• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.52-60
• /
• 2022

Few-shot learning is a sub-area of machine learning problems, which aims to classify target images that only contain a few labeled samples for training. As a representative few-shot learning method, the Prototypical network has been received much attention due to its simplicity and promising results. However, the Prototypical network uses the sample mean of samples from the same class as the prototypes of that class, which easily results in learning uncharacteristic features in the low-data scenery. In this study, we propose to use local descriptors (i.e., patches along the channel within feature maps) from the same class to explicitly obtain more representative prototypes for Prototypical Network so that significant intra-class feature information can be maintained and thus improving the classification performance on few-shot learning tasks. Experimental results on various benchmark datasets including mini-ImageNet, CUB-200-2011, and tiered-ImageNet show that the proposed method can learn more discriminative intra-class features by the local descriptors and obtain more generic prototype representations under the few-shot setting.

• 전자공학회논문지 IE
• /
• v.46 no.4
• /
• pp.57-65
• /
• 2009

This paper presents the image contrast enhancement technique suitable for local dimming backlight of small-sized mobile display while achieving the reduction of the power consumption. In addition to the large-sized TFT-LCD, small-sized one has adopted LED for backlight. Since, conventionally, LED was mounted on the side edge of a display panel, global dimming method has been widely used. However, recently, new advanced method of local dimming by placing the LED to the backside of the display panel and it raised the necessity of sub-blocked processing after partitioning the target image. When the sub-blocked image has low brightness, the supply current of a backlight LED is reduced, which gives both enhancement of contrast ratio and power consumption reduction. In this paper, we propose simple and improved image enhancement algorithm suitable for the small-sized mobile display. After partitioning the input image by equal sized blocks and analyzing the pixel information in each block, we realize the primary contrast enhancement by independently processing the sub-blocks using the information such as histogram, mean, and standard deviation values of luminance(Y) component. And then resulting information is transferred to each backlight control unit for local dimming to realize the secondary contrast enhancement as well as reduction of power consumption.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.2
• /
• pp.475-485
• /
• 2008

One of main issues in watermarking is to resolve the strength of watermark for solving the problem of trade-off between fidelity and robustness of watermarking. In the previous research, the strength of watermark has been resolved fixed value generally without considering local image characteristics such as image brightness, contrast, and edge. This paper proposes a new model to predict the strength of watermark considering local image characteristics such as image brightness, contrast, and edge for digital wavelet transform(DWT)-based image watermarking. For the study, psychological experiment was fulfilled to measure the human image perception and regression analysis showed the proposed model was statistically significant at the level of ${\alpha}\;=\;0.01$. Also the model is practically validated on fidelity and robustness of watermarking.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.183-186
• /
• 2001

In this paper, we first propose new texture features, BVLC (block variation of local correlation coefficients) moments, for content-based image retrieval (CBIR) and then present an image retrieval method based on the fusion of BDIP and BVLC moments. BDIP uses the local probabilities in image blocks to extract valley and edges well. BVLC uses the variations of local correlation coefficients in images blocks to measure texture smoothness well. In order not to be affected with the movement, rotation, and size of an object, the first and second moments of BDIP and BVLC are used for CBIR. Corel DB and Vistex DB are used to evaluate the performance of the proposed retrieval method. Experimental results show that the presented retrieval method yields average 12% better performance than the method using only BDIP or BVLC moments and average 13% better performance than the method using wavelet moments.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.260-263
• /
• 2017

본 논문은 single image에서 측정한 빛 전달량 값과 local contrast 값을 사용하여 안개 량을 수치화하는 방법을 제안한다. 제안하는 방법은 빛 전달량 값을 사용하여 안개로 예측되는 지역을 추정하고, 추정된 안개 예측지역의 넓이와 해당 지역의 local contrast 크기의 범위를 사용하여 안개 정도를 수치화 한다. single image에서 측정 가능한 안개 의 물리적 특성들을 고려하였기 때문에 기존의 안개 검출 알고리즘들이 구분하지 못했던 영상들에서도 안개 량을 정확하게 측정하였다. 실제 빛의 산란 정도를 측정하는 감광 계수 측정계를 사용하여 측정한 안개 량과 제안하는 방법의 수치를 비교했을 때, 다양한 환경과 물체를 포함한 영상들에서 95%이상의 정확도로 안개 정도를 수치화 하였다. 또한 빛 전달량 추정 과정에서 local contrast 값을 추출하여 사용하기 때문에 기존의 빛 전달량을 측정하는 방법에서 복잡도를 거의 증가시키지 않는다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.12
• /
• pp.3033-3045
• /
• 1996

In this paper, we propse an object-oriented coding method in low bit-rate channels using pyramid structure and residual image compensation. In the motion estimation step, global motion is estimated using a set of multiresolution images constructed in a pyramid structure. We split an input image into two regions based on the gradient value. Regions with larte motions obtain observation points at low resolution level to guarantee robustness to noise and to satisfy a motion constraint equation whereas regions with local motions such as eye, and lips get observation points at the original resolution level. Local motion variations and intesity variations of an image reconstructed by the golbal motion are compensated additionally by using the previous residual image component. Finally, the model failure (MF) region is compensated by the pyramid mapping of the previous displaced frame difference (DFD). Computer simulation results show that the proposed method gives better performance that the convnetional one in terms of the peak signal to noise ratio (PSNR), compression ratio (CR), and computational complexity.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.221-224
• /
• 2010

When the image registration methods which were generally used to the low medium resolution satellite images is applied to the high spatial resolution images, some matching errors or limitations might be occurred because of the local distortions in the images. This paper, therefore, proposed the automatic image-to-image registration of high resolution satellite images using local properties of control points to improve the registration result.

• Korean System Dynamics Review
• /
• v.12 no.3
• /
• pp.5-23
• /
• 2011

Studies in social science are performed on the language of social actors. While a metaphor analysis focuses on the meaning of the language, a cognitive map analysis deals with its external relationships. If we can put together both analyses, it will be possible to investigate the internal meanings and external relationship of the language and image at the same time. In this paper, metaphor analysis and cognitive map approach is applied to find the image of local governments. This study shows how to link metaphor analysis to the cognitive map and the benefit of using both approaches together.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.986-989
• /
• 2011

Reversible data hiding is a technique that can embed information into cover media (image, video, voice signal) and can recover the original cover media after extracting the embedded information. In this papa, we propose a new reversible data hiding methods that based on block median preservation and the image local characteristic. By using the median value of a block, a high payload can be got and by considering the image local characteristic, a lot of distortion can be avoided and a high PSNR can be got. In the experiment, our methods can generate better result than the previous reversible data hiding methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4126-4142
• /
• 2015

Finger vein recognition is a biometric technology using finger veins to authenticate a person, and due to its high degree of uniqueness, liveness, and safety, it is widely used. The traditional Symmetric Local Graph Structure (SLGS) method only considers the relationship between the image pixels as a dominating set, and uses the relevant theories to tap image features. In order to better extract finger vein features, taking into account location information and direction information between the pixels of the image, this paper presents a novel finger vein feature extraction method, Multi-Orientation Weighted Symmetric Local Graph Structure (MOW-SLGS), which assigns weight to each edge according to the positional relationship between the edge and the target pixel. In addition, we use the Extreme Learning Machine (ELM) classifier to train and classify the vein feature extracted by the MOW-SLGS method. Experiments show that the proposed method has better performance than traditional methods.