• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• Journal of Korea Multimedia Society
• /
• v.11 no.2
• /
• pp.153-162
• /
• 2008

We propose a novel image inpainting method composed of two parts: band matching and seamless cloning. In band matching, a band enclosing the boundary of a missing region is compared to those from the other parts of the image. The inner area of the minimum difference band is then copied to the missing region. Even though this band matching results in successful inpainting in many practical applications, brightness discontinuity (a seam) may appear between the filled missing region and its neighborhood. We apply seamless cloning to remove such discontinuity between the two regions. However, since this basic method using one patch may not deal with cases where there are abrupt changes of color or brightness along the boundary, we furthermore devise one more step: target sub-division. The target area is subdivided into small sub-areas, and the band matching and seamless cloning are applied to each of them. The multiple results from the sub-division are then ordered according to inpainting quality, which is measured based on the edge map or discontinuity map along the boundary band.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.546-555
• /
• 2009

There is increasingly interested in the measurement of antenna's characteristics for one's manufacture according to one's various application. Due to this, the antenna measurement system need be made with more and more great precision. On measuring of the antenna's characteristic, the conventional system handled by human generates the error due to controlling the position of the system by user. Therefore there need be introduced the automatic measurement system of antenna's characteristic. In this paper, we propose antenna extraction algorithm for the Antenna automatic measurement system of antenna's characteristic. The proposed algorithm gets the antenna image from antenna measurement system, extracts an antenna object from the image, and extracts the parameters for antenna's slant and antenna's location. The extracted parameters is used to correct location and distortions of the antenna and automatic measurement. The proposed algorithm is applied to the patch antenna. The results show that antenna's object is efficiently extracted and the angle for correcting the error is calculated well.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.1
• /
• pp.21-30
• /
• 2011

In this paper, an effective method to detect the laser pointer on the screen using the neural network algorithm for implementing the human-computer interaction system. The proposed neural network algorithm is used to train the patches without a laser pointer from the input camera images, the trained neural network then generates output values for an input patch from a camera image. If a small variation is perceived in the input camera image, amplify the small variations and detect the laser pointer spot in the camera image. The proposed system consists of a laser pointer, low-price web-camera and image processing program and has a detection capability of laser spot even if the background of computer monitor has a similar color with the laser pointer spot. Therefore, the proposed technique will be contributed to improve the performance of human-computer interaction system.

• The Korean Fashion and Textile Research Journal
• /
• v.16 no.4
• /
• pp.645-652
• /
• 2014

This study identifies consumer needs and a pattern sensory evaluation of jacquard fabrics for raincoats using quick-drying-absorbing polyester. We investigate the consumer's consciousness and raincoat improvements. Twelve kinds of jacquard fabrics were developed for use in this study. Developed jacquard fabrics were assessed subjectively by 152 university students using a 7-point scale of 26 consumer needs and 31 pattern image sensory descriptors. Data were analyzed by SPSS. The major results were: There was a need for consumers to improve the front fastener type, cuff fastener, mesh patch position, and raincoat pocket position. The most important parameter to choose raincoat fabric was waterproof and the other parameters were vapor-porous/water repellent, design, color, fashionability, air-permeability and easy-put on/off. The pattern image sensibility of jacquard fabrics was explained by seven factors: gorgeous, simple, cute, futuristic, ethnic, feminine, and cool. A higher pattern preference was found in the jacquard fabrics of unique, sporty, natural, luxurious, and trendy images. The pattern preference was predicted at 45.3% with gorgeous, simple, pure, cute, futuristic factors. The correlation coefficient between the pattern image sensibility factor 1 (gorgeous) and pattern preference was 0.674 and with factor 3 (cute) was 0.416, and with factor 6 (cool) was 0.209. The 4 factors (gorgeous, simple, cute, futuristic) were selected as a significant pattern image sensibility that influenced preference.

• The Research Journal of the Costume Culture
• /
• v.18 no.4
• /
• pp.612-625
• /
• 2010

People have more expectations for arts and design and accordingly, various artworks were combined with fashion to meet the consumer needs. As people live a decent life, the development of leisure activities and industry has a much effect on apparel. With this phenomenon, a free and active casual look is making progress centering around the practical apparel, pursuing diversified efficiency irrespective of a season and considering sensibility not formality. In this study, paintings of Henri Matisse were analyzed in every respect and were applied in apparel design with diverse color arrangement and a motif originating in the phenomenon of modern fashion design which leads to the integration of arts and design. Painting image and color of Henri Matisse were used. Sportive casual and cultural casual was used in design as well. Originality of its color in the paintings which were used an a motif is coming from Gauguin and Gogh. Henri had influenced to the next generation with pursuit of violent color. The following conclusions were drawn from this study. First, the color of Henri Matisse's paintings has a strong contrast effect. It combines notable violent color with a simple yet decorative motif. Therefore color from Matisse's paintings suit for apparel of marked individuality with its free color arrangement. Second, free and active image in Henri Matisse's paintings is easy to express efficiency and popularity. It accords with the feature of casual wear. Third, through adding a flowing curved line in Henri Matisse's paintings to materials and applying various colors putting into a curved line image to a rib section, a decorative effect which goes with the whole shape is obtained. This study presents possibility of emergence of unique design using free color arrangement and motif from the image of paintings and aims development of modern fashion design in accordance with modern fashion giving importance to the difference and sensibility by integration of modern garments and artworks.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.1
• /
• pp.257-264
• /
• 2019

This paper presents a single image haze removal method via a pixel-based joint BDCP (bright and dark channel prior) and a hierarchical bilateral filter in order to reduce computational complexity and memory requirement while improving the dehazing performance. Pixel-based joint BDCP reduces the computational complexity compared to the patch-based DCP, while making it possible to estimate the atmospheric light in pixel unit and the transmission more accurately. Moreover the bilateral filter, which can smooth an image effectively while preserving edges, refines the transmission to reduce the halo effects, and its hierarchical structure applied to edges only prevents the increase of complexity from the iterative application. Experimental results on various hazy images show that the proposed method exhibits excellent haze removal performance with low computational complexity compared to the conventional methods, and thus it can be applied in various fields.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.177-186
• /
• 2023

Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.59-62
• /
• 2017

본 논문에서는 평균 밝기 부분에 가중치 맵으로써 감마 변환에 기반한 선형 결합을 제안하고자 한다. 기존의 패치를 기반으로 한 가중치 맵은 평균 밝기 부분에서 영상 내 밝기 값이 한쪽으로 치우쳐 영상의 밝은 부분이 과포화 상태가 되어 세부 정보가 손실되는 단점이 있다. 이에 본 논문에서는 전역적 및 지역적 영상의 평균 밝기 값을 이용하여 감마 변환된 값을 선형 결합 시켜줌으로써 영역 내 세부 정보를 보존시키고 주관적 화질을 향상시켰다. 실험을 통해 결과를 분석하고 성능을 비교하여 기존 알고리듬에 비해 제안한 알고리듬이 우수함을 증명하였다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.1
• /
• pp.723-733
• /
• 2009

This study proposes a sequence of procedures to extract building boundaries and planar patches through segmentation of rasterized lidar data. Although previous approaches to building extraction have been shown satisfactory, there still exist needs to increase the degree of automation. The methodologies proposed in this study are as follows: Firstly, lidar data are rasterized into grid form in order to exploit its rapid access to neighboring elevations and image operations. Secondly, propagation of errors in raw data is taken into account for in assessing the quality of gradients-driven properties and further in choosing suitable parameters. Thirdly, extraction of planar patches is conducted through a sequence of processes: histogram analysis, least squares fitting, and region merging. Experimental results show that the geometric components of building models could be extracted by the proposed approach in a streamlined way.