• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.II
• /
• pp.170-177
• /
• 2000

Sorting cut roses according to quality is very essential to increase the value of the product. Many factors are involved in determining the grade of cut roses: length, thickness, and straightness of stem, color and maturity of bud, and extra. Among these factors, the stem straightness and bud maturity are considered to be difficult to set proper classification criteria. In this study, a prototype machine and an analysis procedure were developed to grade cut roses according to stem straightness and bud maturity by utilizing color image processing and neural network. The test results indicated 15.8% classification error for stem straightness and 10.0% for bud maturity.

• 제어로봇시스템학회논문지
• /
• 제15권5호
• /
• pp.505-510
• /
• 2009

In recent years the space where a robot works has been expanding to the human space unlike traditional industrial robots that work only at fixed positions apart from humans. A human in the recent situation may be the owner of a robot or the target in a robotic application. This paper deals with the latter case; when a robot vision system is employed to monitor humans for a surveillance application, each person in a scene needs to be identified. Humans, however, often move together, and occlusions between them occur frequently. Although this problem has not been seriously tackled in relevant literature, it brings difficulty into later image analysis steps such as tracking and scene understanding. In this paper, a probabilistic neural network is employed to learn the patterns of the best dividing position along the top pixels of an image region of partly occlude people. As this method uses only shape information from an image, it is simple and can be implemented in real time.

• 반도체디스플레이기술학회지
• /
• 제22권1호
• /
• pp.129-133
• /
• 2023

Image compression is a fundamental technique in the field of digital image processing, which will help to decrease the storage space and to transmit the files efficiently. Recently many deep learning techniques have been proposed to promise results on image compression field. Since many image compression techniques have artifact problems, this paper has compared two deep learning approaches to verify their performance experimentally to solve the problems. One of the approaches is a deep autoencoder technique, and another is a deep convolutional neural network (CNN). For those results in the performance of peak signal-to-noise and root mean square error, this paper shows that deep autoencoder method has more advantages than deep CNN approach.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.315-317
• /
• 2003

Neural oscillator is applied in oscillatory systems (Analysis of image information, Voice recognition. Etc...). If we apply established EBPA(Error back Propagation Algorithm) to oscillatory system, we are difficult to presume complicated input's patterns. Therefore, it requires more data at training, and approximation of convergent speed is difficult. In this paper, I studied the neural oscillator as synchronized states with appropriate phase relation between neurons and recognized the Korean alphabet using Neural Oscillator Phase model Synchronization.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.265-271
• /
• 2022

Social media is a form of communication based on the internet to share information through content and images. Their choice of profile images and type of image they post can be closely connected to their personality. The user posted images are designated as personality traits. The objective of this study is to predict five factor model personality dimensions from profile images by using deep learning and neural networks. Developed a deep learning framework-based neural network for personality prediction. The personality types of the Big Five Factor model can be quantified from user profile images. To measure the effectiveness, proposed two models using convolution Neural Networks to classify each personality of the user. Done performance analysis among two different models for efficiently predict personality traits from profile image. It was found that VGG-69 CNN models are best performing models for producing the classification accuracy of 91% to predict user personality traits.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.907-923
• /
• 2020

For the severe haze situation in the Beijing-Tianjin-Hebei region, conventional fine particulate matter (PM2.5) concentration prediction methods based on pollutant data face problems such as incomplete data, which may lead to poor prediction performance. Therefore, this paper proposes a method of predicting the PM2.5 concentration based on image analysis technology that combines image data, which can reflect the original weather conditions, with currently popular machine learning methods. First, based on local parameter estimation, autoregressive (AR) model analysis and local estimation of the increase in image blur, we extract features from the weather images using an approach inspired by free energy and a no-reference robust metric model. Next, we compare the coefficient energy and contrast difference of each pixel in the AR model and then use the percentages to calculate the image sharpness to derive the overall mass fraction. Furthermore, the results are compared. The relationship between residual value and PM2.5 concentration is fitted by generalized Gauss distribution (GGD) model. Finally, nonlinear mapping is performed via the wavelet neural network (WNN) method to obtain the PM2.5 concentration. Experimental results obtained on real data show that the proposed method offers an improved prediction accuracy and lower root mean square error (RMSE).

• 한국컴퓨터정보학회논문지
• /
• 제27권1호
• /
• pp.77-82
• /
• 2022

본 연구는 장소 이미지를 수집하고 학습하여 사용자가 관심이 있어 하는 이미지의 장소를 예측하여 알려주는 서비스 개발을 목적으로 한다. 이미지 학습을 위한 이미지 데이터들은 크롤링 부분을 통해 수집되도록 설계되었다. 이미지 수집 이후 수집된 이미지들은 장소별로 라벨링 되어 CNN의 다양한 층을 통하여 학습된다. 각 층을 거칠 때마다 입력받은 학습 데이터는 최적화하여 특징 맵과의 비교를 반복하며 특정 장소 이미지의 특징 정보를 뽑아낸다. 충분한 학습 데이터가 쌓이면 다양한 장소 이미지들에 대해 예측이 가능하다. 학습 결과 모델의 정확도는 79.2로 높은 학습 정확도를 보였다.

• 한국생산제조학회지
• /
• 제22권3호
• /
• pp.402-407
• /
• 2013

In this paper, the image processing for flexible disk grinding and the effect of the grinding conditions on the flat zone length of a workpiece are investigated, with the purpose of automating the grinding process. To accomplish this, three issues should be carefully studied. The first is finding the relationship between the flat zone length and the grinding conditions such as the cutting speed and feeding speed. The second is developing a neural network algorithm to predict the flat zone. The third is developing an image processing algorithm to measure the flat zone length of a workpiece. Slope analysis is used to determine straight and curved sections during the image processing. For verification, the estimated length and the length from the image processing are compared with the length measured by a projector. There is a minimum difference of 1.7% between the predicted and measured values. The results of this paper will be useful in compiling a database for process automation.

• 대한조선학회논문집
• /
• 제59권2호
• /
• pp.118-124
• /
• 2022

Marine environment analysis and ship motion prediction during ship navigation are important technologies for safe and economical operation of autonomous ships. As a marine environment analysis technology, there is a method of analyzing waves by measuring the sea states through images acquired based on radar(radio detection and ranging) signal. However, in the process of deriving marine environment information from radar images, noises generated by external factors are included, limiting the interpretation of the marine environment. Therefore, image processing for noise removal is required. In this study, image inpainting by partial convolutional neural network model is proposed as a method to remove noises and reconstruct radar images.