• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.55-66
• /
• 2006

We propose a progressive image retrieval method based on an efficient combination of multiresolution color and torture features in wavelet transform domain. As a color feature, color autocorrelogram of the hue and saturation components is chosen. As texture features, BDIP and BVLC moments of the value component are chosen. For the selected features, we obtain multiresolution feature vectors which are extracted from all decomposition levels in wavelet domain. The multiresolution feature vectors of the color and texture features are efficiently combined by the normalization depending on their dimensions and standard deviation vector, respectively, vector components of the features are efficiently quantized in consideration of their storage space, and computational complexity in similarity computation is reduced by using progressive retrieval strategy. Experimental results show that the proposed method yields average $15\%$ better performance in precision vs. recall and average 0.2 in ANMRR than the methods using color histogram color autocorrelogram SCD, CSD, wavelet moments, EHD, BDIP and BVLC moments, and combination of color histogram and wavelet moments, respectively. Specially, the proposed method shows an excellent performance over the other methods in image DBs contained images of various resolutions.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.122-129
• /
• 2007

As the availability of an image information has been significantly increasing, necessity of system that can manage an image information is increasing. Accordingly, we proposed the content-based image retrieval(CBIR) method based on an efficient combination of a color feature and an image's shape and position information. As a color feature, a HSI color histogram is chosen which is known to measure spatial of colors well. Shape and position information are obtained using Hu invariant moments in the luminance of HSI model. For efficient similarity computation, the extracted features(Color histogram, Hu invariant moments) are combined and then measured precision. As a experiment result using DB that was supported by http://www.freefoto.com, the proposed image search engine has 93% precision and can apply successfully image retrieval applications.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.2
• /
• pp.48-55
• /
• 2008

In this paper we propose a novel method for image retrieval system using image segmentation and salient points. The proposed method consists of four steps. In the first step, images are segmented into several regions by JSEG algorithm. In the second step, for the segmented regions, dominant colors and the corresponding color histogram are constructed. By using dominant colors and color histogram, we identify candidate regions where objects may exist. In the third step, real object regions are detected from candidate regions by SIFT matching. In the final step, we measure the similarity between the query image and DB image by using the color correlogram technique. Color correlogram is computed in the query image and object region of DB image. By experimental results, it has been shown that the proposed method detects multi-object very well and it provides better retrieval performance compared with object-based retrieval systems.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.1
• /
• pp.42-48
• /
• 2016

Since a variety of sound occur in same place and similar sound occurs in other places, the performance of acoustic scene classification is not guaranteed in case of insufficient training data. A Bag of Words (BOW) based histogram feature is foreseen as a method to overcome the problem. However, since the histogram features is made by using a feature distribution, the ordering of sequence of features is ignored. A temporal information such as periodicity and stationarity are also important for acoustic scene classification. In this paper, temporal features about a periodicity and a stationarity are extracted by using a recurrent quantification analysis. In the experiment, performance of the proposed method is shown better than other baseline methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.346-351
• /
• 2006

본 논문은 콘크리트 표면 균열 영상에서 균열의 특징을 추출하기 위해, 영상 처리 기법을 적용하여 균열의 특징(길이, 폭, 방향)을 자동으로 추출 및 처리 할 수 있는 기법을 제안한다. 본 논문에서 적용된 영상 처리 기법으로는 균열 영상의 빛을 보정하기 위하여 모폴로지 기법인 채움(Closing)기법을 적용한다. 균열의 경계를 명확히 추출하기 위하여 고주파 강화 필터링을 적용한 후, 8가지 색상(검정, 빨강, 파랑, 초록, 노랑, 자주, 주황, 하늘)으로 명암 값을 분류하고 그 중 빈도수가 가장 높은 색상을 가진 명암 값을 제거한 후에 추출한 영상을 이진화한다. 이진화된 영상에서 콘크리트 표면 균열의 실거리 측정을 위한 임의의 선을 제거하기 위하여 위치 히스토그램을 적용하여 임의의 선을 제거한다. 임의의 선이 제거된 균열 영상에서 $5\times5$ 마스크를 적용하여 균열을 확대시키고, 3차례에 걸쳐 잡음 제거연산을 수행하여 균열의 후보 영역을 선택한 후, 후보 영역으로부터 특정 균열들을 추출한다. 추출된 특정 균열을 모폴로지 기법인 제거(Opening) 연산을 수행하여 균열의 특징이 일정하게 유지되게 하고 미세하게 끊어진 부분을 보정하여 균열의 특징(길이, 방향, 폭)을 측정한다. 실제 콘크리트 표면 균열영상을 대상으로 실험한 결과, 특정 균열이 효율적으로 추출되었고, 특정 균열의 길이, 방향, 폭의 등이 정확히 추출 및 계산되었다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.9
• /
• pp.889-897
• /
• 2010

Recently, a cutting-edge large-scale image database system has demanded these attributes: search with alarming speed, performs with high accuracy, archives efficiently and much more. An image identifier (descriptor) is for measuring the similarity of two images which plays an important role in this system. The extraction method of an image identifier can be roughly classified into two methods: a local and global method. In this paper, the proposed image identifier, LFH(Local Feature's Histogram), is obtained by a histogram of robust and distinctive local descriptors (features) constrained by a district sub-division of a local region. Furthermore, LFH has not only the properties of a local and global descriptor, but also can perform calculations at a magnificent clip to determine distance with pinpoint accuracy. Additionally, we suggested a way to extract LFH via GPU (OpenGL and GLSL). In this experiment, we have compared the LFH with SIFT (local method) and EHD (global method) via storage capacity, extraction and retrieval time along with accuracy.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.274-276
• /
• 2001

최근 많이 사용되는 대용량의 뉴스 비디오의 편리한 검색 및 관리 방법이 필요하게 되면서 뉴스 비디오 데이터를 자동으로 분석하여 저급 수준의 정보로부터 고급 수준의 내용 정보를 자동으로 추출하는 기술이 필요하게 되었다. 특히 뉴스를 요약하는데 있어서는 이런 기술이 더 유용하게 쓰일 수 있다. 앵커, 그래픽, 인터뷰, 기자보도, 회견/연설 장면 등이 뉴스 비디오의 고급 수준 내용 정보가 될 수 있는데 그 중에서도 앵커 장면은 뉴스의 기사를 나누는 고급 수준의 정보로서 중요한 의미를 갖게 된다. 본 논문에서는 이러한 앵커 장면을 자동으로 추출하는 방법을 제안한다. 앵커 장면의 공통된 특징을 이용하여 검출하게 되는데 첫 번째 특징은 한 뉴스 프로그램을 진행하는 앵커는 동일하다는 점이고 두 번째 특징은 동일한 스튜디오 안이라는 점이다. 본 논문에서는 앵커를 판별하는 방법으로 얼굴의 검출방법과 옷 색깔의 히스토그램 비교방법을 이용한다. 본 논문의 알고리즘을 여러 개의 KBS 9시 뉴스 비디오 데이터에 적용하여 실험한 결과 Recall과 Precision 모두 96% 이상 나오는 것을 알 수 있었다.

• The KIPS Transactions:PartB
• /
• v.12B no.1 s.97
• /
• pp.31-38
• /
• 2005

This paper proposes an object-based image retrieval scheme using color adjacency and clustering method. Color adjacency features in boundary regions are utilized to extract candidate blocks of interest from image database and a clustering method is used to extract the regions of interest(ROI) from candidate blocks of interest. To measure the similarity between the query and database images, the histogram intersection technique is used. The color pair information used in the proposed method is robust against translation, rotation, and scaling. Consequently, experimental results have shown that the proposed scheme is superior to existing methods in terms of ANMRR.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.501-508
• /
• 2002

In this paper, we propose a content-based image retrieval using the color ratio and moment of object region. We acquire an optimal spatial information by the region splitting that utilizes horizontal-vertical projection and dominant color. It is based on hypothesis that an object locates in the center of image. We use color ratio and moment as feature informations. Those are extracted from the splitted regions and have the invariant property for various transformation, and besides, similarity measure utilizes a modified histogram intersection to acquire correlation information between bins in a color histogram. In experimental results, the proposed method shows more flexible and efficient performance than existing methods based on region splitting.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.7
• /
• pp.901-914
• /
• 2002

In this paper, We propose an efficient automatic caption detection and location method, caption recognition using FE-MCBP(Feature Extraction based Multichained BackPropagation) neural network for content based retrieval of video. Frames are selected at fixed time interval from video and key frames are selected by gray scale histogram method. for each key frames, segmentation is performed and caption lines are detected using line scan method. lastly each characters are separated. This research improves speed and efficiency by color segmentation using local maximum analysis method before line scanning. Caption detection is a first stage of multimedia database organization and detected captions are used as input of text recognition system. Recognized captions can be searched by content based retrieval method.