• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.894-907
• /
• 2022

The features extracted by convolutional neural networks are more descriptive of images than traditional features, and their convolutional layers are more suitable for retrieving images than are fully connected layers. The convolutional layer features will consume considerable time and memory if used directly to match an image. Therefore, this paper proposes a feature weighting and region integration method for convolutional layer features to form global feature vectors and subsequently use them for image matching. First, the 3D feature of the last convolutional layer is extracted, and the convolutional feature is subsequently weighted again to highlight the edge information and position information of the image. Next, we integrate several regional eigenvectors that are processed by sliding windows into a global eigenvector. Finally, the initial ranking of the retrieval is obtained by measuring the similarity of the query image and the test image using the cosine distance, and the final mean Average Precision (mAP) is obtained by using the extended query method for rearrangement. We conduct experiments using the Oxford5k and Paris6k datasets and their extended datasets, Paris106k and Oxford105k. These experimental results indicate that the global feature extracted by the new method can better describe an image.

• 한국인쇄학회지
• /
• 제22권2호
• /
• pp.73-82
• /
• 2004

A thermal transfer method was developed novel method to form the phosphor screen for monochrom VPT. This method have advantages of simple process, clean environment, saving raw material and running-cost. But now applying phosphor screen for thermal transfer method has been formed three layers (phosphor layer, ITO layer and thermal adhesive layer) on the PET film as substrate. This is complex process, consumption of raw-material and require of high cost. Also ITO paste at present has been imported from Japan. To improve these problems, we have developed ITO paste as conductive paste by using ITO sol and binder resin (AA3003). Ito paste as developed in this study has both conductive and excellent thermal transfer abilities. Thus we could manufacture phosphor screen formed two layers (phosphor layer and ITO layer).

• 전기전자학회논문지
• /
• 제25권3호
• /
• pp.493-500
• /
• 2021

본 논문에서는 다각형 용기의 품질 향상을 위한 딥러닝 구조 개발을 제안한다. 딥러닝 구조는 convolution 층, bottleneck 층, fully connect 층, softmax 층 등으로 구성된다. Convolution 층은 입력 이미지 또는 이전 층의 특징 이미지를 여러 특징 필터와 convolution 3x3 연산하여 특징 이미지를 얻어 내는 층이다. Bottleneck 층은 convolution 층을 통해 추출된 특징 이미지상의 특징들 중에서 최적의 특징들만 선별하여 convolution 1x1 ReLU로 채널을 감소시키고convolution 3x3 ReLU를 실시한다. Bottleneck 층을 거친 후에 수행되는 global average pooling 연산과정은 convolution 층을 통해 추출된 특징 이미지의 특징들 중에서 최적의 특징들만 선별하여 특징 이미지의 크기를 감소시킨다. Fully connect 층은 6개의 fully connect layer를 거쳐 출력 데이터가 산출된다. Softmax 층은 입력층 노드의 값과 연산을 진행하려는 목표 노드 사이의 가중치와 곱을 하여 합하고 활성화 함수를 통해 0~1 사이의 값으로 변환한다. 학습이 완료된 후에 인식 과정에서는 학습 과정과 마찬가지로 카메라를 이용한 이미지 획득, 측정 위치 검출, 딥러닝을 활용한 비원형 유리병 분류 등을 수행하여 비원형 유리병을 분류한다. 제안된 다각형 용기의 품질 향상을 위한 딥러닝 구조의 성능을 평가하기 위하여 공인시험기관에서 실험한 결과, 양품/불량 판별 정확도 99%로 세계최고 수준과 동일한 수준으로 산출되었다. 검사 소요 시간은 평균 1.7초로 비원형 머신비전 시스템을 사용하는 생산 공정의 가동 시간 기준 내로 산출되었다. 따라서 본 본문에서 제안한 다각형 용기의 품질 향상을 위한 딥러닝 구조의 성능의 그 효용성이 입증되었다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2005년도 하계학술대회 논문집 Vol.6
• /
• pp.390-392
• /
• 2005

The digital radiation detectors are used clinically by diagnostic apparatus. However the digital radiation detector are some problem like high operating voltage, light blurring, low conversion efficiency, low fill factor, etc. Thus we propose a new radiation detector that the photoconductor layer and liquid crystal layer are coupled in sandwich structure. X-ray absorption in the photoconductor layer controls the state of the liquid crystal via creation of charge carrier and the light modulation of liquid crystal make image formation. The advantage of the new radiation detector is that high resolution image is acquired and the signal amplification is possible by external visible light source. In this study, we study the optical properties and electrical properties of the new radiation detector to irradiate X-ray. The Mercury Iodide($HgI_2$) was used by photoconductor material, and the aluminum is used by reflective layer. The thickness of Mercury Iodide is about $200{\mu}m$, the operating voltage of the liquid crystal is 1.5~5V. The electrical properties of Mercury Iodide was measured, and the transmission efficiency of liquid crystal was measured by modulation potential.

• 한국콘텐츠학회논문지
• /
• 제13권12호
• /
• pp.38-47
• /
• 2013

다중 레이어 영상 모델인 Mixed Raster Content 모델 (MRC) 기반의 영상 부호화는 스크린 이미지와 같은 혼합 영상을 전경 레이어, 이진 마스크 레이어, 배경 레이어로 재구성한 뒤, 각 레이어마다 그 레이어의 신호 특성에 적합한 부호화기를 이용하여 영상을 압축하는 기법이다. 문자와 같은 계단 형태의 강한 에지를 갖는 영역의 위치 정보를 마스크 레이어에 저장하고, 그 위치의 색상 신호는 전경 레이어에 저장한다. 그리고 나머지 영역인 배경 영역의 색상 신호는 배경 레이어에 저장한다. 따라서 마스크 레이어가 전경과 배경의 분할 정보를 담게 되며, 이 분할 정보의 정확도에 따라 전체 부호화기의 압축 효율이 직접적인 영향을 받는다. 본 논문은 MRC 기반의 영상 부호화를 위한 새로운 레이어 분할 알고리즘을 제안한다. 제안 방법은 형태학적 필터인 top hat 변환을 이용하여 문자를 배경신호로부터 분할한다. 이때 문자의 경계를 에지 맵으로부터 추정하여 문자 색상과 배경과의 상대적 밝기를 결정하고 이를 통해 형태학적 필터링에 필요한 top hat 변환의 종류를 정확히 선택하도록 하였다. 실험을 통해 제안 방법이 비교 대상 알고리즘에 비해 우수한 분할 성능을 가짐을 보인다.

• 한국멀티미디어학회논문지
• /
• 제23권6호
• /
• pp.756-764
• /
• 2020

A typical algorithm used for image analysis is the Convolutional Neural Network(CNN). R-CNN, Fast R-CNN, Faster R-CNN, etc. have been studied to improve the performance of the CNN, but they essentially require large amounts of data and high algorithmic complexity., making them inappropriate for small and medium-sized services. Therefore, in this paper, the image label prediction algorithm based on CNN with collaborative layer with low complexity, high accuracy, and small amount of data was proposed. The proposed algorithm was designed to replace the part of the neural network that is performed to predict the final label in the existing deep learning algorithm by implementing collaborative filtering as a layer. It is expected that the proposed algorithm can contribute greatly to small and medium-sized content services that is unsuitable to apply the existing deep learning algorithm with high complexity and high server cost.

• International Journal of Advanced Culture Technology
• /
• 제6권3호
• /
• pp.142-150
• /
• 2018

This paper describes the algorithm that lowers the dimension, maintains the object recognition and significantly reduces the eigenspace configuration time by combining the edge orientation histogram and principle component analysis. By using the detected object region as a recognition input image, in this paper the object recognition method combined with principle component analysis and the multi-layer network which is one of the intelligent classification was suggested and its performance was evaluated. As a pre-processing algorithm of input object image, this method computes the eigenspace through principle component analysis and expresses the training images with it as a fundamental vector. Each image takes the set of weights for the fundamental vector as a feature vector and it reduces the dimension of image at the same time, and then the object recognition is performed by inputting the multi-layer neural network.

• ETRI Journal
• /
• 제39권6호
• /
• pp.841-850
• /
• 2017

We investigate neural network image reconstruction for magnetic particle imaging. The network performance strongly depends on the convolution effects of the spectrum input data. The larger convolution effect appearing at a relatively smaller nanoparticle size obstructs the network training. The trained single-layer network reveals the weighting matrix consisting of a basis vector in the form of Chebyshev polynomials of the second kind. The weighting matrix corresponds to an inverse system matrix, where an incoherency of basis vectors due to low convolution effects, as well as a nonlinear activation function, plays a key role in retrieving the matrix elements. Test images are well reconstructed through trained networks having an inverse kernel matrix. We also confirm that a multi-layer network with one hidden layer improves the performance. Based on the results, a neural network architecture overcoming the low incoherence of the inverse kernel through the classification property is expected to become a better tool for image reconstruction.

• Current Optics and Photonics
• /
• 제7권2호
• /
• pp.200-206
• /
• 2023

Near-infrared (NIR) sensing technology using CMOS image sensors is used in many applications, including automobiles, biological inspection, surveillance, and mobile devices. An intuitive way to improve NIR sensitivity is to thicken the light absorption layer (silicon). However, thickened silicon lacks NIR sensitivity and has other disadvantages, such as diminished optical performance (e.g. crosstalk) and difficulty in processing. In this paper, a pixel structure for NIR sensing using a stacked CMOS image sensor is introduced. There are two photodetection layers, a conventional layer and a bottom photodiode, in the stacked CMOS image sensor. The bottom photodiode is used as the NIR absorption layer. Therefore, the suggested pixel structure does not change the thickness of the conventional photodiode. To verify the suggested pixel structure, sensitivity was simulated using an optical simulator. As a result, the sensitivity was improved by a maximum of 130% and 160% at wavelengths of 850 nm and 940 nm, respectively, with a pixel size of 1.2 ㎛. Therefore, the proposed pixel structure is useful for NIR sensing without thickening the silicon.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1347-1360
• /
• 2018

Owing to limited energy in wireless devices power saving is very critical to prolong the lifetime of the networks. In this regard, we designed a cross-layer optimization mechanism based on power control in which source node broadcasts a Route Request Packet (RREQ) containing information such as node id, image size, end to end bit error rate (BER) and residual battery energy to its neighbor nodes to initiate a multimedia session. Each intermediate node appends its remaining battery energy, link gain, node id and average noise power to the RREQ packet. Upon receiving the RREQ packets, the sink node finds node disjoint paths and calculates the optimal power vectors for each disjoint path using cross layer optimization algorithm. Sink based cross-layer maximal minimal residual energy (MMRE) algorithm finds the number of image packets that can be sent on each path and sends the Route Reply Packet (RREP) to the source on each disjoint path which contains the information such as optimal power vector, remaining battery energy vector and number of packets that can be sent on the path by the source. Simulation results indicate that considerable energy saving can be accomplished with the proposed cross layer power control algorithm.