• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.12
• /
• pp.2547-2554
• /
• 2009

In this paper, we proposed a face detection algorithm and a hardware implementation method for ROI(Region Of Interest) of AF(Auto Focusing). We used face features in skin regions of YCbCr color space for face detection. The face features are the number of skin pixels in face regions, edge pixels in eye regions, and shadow pixels in lip regions. The each feature was statistically selected by 2,000 sample pictures of face. The proposed algorithm detects two faces that are closer center of the image for considering the effectiveness of hardware resource. The detected faces are displayed by rectangle for ROI of AF, and the rectangles are represented by positions in the image about starting point and ending point of the rectangles. The proposed face detection method was verified by using FPGA boards and mobile phone camera sensor.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.19-22
• /
• 2019

상완동맥은 어깨에서부터 팔꿈치까지 내려오는 상완골의 내측부에 존재하며 혈압을 측정할 때 사용되는 혈관이다. 이 혈관은 골절로 인해 찢어지거나, 또는 혈액순환에 문제가 생겨 혈관이 막히는 경우가 발생한다. 이러한 경우 혈관의 상태를 확인하기 위하여 색조 도플러 초음파 검사를 사용하지만, 사용자에 따라 영상을 통한 판단 기준이 다르다는 문제점이 발생한다. 따라서 본 논문에서는 FCM과 Fuzzy Decision Tree를 이용한 영상 처리를 통해 일관성 있는 판단기준을 세우기 위한 혈류의 속도를 제안한다. 색조 도플러 초음파 영상에서의 상완 동맥을 추출하여 기울기를 이용한 FCM 알고리즘을 통해 소속도를 추출한 뒤 퍼지 룰에 적용하여 의사 결정 트리로 등급을 분류하고 결과적으로 혈류 속도를 추출한다. 색조 도플러 초음파 영상에서 환자의 개인 정보를 보호하기 위해 개인 정보 영역을 제거하여 ROI 영역을 추출하고 ROI 영역을 이진화를 통하여 상완동맥이 있는 영역을 추출한다. 이진화 된 ROI 영역에서 혈관 영상의 혈류 방향으로의 무게중심을 설정하고 각각의 픽셀과 무게중심 선과의 거리를 이용하여 소속도를 추출한 후 FCM을 사용하여 최적의 기울기를 선정한다. FCM을 통해 추출한 최종 소속도를 이용하여 퍼지 룰에 적용한 뒤 계산된 T-norm과 소속도의 분산을 이용하여 의사 결정 트리를 형성 트리의 단말 노드들은 각 픽셀을 분류한다. 분류되어진 데이터들의 노드별 소속도 평균을 구한 뒤 디퍼지화를 통해 COG(Center of Gravity)를 계산한다. 마지막으로 그 값을 이용하여 혈류 속도에 영향을 미치는 정도를 계산한 뒤 최종 혈류의 속도를 제안한다.

• Imaging Science in Dentistry
• /
• v.31 no.2
• /
• pp.85-91
• /
• 2001

Purpose: To evaluate the effect of the slice thickness and the size of region of interest (ROI) on CT number using quantitative CT phantom Materials and Methods: The phantom containing 150 mg/cc, 75 mg/cc and 0 mg/cc calcium hydroxyapatite was scanned with 1, 3, 5 and 10 mm slice thicknesses by single energy quantitative computed tomography (QCT). CT numbers were measured on center position of the phantom. Shape of ROI was circular and sizes were 1, 3, 5, 11, 16, 21, 26 and 33 mm². ANOVA and Tukey's multiple comparison method were performed for statistical comparison of CT numbers according to different slice thicknesses. Coefficient of variation of CT number measured in each size of ROI was evaluated in same slice thickness. Results : CT numbers had statistically significant difference according to slice thicknesses (p<0.05). As the slice thickness increased, CT number also increased. As the density of phantom became lower and the size of ROI became smaller, the coefficient of variation of CT number increased. When the size of ROI was more than 11 mm² in 1 mm slice thickness, 5 mm² in 3 mm slice thickness and 3 mm² in 5 mm slice thickness, the coefficient of variation became consistent. In 10 mm slice thickness, the size of ROI had little effect on the coefficient of variation. Conclusion: CT number had variation according to the slice thickness and the size of ROI although the object was homogeneous. The slice thickness and the size of ROI are critical factors in precision of the CT number measurements.

• Proceedings of the KAIS Fall Conference
• /
• 2009.05a
• /
• pp.709-712
• /
• 2009

대부분의 고속도로 안개경고시스템은 시정측정을 위해 고가의 광학센서를 사용하고 있으나 운전자의 시정감각과 유사하면서도 비교적 저가인 CCTV를 이용한 시정측정에 관한 연구가 활발히 이루어지고 있다. 그러나 대부분의 CCTV를 이용한 시정측정 방법은 ROI를 기반으로 하고 있어 설치가 까다롭고 기존 CCTV를 활용하기 어렵다는 문제점을 가지고 있다. 본 논문에서는 고속도로상의 안개경고는 약 1~2Km이내의 시정일 때 발생되며, 눈으로 물체를 식별할 수 있는 최대거리가 시정이라는 기초적인 개념에 근거하여 고속도로 안개경고시스템에 사용될 수 있는 Non-ROI 기반의 실시간 CCTV 시정측정 방법을 제안한다. 이를 위해 본 논문에서는 고속도로상에 주행중인 차량의 실시간 이동영역과 가시선을 검출하고 카메라와 도로간의 상관관계를 나타내는 도로모델을 이용하여 시정측정을 수행하는 방법을 제시한다. 제안된 방법은 1~2Km 이내의 시정측정을 위한 방법으로 ROI가 필요없고 직관적이고 현실적인 주야간 시정측정이 가능하며 기존의 고속도로 CCTV에 바로 적용할 수 있다는 장점이 있다.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.983-991
• /
• 2019

This study aims to analyze movies which contain various stories according to the size of their shots. To achieve this, it is needed to classify dataset according to the shot size, such as extreme close-up shots, close-up shots, medium shots, full shots, and long shots. However, a typical video storytelling is mainly composed of close-up shots, medium shots, full shots, and long shots, it is not an easy task to construct an appropriate dataset for extreme close-up shots. To solve this, we propose an image cropping method based on the region of interest (ROI) detection. In this paper, we use the face detection and saliency detection to estimate the ROI. By cropping the ROI of close-up images, we generate extreme close-up images. The dataset which is enriched by proposed method is utilized to construct a model for classifying shots based on its size. The study can help to analyze the emotional changes of characters in video stories and to predict how the composition of the story changes over time. If AI is used more actively in the future in entertainment fields, it is expected to affect the automatic adjustment and creation of characters, dialogue, and image editing.

• Journal of Broadcast Engineering
• /
• v.11 no.3 s.32
• /
• pp.336-348
• /
• 2006

The recent advances in multimedia signal coding and transmission technologies allow lots of users to watch videos on small LCD displays. In this paper, we briefly describe an intelligent display technique to provide small-display-viewers with comfortable experiences, and study the minimum image size tolerated and utility of displaying region of interest (ROI) only when needed. The study, with 111 participants, examines minimum image size to ensure viewers pleasant viewing experiences, and evaluates the degree of satisfaction when they are viewed with region of interest (ROI) only. The experimental results show that the ROI display enhances the viewers' satisfaction when the image size becomes less than $320{\times}240$, and thus it is useful to provide the intelligent display, if necessary, which can extract and display ROI only.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.11a
• /
• pp.142-145
• /
• 2014

동영상에서의 객체 추적 알고리즘에 대한 활발한 연구가 진행되고 있음에도 불구하고 실시간 객체추적을 위해서는 여전히 정확도, 복잡도 등에서의 성능향상이 필요하다. 압축영역 기반 방식에서는 전역 움직임 보상(GMC : Global Motion Compensation)과정을 거쳐 추적하려는 객체와 배경을 구분한다. 전역 움직임 보상방법은 프레임 전 영역을 대상으로 하는 연산으로 전체 추적 시스템에서 차지하는 복잡도가 높다. 본 논문은 관심영역(ROI : Region Of Interest) 기반 전역 움직임 보상방법을 이용한 ST-MRF(Spatio-Temporal Markov Random Field)기반 추적기 고속화 방법을 제안한다. 관심영역을 기반으로 전역 움직임 보상을 적용함으로써 객체와 배경을 분리할 뿐만 아니라 알고리즘의 복잡도를 효과적으로 줄일 수 있다. 제안하는 방법의 추적성능은 평균 precision 87.29%, recall 82.58%, F-measure 83.78%로 기존방법과 비교하여 약 1%의 차이를 유지하였으며 전체 시스템의 수행시간은 평균 29.95ms로 기존방법과 비교하여 1.74배의 속도향상을 보였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.11
• /
• pp.495-502
• /
• 2014

An effective solution to the variation on scale and rotation is required to recognize contactless palmprint. In this study, we firstly minimize the variation by extracting a region of interest(ROI) according to the size and orientation of hand and normalizing the ROI. This paper proposes a contactless palmprint recognition method based on KLT(Kanade-Lukas-Tomasi) feature points. To detect corresponding feature points, texture in local regions around KLT feature points are compared. Then, we recognize palmprint by measuring the similarity among displacement vectors which represent the size and direction of displacement of each pair of corresponding feature points. An experimental results using CASIA public database show that the proposed method is effective in contactless palmprint recognition. Especially, we can get the performance of exceeding 99% correct identification rate using multiple Gabor filters.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.395-402
• /
• 2018

Human palms contain discriminative features for proving the identity of each person. In this paper, we present a novel method for user verification based on palmprints and palm veins. Specifically, the region of interest (ROI) is first determined to be forced to include the maximum amount of information with respect to underlying structures of a given palm image. The extracted ROI is subsequently enhanced by directional patterns and statistical characteristics of intensities. For multispectral palm images, each of convolutional neural networks (CNNs) is independently trained. In a spirit of ensemble, we finally combine network outputs to compute the probability of a given ROI image for determining the identity. Based on various experiments, we confirm that the proposed ensemble method is effective for user verification with palmprints and palm veins.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.813-815
• /
• 2011

This study inspects the fault of the vehicle forming assembly and the assembly state of components at high speed and high degree of precision. This study also proposes the general inspection system capable of adapting to a number of products. The inspection program is composed of the fault inspection algorithm to examine the surface of the object and the state of the assembly and the high speed procession algorithm for the real time examination. The fault inspection algorithm is processed largely by a method using average of pixel in ROI and a method dividing the area and checking the presence of the object. Lastly, we verified the efficiency of the sysytem through the evaluation of its accuracy and processing time.