• Journal of Biosystems Engineering
• /
• v.21 no.4
• /
• pp.414-421
• /
• 1996

한국과 일본의 경우 건표고를 외관의 품질상태 에 따라 12등급에서 16등급으로 구분하고 있다. 그리고 등급판정 작업은 임의로 추출한 샘플을 대상으로 전문 감정가에 의해 수작업으로 수행되고 있다. 건표고의 품질을 결정짓는 외관의 품질인자들은 갓과 내피에 고루 분포하고 있다. 본 논문에서는 컴퓨터 영상처리 시스템에 의거하여 개발한 건표고 자동 등급판정 및 선별 시작시스템의 구조와 기능 그리고 성능에 대하여 설명하였다. 개발한 시작시스템은 표고의 이송과 취급자동화를 위한 진동이송기, 반전장치, 컨베이어 이송장치와 두 세트의 컴퓨터 영상처리 시스템, 그리고 시스템 통괄제어를 위한 IBM PC AT호환 컴퓨터, 디지털 입출력 보드, 전공압실린더 구동제어를 위한 PLC등으로 구성하였다. 등급판정의 효율성 및 실시간 작업시스템을 고려하여 건표고의 등급판정은 두 세트의 컴퓨터 영상처리 시스템을 이용하여 이송되는 건표고의 갓 또는 내피 중 어디가 위를 향하는 지에 따라 두 단계에 걸쳐 독립적으로 판정을 수행하도록 하였다. 첫 번째 영상처리부에서는 갓표면 영상으로부터 4등급의 고품질 표고를 분류하며 두 번째 영상처리부에서는 내피표면 영상으로부터 중간 및 저품질 표고를 8개의 등급으로 분류한다. 실시간 영상정보처리를 목적으로 기존에 개발한 신경회로망을 이용한 등급판정 알고리즘을 시작시스템에 적용하였다. 개발한 시작기는 88% 이상의 등급판정 정확도를 보여 주었으며, 전공압시스템의 구동제약으로 인하여 표고 1개당 약0.7초의 선별시간이 소요되었다. 일조 선별라인의 경우 본 연구에서 제안한 시작기의 선별능력은 표고가 일차 처리부로 갓이 위로 올라와 있는 상태로 계속 공급된다면 시간당 대략 5,000여 개의 표고를 처리할 수 있을 것으로 기대된다.보강하여 가능하면 B-Pillar의 Middle이 Bending type collapse을 방지하여 Pelvis와 Door가 먼저 접촉하는 방법 등이 적용가능하다. 제작하기 이전에 설계된 부품에 대한 스프링 상수 및 내구특성을 체계적으로 규명하여 제품 시험의 횟수를 줄이고, 보다 정밀한 제품을 제작할 수 있도록 하기 위한 것이다.세포수는 초기 배반포기배에서 팽윤 배반포기배로 진행됨에 따라 두배에서 세배 정도 증가되었음을 알 수 있었다. 또한, differential labelling과 bisbenzimide기법에서 얻어진 각각의 총세포수를 비교하였을 때 총세포수는 발달의 진행 정도에 따라 증가되며 그와 동시에 동일한 군 간의 세포수도 거의 유사함을 알 수 있었다. 따라서, ICM과 TE를 differential labelling하는 기법은 수정란의 quality를 평가하는데 매우 유용한 기법으로서 착상전 embryo 발달을 연구하는데 효과적으로 이용될 수 있다는 것을 시사한다. 고도의 유의차를 나타낸 반면 비수구, 초생수로구 및 Bromegrass 목초구 간에는 아무런 유의차가 인정되지 않았다. 7. 농지보전 처리구인 배수구와 초생수로구는 비처리구에 비해 낮은 침두 유출량과 낮은 토양유실량을 나타내었다.구보다 14% 절감되는 것으로 나타났다.작용하는 것으로 사료된다.된다.정량 분석한 결과이다. 시편의 조성은 33.6 at% U, 66.4 at% O의 결과를 얻었다. 산화물 핵연료의 표면 관찰 및 정량 분석 시험시 시편 표면을 전도성 물질로 증착시키지 않고, Silver Paint 에 시편을 접착하는 방법으로도 만족한 시험 결과를 얻을 수 있었다.째, 회복기 중에 일어나는 입자들의 유입은 자기폭풍의 지속시간을 연장시키는 경향을 보이며 큰

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.10
• /
• pp.427-436
• /
• 2013

In this paper, a method of moving path control of an automatic guided vehicle in an indoor environment through recognition of marker images using vision sensors is presented. The existing AGV moving control system using infrared-ray sensors and landmarks have faced at two critical problems. Since there are many windows in a crematorium, they are going to let in too much sunlight in the main hall which is the moving area of AGVs. Sunlight affects the correct recognition of landmarks due to refraction and/or reflection of sunlight. The second one is that a crematorium has a narrow indoor environment compared to typical industrial fields. Particularly when an AVG changes its direction to enter the designated furnace the information provided by guided sensors cannot be utilized to estimate its location because the rotating space is too narrow to get them. To resolve the occurrences of such circumstances that cannot access sensing data in a WSN environment, a relative distance from marker to an AGV will be used as fingerprinting used for location estimation. Compared to the existing fingerprinting method which uses RSS, our proposed method may result in a higher reliable estimation of location. Our experimental results show that the proposed method proves the correctness and applicability. In addition, our proposed approach will be applied to the AGV system in the crematorium so that it can transport a dead body safely from the loading place to its rightful destination.

• Journal of Bio-Environment Control
• /
• v.7 no.3
• /
• pp.226-236
• /
• 1998

If the lowest leaves of the cucumber were removed or training cultivable method was changed, a computer vision system could divide well the cucumber fruit from the others, and also an end-effector could reach and grip cucumber fruit and cut well its fruit stalk. Therefore, this study investigated whether removal leaves and training cultivable method of a cucumber could affect its growth and yield. They can help to be designed the vision system and the end-effector. A cucumber fruit grew by 6-l5cm long for 2 days regardless of removing leaves. Removal leaves didn't affect growth of cucumber fruit. Number of cucumber fruit was produced within 10% different values by three methods (A, B, C) of removal leaves. The first grade rate (best quality) of 4 B and C was 56.7%, 53.1%, 56.3% respectively. Consequently, proper removal leaves were better than traditional way, which does not remove a leaf, because they make cucumber plant ventilate more freely and absorb more light.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.6
• /
• pp.315-320
• /
• 2017

Estimating the correct pose of augmented objects on the real camera view efficiently is one of the most important questions in image tracking area. In computer vision, Homography is used for camera pose estimation in augmented reality system with markerless. To estimating Homography, several algorithm like SURF features which extracted from images are used. Based on extracted features, Homography is estimated. For this purpose, RANSAC algorithm is well used to estimate homography and DCS-RANSAC algorithm is researched which apply constraints dynamically based on Constraint Satisfaction Problem to improve performance. In DCS-RANSAC, however, the dataset is based on pattern of feature distribution of images manually, so this algorithm cannot classify the input image, pattern of feature distribution is not recognized in DCS-RANSAC algorithm, which lead to reduce it's performance. To improve this problem, we suggest the KCS-RANSAC algorithm using K-means clustering in CS-RANSAC to cluster the images automatically based on pattern of feature distribution and apply constraints to each image groups. The suggested algorithm cluster the images automatically and apply the constraints to each clustered image groups. The experiment result shows that our KCS-RANSAC algorithm outperformed the DCS-RANSAC algorithm in terms of speed, accuracy, and inlier rate.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.24 no.2
• /
• pp.279-290
• /
• 1994

The purpose of this study was to compare the diagnostic accuracy of periapical radiographs and their digitized images for the detection of simulated interproximal carious lesions. A total of 240 interproximal surfaces was used in this study. The case sample was composed of 80 anterior teeth, 80 bicuspids and 80 molars which were prepared in order to distribute the surfaces from carious free to those containing simulated carious lesions of varying depths (0.5㎜, 0.8㎜, and 1.2㎜). The periapical radiographs were taken by paralleling technique and film used was Kodak Ektaspeed(E group). All radiographs were evaluated by five dentist to recognize the true status of simulated carious lesion. They were asked to give a score of 0, 1, 2, or 3. Digitized images were obtained using a commercial video processor(FOTOVIX Ⅱ- XS). And the computer system was 486 DX PC with PC Vision and frame grabber. The 17' display monitor had a resolution of 1280×1024 pixels(0.26㎜ dot pitch). But the one frame of the intraoral radiograph has a resolution of 700×480 pixels and each pixel has a grey level value of 256. All the radiographs and digital images were viewed under uniform subdued lighting in the same reading room. After a week the second interpretation was performed in the same condition. The detection of lesions on the monitor was compared with the finding of simulated interproximal carious lesions on the film images. The results were as follows: 1. When the scoring criteria was dichotomous ; lesion present and not present 1) The overall sensitivity, specificity and diagnostic accuracy of periapical radiographs and their digital images showed no statistically significant difference. 2) The sensitivity and specificity according to the region of teeth and the grade of lesions showed no statistically significant difference between periapical radiographs and their digital images. 2. When estimate the grade of lesions ; score 0, 1, 2, 3 1) The overall diagnostic accuracy was 53.3% on the intraoral films and 52.9% on digital images. There was no significant difference. 2) The diagnostic accuracy according to the region of teeth showed no statistically significant difference between periapical radiographs and their digital images. 3. The degree of agreement and reliability 1) Using gamma value to show the degree of agreement, there was similarity between periapical films and digital images. 2) The reliability of each twice interpretation of periapical films and digital images showed no statistically significant difference. In all cases P value was greater than 0.05, showing that both techniques can be used to detect the incipient and moderate interproximal carious lesions with similar accuracy.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.157-168
• /
• 2016

In image processing and computer vision fields, mean squared error (MSE) has popularly been used as an objective metric in image quality optimization problems due to its desirable mathematical properties such as metricability, differentiability and convexity. However, as known that MSE is not highly correlated with perceived visual quality, much effort has been made to develop new image quality assessment (IQA) metrics having both the desirable mathematical properties aforementioned and high prediction performances for subjective visual quality scores. Although recent IQA metrics having the desirable mathematical properties have shown to give some promising results in prediction performance for visual quality scores, they also have high computation complexities. In order to alleviate this problem, we propose a new fast IQA metric using a simple Laplace operator. Since the Laplace operator used in our IQA metric can not only effectively mimic operations of receptive fields in retina for luminance stimulus but also be simply computed, our IQA metric can yield both very fast processing speed and high prediction performance. In order to verify the effectiveness of the proposed IQA metric, our method is compared to some state-of-the-art IQA metrics. The experimental results showed that the proposed IQA metric has the fastest running speed compared the IQA methods except MSE under comparison. Moreover, our IQA metric achieves the best prediction performance for subjective image quality scores among the state-of-the-art IQA metrics under test.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.7-15
• /
• 2014

Image retrieval has become a huge part of computer vision and data mining. Although commercial image retrieval systems such as Google show great performances, the improvement on the performances are constantly on demand because of the rapid growth of data on web space. To satisfy the demand, many re-ranking methods, which enhance the performances by reordering retrieved results with independent algorithms, has been proposed. Conventional re-ranking algorithms are based on the assumption that visual patterns are not used on initial image retrieval stage. However, image search engines in present have begun to use the visual and the assumption is required to be reconsidered. Also, though it is possible to suspect that integration of multiple retrieval systems can improve the overall performance, the research on the topic has not been done sufficiently. In this paper, we made the condition that other manner than cooperation cannot improve the ranking result. We evaluate the algorithm on toy model and show that propose module can improve the retrieval results.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.15-23
• /
• 2017

The person Re-identification is the most challenging part of computer vision due to the significant changes in human pose and background clutter with occlusions. The picture from non-overlapping cameras enhance the difficulty to distinguish some person from the other. To reach a better performance match, most methods use feature selection and distance metrics separately to get discriminative representations and proper distance to describe the similarity between person and kind of ignoring some significant features. This situation has encouraged us to consider a novel method to deal with this problem. In this paper, we proposed an enhanced recurrent neural network with three-tier hierarchical network for person re-identification. Specifically, the proposed recurrent neural network (RNN) model contain an iterative expectation maximum (EM) algorithm and three-tier Hierarchical network to jointly learn both the discriminative features and metrics distance. The iterative EM algorithm can fully use of the feature extraction ability of convolutional neural network (CNN) which is in series before the RNN. By unsupervised learning, the EM framework can change the labels of the patches and train larger datasets. Through the three-tier hierarchical network, the convolutional neural network, recurrent network and pooling layer can jointly be a feature extractor to better train the network. The experimental result shows that comparing with other researchers' approaches in this field, this method also can get a competitive accuracy. The influence of different component of this method will be analyzed and evaluated in the future research.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.70-80
• /
• 1999

In this paper, a new hierarchical image segmentation algorithm based on human visual system(HVS) characteristic is proposed which can efficiently reduce and control transmission information quantity without the degradation of the subjective and objective image quality. It consists of image segmentation based on mathematical morphology and region merging considering HVS characteristic for the pairs of two adjacent regions at each level of the hierarchy. Image segmentation is composed of 3-level hierarchical structure. In the region merging structure of each level, we extract the pairs of two adjacent regions which human vision can't discriminate, and then merge them. The proposed region merging method extracts pairs of two neighbor regions to be merged and performs region merging according to merging priority based on HVS characteristics. The merging priority for each adjacent pair is determined by the proposed merging priority function(MPF). First of all, the highest priority pair is merged. The information control factor is used to regulate the transmission information at each level. The proposed segmentation algorithm can efficiently improve bottleneck problem caused by excessive contour information at region-based very low bit rate coding. And it shows that it is more flexible structure than that of conventional method. In experimental results, though PSNR and the subjective image quality by the proposed algorithm is similar to that of conventional method, the contour information quantity to be transmitted is reduced considerably. Therefore it is an efficient image segmentation algorithm for region-based very low bit rate coding.