• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.35-38
• /
• 2013

최근, 대용량 영상 데이터베이스가 축적되면서 영상 인식과 영상 검색 분야가 주목받고 있으며, 다양한 디바이스에 따라 생성되는 영상의 해상도가 상이하게 나타나고 있다. 본 논문에서는 내용-기반 영상 검색을 위한 새로운 칼라 기술자를 제안한다. 제안 알고리즘에서는 공간 칼라 정보에 대한 웨이블릿 변환과 채널 및 변환 서브밴드에 따른 가중치를 적용하여 칼라 특징 벡터를 추출한다. 시뮬레이션을 통하여 제안하는 알고리즘의 검색 성능을 평가하였으며, 유사한 특징 벡터 크기를 기준으로, 기존의 MPEG-7 등의 칼라 검색 기술자보다 다중-해상도의 영상 데이터베이스에서 향상된 검색율을 보임을 확인하였다. 본 논문에서 제시한 알고리즘은 단일 특성의 특징 벡터를 추출하는 검색 기술자로써, 다중 특징으로 결합하기 위한 기본 기술자로 활용될 수 있다.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.5
• /
• pp.111-120
• /
• 2004

The MPEG-7 standard defines a set of descriptors that extracts low-level features such as color, texture and object shape from an image and generates metadata in order to represent these extracted information. But the matching performance for image mining ma y not be satisfactory by u sing only on e of these features. Rather than by combining these features we can achieve a better query performance. In this paper we propose a new image retrieval technique for image mining that combines the features extracted from MPEG-7 visual color and texture descriptors. Specifically, we use only some specifications of Scalable Color Descriptor (SCD) and Non-Homogeneous Texture Descriptor also known as Edge Histogram Descriptor (EHD) for the implementation of the color and edge histograms respectively. MPEG-7 standard defines $l_{1}$-norm based matching in EHD and SCD. But in our approach, for distance measurement, we achieve a better result by using cosine similarity coefficient for color histograms and Euclidean distance for edge histograms. Our approach toward this system is more experimental based than hypothetical.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.397-398
• /
• 2006

본 논문에서는 이미지 검색을 위해 가장 기본적인 요소인 이미지 색상에 따른 칼라 분포정보를 이용하고 다양한 요소에 따라 가중치를 부여한 칼라기반의 검색 기술자를 제안하였고 실험적 평가를 통하여 제안 기술자의 성능을 평가하였다. 칼라 히스토그램을 통한 이미지 검색 기술자를 설계하는데 있어 칼라모델은 HSV, 웨이블릿 변환 필터는 D9/7, 웨이블릿 분해는 2 레벨을 적용하였을 때 가장 좋은 검색효율성을 보였다.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.275-282
• /
• 2006

For the efficient image retrieval, the method has studied that uses color distribution and relations between pixels. This paper presents the color descriptor that stands high above the others in image retrieval capacity. It is based on color co-occurrence histogram that the diagonal part and the non-diagonal part are attached the weight and modified to energy of color co-occurrence histogram, and the number of bins with petty worth have little influence is curtailed. It's verified by analysis that the diagonal part carries size information of homogeneous color region and the non-diagonal part does information about the coherence of it, Moreover the non-diagonal part is more influential than diagonal part in survey of similarity between images. So, the non-diagonal part is attached more weight than the diagonal part as a result of the research. The experiments validate that the proposed descriptor shows better image retrieval performance when the weight for non-diagonal part is set to the value between 0.7 and 0.9.

• Journal of the Korea Computer Industry Society
• /
• v.7 no.5
• /
• pp.537-544
• /
• 2006

Image Search is one of the most exciting and fast growing research areas in the filed of multimedia technology. This paper conducts an empirical evaluation of color descriptor that uses the information of color distribution in color images, which is the most basic element for image search. With the experimental results, we observe that in the top 10% of precision, HSV, Daubechies 9/7 and 2 level decomposition have little better than others. Also histogram quadratic metrics outperform the Minkowski form distance metrics in similarity measurements, but spend more than 20 in computational times.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.148-150
• /
• 2004

최근 멀티미디어 정보를 기술하기 위한 표준인 MPEG-7이 제안되어 이미지/동영상 검색 시스템과 같은 응용분야에서 사용되기 시작하였다. 그러나 MPEG-7 시각 정보 기술자들은 대부분 고차원으로 표현되고 기술자들이 가지는 각 속성들의 성질이 서로 동일하지 않기 때문에 기존의 인덱싱 방법으로는 효율적인 검색을 할 수 없다. 본 논문에서는 MPEG-7 시각 정보 기술자중에서 많이 사용되는 Dominant Color 기술자와 Contour Shape 기술자에 대한 새로운 인덱싱 알고리즘을 제안한다. Dominant Color 기술자에서 사용되는 비 교 연산 식 은 가우스 혼합 모델에 기초하고 있기 때문에, 기술자의 각 속성들을 하냐의 칼라 히스토그램 형태로 변형시켜서 인덱스로 사용한다. Contour Shape기술자는 2 단계 형태의 알고리즘을 사용한다. 각 단계는 글로벌 파라미터 속성과 비트맵 인덱스를 사용한 인덱싱이 적용된다. 제안된 인덱싱 방법을 사용했을 때 Dominant Color의 경우 90%의 정확도에 120배 이상의 속도 향상을 나타냈고, Contour Shape의 경우 82%의 정확도에 3배 이상의 속도 향상을 나타냈다.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.179-188
• /
• 2003

In content-based image retrieval, the query is an image itself and the retrieval process is the process that seeking the similar images to the given query image. In this way of retrieval, the user has to know the basic physical features of target images that he wants to retrieve. But it has some restriction because to retrieve the target image he has to know the basic physical feature space such as color, texture, shape and spatial relationship. In this paper, we propose an emotion-based retrieval system. It uses the emotion that color images have. It is different from past emotion-based image retrieval in point of view that it uses relevance feedback to estimate the users intend and it is easily combined with past content-based image retrieval system. To test the performance of our proposed system, we use MPEG-7 color descriptor and emotion language such as "warm", "clean", "bright" and "delight" We test about 1500 wallpaper images and get successful result.lpaper images and get successful result.

• Journal of Broadcast Engineering
• /
• v.5 no.1
• /
• pp.61-67
• /
• 2000

Generally, relevance, feedback reflecting user's intention has been used to refine the refine the query conditions in image retrieval. However, in this paper, the usage of the relevance feedback is extended to the image database categorization so as to be accommodated to the user independent image retrieval. In our approach, to guarantee a desirable user-satisfactory performance descriptors and the elements of the descriptors corresponding unique features associatiated with of each image are weighted using the relevance feedback where experts can more lead rather than beginners do. In this paper, we propose a proper image description scheme consisting of global information, local information, descriptor weights and element weights based on color and texture descriptors. In addition, we also introduce an appropriate learning method based on the reliability scheme preventing wrong learning from abusive feedback.

• Journal of Broadcast Engineering
• /
• v.5 no.1
• /
• pp.10-22
• /
• 2000

In this paper, we present a texture description method as a standardization of multimedia contents description. Like color, shape, object and camera motion information, texture is one of very important information in the visual part of international standard (MPEG-7) in multimedia contents description. Current MPEG-7 texture descriptor has been designed to fit human visual system. Many psychophysical experiments give evidence that the brain decomposes the spectra into perceptual channels that are bands in spatial frequency. The MPEG-7 texture description method has employed Radon transform that fits with HVS behavior. By taking average energy and energy deviation of HVS channels, the texture descriptor is generated. To test the performance of current texture descriptor, experiments with MPEG-7 Texture data sets of T1 to T7 are performed. Results show that the current MPEG-7 texture descriptor gives better retrieval rate and fast and fast extraction time for texture feature.

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.1-10
• /
• 2007

This paper proposes a new indexing mechanism for MPEG-7 visual descriptors, especially Dominant Color and Contour Shape descriptors, that guarantees an efficient similarity search for the multimedia database whose visual meta-data are represented with MPEG-7. Since the similarity metric used in the Dominant Color descriptor is based on Gaussian mixture model, the descriptor itself could be transform into a color histogram in which the distribution of the color values follows the Gauss distribution. Then, the transformed Dominant Color descriptor (i.e., the color histogram) is indexed in the proposed indexing mechanism. For the indexing of Contour Shape descriptor, we have used a two-pass algorithm. That is, in the first pass, since the similarity of two shapes could be roughly measured with the global parameters such as eccentricity and circularity used in Contour shape descriptor, the dissimilar image objects could be excluded with these global parameters first. Then, the similarities between the query and remaining image objects are measured with the peak parameters of Contour Shape descriptor. This two-pass approach helps to reduce the computational resources to measure the similarity of image objects using Contour Shape descriptor. This paper also proposes two integration schemes of visual descriptors for an efficient retrieval of multimedia database. The one is to use the weight of descriptor as a yardstick to determine the number of selected similar image objects with respect to that descriptor, and the other is to use the weight as the degree of importance of the descriptor in the global similarity measurement. Experimental results show that the proposed indexing and integration schemes produce a remarkable speed-up comparing to the exact similarity search, although there are some losses in the accuracy because of the approximated computation in indexing. The proposed schemes could be used to build a multimedia database represented in MPEG-7 that guarantees an efficient retrieval.