in Dentistry
• /
• 제47권2호
• /
• pp.99-107
• /
• 2017

Purpose: Erosions and osteophytes are radiographic characteristics that are found in different stages of temporomandibular joint (TMJ) osteoarthritis. This study assessed the effectiveness of digital subtraction radiography (DSR) in diagnosing simulated osteophytes and erosions in the TMJ. Materials and Methods: Five intact, dry human skulls were used to assess the effectiveness of DSR in detecting osteophytes. Four cortical bone chips of varying thicknesses (0.5 mm, 1.0 mm, 1.5 mm, and 2.0 mm) were placed at the medial, central, and lateral aspects of the condyle anterior surface. Two defects of varying depth (1.0 mm and 1.5 mm) were created on the lateral, central, and medial poles of the condyles of 2 skulls to simulate erosions. Panoramic images of the condyles were acquired before and after artificially creating the changes. Digital subtraction was performed with Emago dental image archiving software. Five observers familiar with the interpretation of TMJ radiographs evaluated the images. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic accuracy of the imaging methods. Results: The area under the ROC curve (Az) value for the overall diagnostic accuracy of DSR in detecting osteophytic changes was 0.931. The Az value for the overall diagnostic accuracy of panoramic imaging was 0.695. The accuracy of DSR in detecting erosive changes was 0.854 and 0.696 for panoramic imaging. DSR was remarkably more accurate than panoramic imaging in detecting simulated osteophytic and erosive changes. Conclusion: The accuracy of panoramic imaging in detecting degenerative changes was significantly lower than the accuracy of DSR (P<.05). DSR improved the accuracy of detection using panoramic images.

• 한국멀티미디어학회논문지
• /
• 제12권10호
• /
• pp.1418-1426
• /
• 2009

주어진 배경 이미지로부터 전경 객체를 분리하는 것을 목표로 하는 배경 차분화 기법에 관한 많은 연구가 있어 왔다. 최근에 발표된 몇 가지 통계 기반 배경 차분화 기법들은 동적인 환경에서 동작할 수 있을 정도로 안정된 성능을 보이는 것으로 보고되고 있다. 그러나 이들 기법은 일반적으로 매우 많은 계산 자원을 요구하며, 객체의 명확한 윤곽을 획득하는데 있어서는 아직 어려움이 있다. 본 논문에서는 점진적으로 변화하는 배경을 모델링하기 위해 복잡한 통계 기법을 적용하는 대신 간단한 이동-평균 기법을 사용한다. 또한 픽셀별로 할당되는 다중의 임계치 대신 유전자 학습에 의해 최적화되는 하나의 전역적 임계치를 사용한다. 유전자 학습을 위해 새로운 적합도 함수를 정의하여 학습하고 이를 이용하여 이미지의 분할 결과들을 평가한다. 본 논문의 시스템은 웹 카메라가 장착된 개인용 컴퓨터에서 구현하였으며, 실사 이미지들에 대한 실험 결과에 의하면 기존의 가우시안 믹스쳐 방식보다 우수한 성능을 보이는 것으로 나타났다.

• Imaging Science in Dentistry
• /
• 제46권1호
• /
• pp.17-24
• /
• 2016

Purposes: This study employed a posteriori registration and subtraction of radiographic images to quantify the apical root resorption in maxillary permanent central incisors after orthodontic treatment, and assessed whether the external apical root resorption (EARR) was related to a range of parameters involved in the treatment. Materials and Methods: A sample of 79 patients (mean age, $13.5{\pm}2.2years$) with no history of trauma or endodontic treatment of the maxillary permanent central incisors was selected. Periapical radiographs taken before and after orthodontic treatment were digitized and imported to the Regeemy software. Based on an analysis of the post-treatment radiographs, the length of the incisors was measured using Image J software. The mean EARR was described in pixels and relative root resorption (%). The patient's age and gender, tooth extraction, use of elastics, and treatment duration were evaluated to identify possible correlations with EARR. Results: The mean EARR observed was $15.44{\pm}12.1pixels$ (5.1% resorption). No differences in the mean EARR were observed according to patient characteristics (gender, age) or treatment parameters (use of elastics, treatment duration). The only parameter that influenced the mean EARR of a patient was the need for tooth extraction. Conclusion: A posteriori registration and subtraction of periapical radiographs was a suitable method to quantify EARR after orthodontic treatment, and the need for tooth extraction increased the extent of root resorption after orthodontic treatment.

• Journal of Veterinary Science
• /
• 제24권5호
• /
• pp.65.1-65.9
• /
• 2023

Background: Bone subtraction computed tomography angiography (BSCTA) is a useful alternative technique for improving visualization of vessels surrounded by skull bone. However, no studies have compared computed tomography angiography (CTA) and BSCTA for improving the visibility of canine cerebral blood vessels. Objectives: To evaluate the potential benefit of BSCTA for better delineation of brain arteries of the circle of Willis (CoW) in dogs by comparing BSCTA with non-subtraction computed tomography angiography (NSCTA). Methods: Brain CTA was performed for nine healthy beagle dogs using a bolus tracking method with saline flushing. A total dose of 600 mgI/kg of contrast agent with an iodine content of 370 mgI/mL was injected at a rate of 4 ml/s. Bone removal was achieved automatically by subtracting non-enhanced computed tomography (CT) data from contrast CT data. Five main intracranial arteries of the CoW were analyzed and graded on a scale of five for qualitative evaluation. Results: Scores of basilar artery, middle cerebral artery, and rostral cerebral artery in the BSCTA group were significantly higher than those in the NSCTA group (p = 0.001, p = 0.020, and p < 0.0001, respectively). Scores of rostral cerebellar artery (RcA) and caudal cerebral artery (CCA) did not differ significantly between the two groups. However, scores of RcA and CCA in the BSCTA group were higher than those in the NSCTA group. Conclusions: BSCTA improved visualization of intracranial arteries of the CoW with close contact to bone. Thus, it should be recommended as a routine scan method in dogs suspected of having brain vessel disease.

• 대한임베디드공학회논문지
• /
• 제3권2호
• /
• pp.74-81
• /
• 2008

This paper describes a low-cost omnidirectional camera system designed for the intruder detection capability of a security robot. Moving targets on sequential images are detected first by an adaptive background subtraction technique, and the targets are identified as intruders if they fail to enter a password within a preset time. A warning message is then sent to the owner's mobile phone. The owner can check scene pictures posted by the system on the web. The system developed worked well in experiments including a situation when the indoor lighting was suddenly changed.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1985년도 학술발표회 논문집
• /
• pp.87-94
• /
• 1985

In this paper, enhancement of speech corrupted by additive white or colored noise is stuided. The nuconstrained frequency-domain block least-mean-square (UFBLMS) adaptation algorithm and its frequency-weighted version are newly applied to speech enhancement. For enhancement of speech degraded by white noise, the performance of the UFBLMS algorithm is superior to the spectral subtraction method or Wiener filtering technique by more than 3 dB in segmented frequency-weighted signal-to-noise ratio(FWSNERSEG) when SNR of speech is in the range of 0 to 10 dB. As for enhancement of noisy speech corrupted by colored noise, the UFBLMS algorithm is superior to that of the spectral subtraction method by about 3 to 5 dB in FWSNRSEG. Also, it yields better performance by about 2 dB in FWSNR and FWSNRSEG than that of time-domain least-mean-square (TLMS) adaptive prediction filter(APF). In view of the computational complexity and performance improvement in speech quality and intelligibility, the frequency-weighted UFBLMS algorithm appears to yield the best performance among various algorithms in enhancing noisy speech corrupted by white or colored noise.