• 한국정보디스플레이학회:학술대회논문집
• /
• 2006.08a
• /
• pp.1429-1431
• /
• 2006

We developed new anti-glare(AG) layer which has improved image quality and solved mechanical problems. Conventional silica-type AG has some restrictions related to sparkling, causing mechanical defects. The new anti-glare layer is designed with adjusted optical factors and polymer type. Therefore new anti-glare layer meets two main characteristics at once using unmatched optical property between scattering in material and surrounding.

• Journal of Internet Computing and Services
• /
• v.19 no.3
• /
• pp.35-42
• /
• 2018

Deep learning is known as a method of high accuracy among several methods for image classification. In this paper, we propose a method of enhancing the accuracy of image classification using CNN with a batch normalization method for classification of images using deep CNN (Convolutional Neural Network). In this paper, we propose a method to add a batch normalization layer to existing neural networks to enhance the accuracy of image classification. Batch normalization is a method to calculate and move the average and variance of each batch for reducing the deflection in each layer. In order to prove the superiority of the proposed method, Accuracy and mAP are measured by image classification experiments using five image data sets SHREC13, MNIST, SVHN, CIFAR-10, and CIFAR-100. Experimental results showed that the CNN with batch normalization is better classification accuracy and mAP rather than using the conventional CNN.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.18 no.8
• /
• pp.720-723
• /
• 2005

We studied the quantitativity of the image sticking which is occured by the resicual DC in the fringe-electric field switching (FFS) mode. Actually, in the FFS mode driven by the strong fringe electric field, the asymmetric residual DC was formed in the bottom substrate. It made the impurity ion stick to the alignment layer such as polyimde layer. Thus, the differnece of the luminance existes after the stress check pattern is applied to the panel so that we can see the image sticking. This image sticking decreases as the residual DC value between specific patterns decreases. Therefore, it is necessary to control the residual DC for the FFS mode with the high image quality. It is possible to eliminate the image stiking when the extra pixel voltage is applied through the circuit tunning for reducing the difference of residual DC accroding to the panel position.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.9-23
• /
• 2019

In this paper, we propose a layer structure of a pest image classifier model using CNN (Convolutional Neural Network) and background removal image processing algorithm for improving classification accuracy in order to build a smart monitoring system for pine wilt pest control. In this study, we have constructed and trained a CNN classifier model by collecting image data of pine wilt pest mediators, and experimented to verify the classification accuracy of the model and the effect of the proposed classification algorithm. Experimental results showed that the proposed method successfully detected and preprocessed the region of the object accurately for all the test images, resulting in showing classification accuracy of about 98.91%. This study shows that the layer structure of the proposed CNN classifier model classified the targeted pest image effectively in various environments. In the field test using the Smart Trap for capturing the pine wilt pest mediators, the proposed classification algorithm is effective in the real environment, showing a classification accuracy of 88.25%, which is improved by about 8.12% according to whether the image cropping preprocessing is performed. Ultimately, we will proceed with procedures to apply the techniques and verify the functionality to field tests on various sites.

• The KIPS Transactions:PartC
• /
• v.15C no.4
• /
• pp.281-288
• /
• 2008

Recently, the advance of multimedia hardware has fostered the development of wireless multimedia sensor network which is able to ubiquitously obtain multimedia content such as image or audio from the environment. The multimedia data which has several characteristics such as large size and correlation between the data requires reliability in transmission. However, the existing solution which take the focus on the efficiency of network mainly, is not appropriate to transmit the multimedia data. In the paper, we proposes a reliable asynchronous image transfer protocol, RAIT. RAIT applies double sliding window method in node-to-node image tansfer to prevent the packet loss caused by network congestion. The double sliding window consists of one sliding window for the receiving queue, which is used for prevention of packet loss caused by communication failure between nodes and the other sliding window for the sending queue which prevents the packet loss caused by network congestion. the routing node prevents the packet loss and guarantees the fairness between the nodes by scheduling the packets based on the image non-preemptively. The RAIT implements the double sliding window method by cross layer design between RAIT layer, routing layer, and queue layer. The experiment shows that RAIT guarantees the reliability of image transmission compared with the existing protocol.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2002.05b
• /
• pp.107-110
• /
• 2002

The optical memory devices of BST thin films to composite $(Ba_{0.7}\;Sr_{0.3})TiO_{3}$ using sol-gel method were fabricated by changing of the depositing layer number on $Pt/Ti/SiO_{2}/Si$ substrate. The structural properties of optical memory devices to be ferroelectric was investigated by fractal analysis and 3-dimension image processing. The thickness of BST thin films at each coating numbers 3, 4 and 5 times was $2500[\AA]$, $3500[\AA]$ and $3800[\AA]$. BST thin films exhibited the most pronounced grain growth. The surface morphology image was roughness with coating numbers. The thin films increasing with coating numbers shows a more textured and complex configuration.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2002.05b
• /
• pp.31-34
• /
• 2002

In this paper, the electric properties of amophous selenium multilayer samples has been investigated. In order to develop the hybrid flat-panel digital· X-ray image detector, we measured and analyzed their performance parameters such as the X -ray sensitivity and dark-current for a amophous selenium multilayers X-ray detector with a phosphor layer, The hybrid digital X-ray image detector can be constructed by integrating a phosphor layer (or a scintillative layer) that convert X-ray to a light on a-Se photoconduction mulilayers that convert a light to electrical signal. As results, the dielectric materials such as parylene between the phosphor layer and the top electrode may reduce the dark-current of the samples. Amorphous selenium multilayers having dielectric layer(parylene) has characteristics of low dark-current, high X-ray sensitivity. So we can acquired a enhanced signal to noise ratio. In this paper offer the method can reduce the dark-current in the hybrid X-ray detector.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• Journal of Practical Engineering Education
• /
• v.16 no.1_spc
• /
• pp.59-64
• /
• 2024

As the aging population grows, the incidence of cancer is increasing. Skin cancer appears externally, but people often don't notice it or simply overlook it. As a result, if the early detection period is missed, the survival rate in the case of late stage cancer is only 7.5-11%. However, the disadvantage of diagnosing, serious skin cancer is that it requires a lot of time and money, such as a detailed examination and cell tests, rather than simple visual diagnosis. To overcome these challenges, we propose an Attention-based CNN model skin cancer classification system. If skin cancer can be detected early, it can be treated quickly, and the proposed system can greatly help the work of a specialist. To mitigate the problem of image data imbalance according to skin cancer type, this skin cancer classification model applies the Over Sampling, technique to data with a high distribution ratio, and adds a pre-learning model without an Attention layer. This model is then compared to the model without the Attention layer. We also plan to solve the data imbalance problem by strengthening data augmentation techniques for specific classes.