• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2881-2894
• /
• 2014

In complicated environment, context information plays an important role in image segmentation/labeling. The recently proposed auto-context algorithm is one of the effective context-based methods. However, the standard auto-context approach samples the context locations utilizing a fixed radius sequence, which is sensitive to large scale-change of objects. In this paper, we present a scale invariant auto-context (SIAC) algorithm which is an improved version of the auto-context algorithm. In order to achieve scale-invariance, we try to approximate the optimal scale for the image in an iterative way and adopt the corresponding optimal radius sequence for context location sampling, both in training and testing. In each iteration of the proposed SIAC algorithm, we use the current classification map to estimate the image scale, and the corresponding radius sequence is then used for choosing context locations. The algorithm iteratively updates the classification maps, as well as the image scales, until convergence. We demonstrate the SIAC algorithm on several image segmentation/labeling tasks. The results demonstrate improvement over the standard auto-context algorithm when large scale-change of objects exists.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.83-88
• /
• 1999

In this paper, a novel gray-scale lossless image coder combining context-based minimum mean squared error (MMSE) prediction and entropy coding is proposed. To obtain context of prediction, this paper first defines directional difference according to sharpness of edge and gradients of localities of image data. Classification of 4 directional differences forms“geometry context”model which characterizes two-dimensional general image behaviors such as directional edge region, smooth region or texture. Based on this context model, adaptive DPCM prediction coefficients are calculated in MMSE sense and the prediction is performed. The MMSE method on context-by-context basis is more in accord with minimum entropy condition, which is one of the major objectives of the predictive coding. In entropy coding stage, context modeling method also gives useful performance. To reduce the statistical redundancy of the residual image, many contexts are preset to take full advantage of conditional probability in entropy coding and merged into small number of context in efficient way for complexity reduction. The proposed lossless coding scheme slightly outperforms the CALIC, which is the state-of-the-art, in compression ratio.

• 한국지능시스템학회논문지
• /
• 제20권3호
• /
• pp.368-374
• /
• 2010

영상 분할 (Image Segmentation)은 패턴 인식, 환경 인식, 문서 분석을 위한 영상 처리 과정에서 가장 기본적인 단계이다. 영상 분할 방법들 중 Otsu의 영상의 정규화된 히스토그램의 분포 정보를 이용하여 클래스 간의 분산을 최대화 시키는 임계치값을 결정하는 자동 임계치값 선정방법이 가장 잘 알려진 방법이다. Otsu의 방법은 영상의 전 영역에 대한 히스토그램을 분석함으로써 영상의 부분적인 특성을 반영하여 임계치값을 결정하기는 어렵다. 본 논문에서는 이 어려움 해소하기 위하여 Context Fuzzy c-Means 알고리즘을 이용하여 영상을 여러 개의 부분 영역으로 나누고, 정의된 부 영역에 영상 분할 기법을 적용함으로써 부 영역들에 적합한 여러 개의 임계치값을 계산함으로써 영상 분할 성능을 개선하고자 하였다.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2006년도 학술대회 1부
• /
• pp.926-930
• /
• 2006

Current image retrieval techniques have shortcomings that make it difficult to search for images based on a semantic understanding of what the image is about. Since an image is normally associated with multiple contexts (e.g. when and where a picture was taken,) the knowledge of these contexts can enhance the quantity of semantic understanding of an image. In this paper, we present a context-aware image retrieval system, which uses the context information to infer a kind of metadata for the captured images as well as images in different collections and databases. Experimental results show that using these kinds of information can not only significantly increase the retrieval accuracy in conventional content-based image retrieval systems but decrease the problems arise by manual annotation in text-based image retrieval systems as well.

• 한국정보통신학회논문지
• /
• 제24권5호
• /
• pp.674-677
• /
• 2020

The cultural background of users utilizing image search engines has a significant impact on the satisfaction of the search results. Therefore, it is important to analyze and understand the cultural context of images for more accurate image search. In this paper, we investigate how the cultural context of images can affect the performance of image classification. To this end, we first collected various types of images (e.g,. food, temple, etc.) with various cultural contexts (e.g., Korea, Japan, etc.) from web search engines. Afterwards, a deep transfer learning approach using VGG19 and MobileNetV2 pre-trained with ImageNet was adopted to learn the cultural features of the collected images. Through various experiments we show the performance of image classification can be differently affected according to the cultural context of images.

• 대한의용생체공학회:의공학회지
• /
• 제40권5호
• /
• pp.179-188
• /
• 2019

In ultrasound telemedicine, it is important to reduce the size of the data by compressing the ultrasound image when sending it. Ultrasound images can be divided into image context and other information consisting of patient ID, date, and several letters. Between them, ultrasound context is very important information for diagnosis and should be securely preserved as much as possible. In several previous papers, ultrasound compression methods were proposed to compress ultrasound context and other information into different compression parameters. This ultrasound compression method minimized the loss of ultrasound context while greatly compressing other information. This paper proposed the method of automatic segmentation of ultrasound context to overcome the limitation of the previously described ultrasound compression method. This algorithm was designed to robust for various ultrasound device and to enable real-time operation to maintain the benefits of ultrasound imaging machine. The operation time of extracting ultrasound context through the proposed segmentation method was measured, and it took 311.11 ms. In order to optimize the algorithm, the ultrasound context was segmented with down sampled input image. When the resolution of the input image was reduced by half, the computational time was 126.84 ms. When the resolution was reduced by one-third, it took 45.83 ms to segment the ultrasound context. As a result, we verified through experiments that the proposed method works in real time.

• 디지털융복합연구
• /
• 제10권4호
• /
• pp.129-136
• /
• 2012

본 연구는 기업의 사회공헌활동에 관한 인터넷 기사의 맥락을 활용한 기업광고 전략을 제시하고자 하였다. 이를 위해 인터넷 기사맥락을 긍정과 부정으로 구분하고, 인터넷 기사의 주목도를 고/저 집단으로 구분한 후 광고태도와 기업이미지에 미치는 상호작용 효과를 검증하였다. 연구결과 첫째, 인터넷 기사의 주목도가 낮은 조건에서, 긍정 맥락이 부정맥락보다 회상율이 높게 나타났다. 둘째, 인터넷 기사의 맥락과 주목도에 따른 광고태도는 상호작용효과가 나타났다. 셋째, 인터넷 기사의 맥락과 주목도에 따른 기업이미지는 상호작용효과가 나타났다. 끝으로 인터넷 기사의 맥락과 주목도에 따른 기업경영 경쟁력은 상호작용효과가 나타났다. 따라서 인터넷 기사의 맥락과 주목도 수준에 따른 광고의 맥락효과를 확인함으로써 소비자의 광고 인지도와 호의적인 기업광고태도 그리고 기업이미지의 향상과 기업경영의 경쟁력 제고에 효과적인 전략방안이 될 수 있음을 시사한다.

• 전기학회논문지
• /
• 제56권12호
• /
• pp.2251-2256
• /
• 2007

In this paper, the wavelet transform based lossless image compression algorithm is proposed. The proposed algorithm transforms the input image using 9/7 ICFB and S+P filter, and eliminates the spacious correlation of the subband coefficients, applying the context modeling predictive technique based on the multi-resolution structure and the feedback of the prediction error. The prediction context exploits the subordination and direction property of the different level subband in the vertical, horizontal, and diagonal subband coefficients. The simulation result of the high frequency images such as PEPPERS, BOAT, and AIRPLANE shows that the proposed algorithm efficiently predicts the edge area of each multi-resolution subband.

• 복식문화연구
• /
• 제12권2호
• /
• pp.199-210
• /
• 2004

This study was intended to identify the differences in perception of image words and perception dimension of desired image according to sex variable for college students in a school context. Data were collected by questionnaires distributed to 443 college students from August to September of 2000. After eliminating incomplete questionnaires, 396 were analyzed. As results of factor analysis, 7 desired image factors were determined for male and female, respectively. On the basis of these results, major perception differences were identified according to sex variable. Differently-perceived image words were as fellows: For intellectual image, male relates it with sporty while female relates it with graceful; for masculine image, male relates it with mature while female relates it with sporty; and for feminine image, male relates it with sexy and graceful while female relates it modest, pure, and cute. Multidimensional scaling was employed to determine the perception dimension of desired image. Two dimensions were accepted to interpret the results for both sex, respectively. 'Feminine-masculine' and 'conspicuous-plain' were criteria for male students, while 'unnatural-natural' and 'feminine-masculine' were criteria for female students.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 추계학술발표회 논문집
• /
• pp.397-402
• /
• 2003

This study is aimed to improve the quality of image fusion results through shadow effects correction. For this, shadow effects correction algorithm is proposed and visual comparisons have been made to estimate the quality of image fusion results. The following four steps have been performed to improve the image fusion qualify First, the shadow regions of satellite image are precisely located. Subsequently, segmentation of context regions is manually implemented for accurate correction. Next step, to calculate correction factor we compared the context region with the same non-shadow context region. Finally, image fusion is implemented using collected images. The result presented here helps to accurately extract and interpret geo-spatial information from satellite imagery.