• 제목/요약/키워드: Texture Similarity

검색결과 130건 처리시간 0.025초

비지역적 유사성 및 3차원 필터링 기반 영상 잡음제거 (Image Denoising Using Nonlocal Similarity and 3D Filtering)

  • 김시현
    • 한국정보통신학회논문지
    • /
    • 제21권10호
    • /
    • pp.1886-1891
    • /
    • 2017
  • 영상 신호 처리 분야 중 잡음제거(denoising)는 가산 잡음이 포함된 영상의 복원을 다룬다. 자연 영상은 지역적 유사성 뿐 만 아니라 비지역적 유사성도 높다는 점은 널리 알려져 있다. 즉, 입력 영상의 특성을 결정짓는 에지나 텍스쳐 패턴이 떨어져 있는 영역에서도 반복적으로 나타난다. 본 논문에서는 비지역적 유사도가 높은 영상 블록을 검출하여 과충분한 신호 집합을 만들고 이를 3차원 변환을 통해 희소(sparse)하게 표현한 후 영상에 포함된 잡음 성분을 제거하는 잡음제거 알고리듬을 제안한다. 여러 영상에 대해 잡음제거 결과로부터 제안된 알고리듬이 부드러운 영역과 에지 영역을 잘 살려 원 영상을 복원할 수 있음을 알 수 있고, 또한 최근 보고된 여러 잡음제거 알고리듬들과의 복원 성능 비교를 통해 상대적으로 우수한 성능을 보임을 확인하였다.

DC값 차이와 AC계수 유사성을 이용한 방향성 블록 보간 (Directional Interpolation of Lost Block Using Difference of DC values and Similarity of AC Coefficients)

  • 이홍엽;엄일규;김유신
    • 한국통신학회논문지
    • /
    • 제30권6C호
    • /
    • pp.465-474
    • /
    • 2005
  • 본 논문은 잡음이 존재하는 전송 선로를 통해 전송된 영상의 손실 블록에 대해 방향성 복구 방법을 제안한다. 손실된 DCT 계수나 화소값들은 손실된 블록 주위의 마주보는 블록 간 DC값 차이(DDC:Difference of DC)와 AC계수의 유사성(SAC: Similarity of AC)으로 구성된 방향성 척도에 의해 적응적으로 선택되어진 이웃 블록들을 이용해서 선형 보간법으로 복구된다. 본 논문에서 제안하는 방향성 복구 방법은 고정된 이웃 블록을 이용하지 않고 국부 영상 내의 방향성 정보에 따라 적응적으로 변하는 이웃 블록들이 사용하기 때문에 강한 에지 성분이나 텍스쳐 영역에 대해서 효과적이다. 본 논문에서는 DDC와 SAC로 구성된 새로운 방향성 척도(CDS: Combination of DDC and SAC)를 구하고 그 방향성 척도를 통해 국부 영역의 특성에 따라 손실된 블록을 복구하기 위한 블록들을 선택한다. 모의실험에서 제안 방법은 기존의 방법보다 평균적으로 약 0.6dB의 PSNR 개선을 보였다.

Image Denoising Based on Adaptive Fractional Order Anisotropic Diffusion

  • Yu, Jimin;Tan, Lijian;Zhou, Shangbo;Wang, Liping;Wang, Chaomei
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제11권1호
    • /
    • pp.436-450
    • /
    • 2017
  • Recently, the method based on fractional order partial differential equation has been used in image processing. Usually, the optional order of fractional differentiation is determined by a lot of experiments. In this paper, a denoising model is proposed based on adaptive fractional order anisotropic diffusion. In the proposed model, the complexity of the local image texture is reflected by the local variance, and the order of the fractional differentiation is determined adaptively. In the process of the adaptive fractional order model, the discrete Fourier transform is applied to compute the fractional order difference as well as the dynamic evolution process. Experimental results show that the peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) of the proposed image denoising algorithm is better than that of other some algorithms. The proposed algorithm not only can keep the detailed image information and edge information, but also obtain a good visual effect.

내용기반 영상검색 시스템 (Content-based Image Retrieval System)

  • 유헌우;장동식;정세환;박진형;송광섭
    • 대한산업공학회지
    • /
    • 제26권4호
    • /
    • pp.363-375
    • /
    • 2000
  • In this paper we propose a content-based image retrieval method that can search large image databases efficiently by color, texture, and shape content. Quantized RGB histograms and the dominant triple (hue, saturation, and value), which are extracted from quantized HSV joint histogram in the local image region, are used for representing global/local color information in the image. Entropy and maximum entry from co-occurrence matrices are used for texture information and edge angle histogram is used for representing shape information. Relevance feedback approach, which has coupled proposed features, is used for obtaining better retrieval accuracy. Simulation results illustrate the above method provides 77.5 percent precision rate without relevance feedback and increased precision rate using relevance feedback for overall queries. We also present a new indexing method that supports fast retrieval in large image databases. Tree structures constructed by k-means algorithm, along with the idea of triangle inequality, eliminate candidate images for similarity calculation between query image and each database image. We find that the proposed method reduces calculation up to average 92.9 percent of the images from direct comparison.

  • PDF

형태 전역특징과 히스토그램을 이용한 내용 기반 영상 검색 시스템 (Content based Image Retrieval System by Shape Global Feature and Histogram)

  • 황병곤;정성호;이상열
    • 한국산업정보학회논문지
    • /
    • 제7권4호
    • /
    • pp.9-16
    • /
    • 2002
  • 멀티미디어 정보검색 중 내용기반 영상검색은 색상, 질감, 형태 등의 영상 내용 특징들을 이용하여 검색하는 방법으로, 색상과 질감 특징이 영상 검색 시스템에서 일반적으로 널리 사용되고 있다. 그러나 이 시스템은 영상의 형태가 서로 다른 경우 서로 다른 내용을 나타내므로 유사 영상검색에서 오류를 수반할 수 있다. 그러므로 영상의 특징을 나타내는 형태의 사용은 효과적인 내용기반 영상검색에서 중요하다. 그래서 본 논문에서는 영상의 윤곽선에 의한 전역 특징 필터링 처리 후에 형태정보의 히스토그램에 의한 성능이 더 우수한 형태 유사도 영상 검색 시스템을 개발한다.

  • PDF

The Need for Research on the Comparison of Sensory Characteristics between Cultured Meat Produced Using Scaffolds and Meat

  • Sol-Hee Lee;Jungseok Choi
    • 한국축산식품학회지
    • /
    • 제44권2호
    • /
    • pp.269-283
    • /
    • 2024
  • Cultured meat is one of the research areas currently in the spotlight in the agricultural and livestock industry, and refers to cells obtained from livestock that are proliferated and differentiated and processed into edible meat. These cell-cultured meats are mainly studied at the lab-scale by culturing them in flasks, and for commercial use, they are produced using scaffolds that mimic cell supports. Scaffolds are broadly divided into fiber scaffolds, hydrogels, and micro-carrier beads, and these are classified according to processing methods and materials. In particular, a scaffold is essential for mass production, which allows it to have appearance, texture, and flavor characteristics similar to meat. Because cultured meat is cultured in a state where oxygen is blocked, it may be lighter in color or produce less flavor substances than edible meat, but these can be compensated for by adding natural substances to the scaffolds or improving fat adhesion. In addition, it has the advantage of being able to express the texture characteristics of the scaffolds that make up the meat in various ways depending on the materials and manufacturing methods of the scaffolds. As a result, to increase consumers' preference for cultured meat and its similarity to edible meat, it is believed that manufacturing scaffolds taking into account the characteristics of edible meat will serve as an important factor. Therefore, continued research and interest in scaffolds is believed to be necessary.

우리나라 포(袍)와 터키 Sultans′의 의례용 외의 형태 비교 연구 - 1400∼1800년대를 중심으로 - (A Comparisonal Study between Korean Po and Turkish Sultans′ Dress)

  • 이상은;김영란
    • 한국의상디자인학회지
    • /
    • 제6권1호
    • /
    • pp.55-63
    • /
    • 2004
  • The dress culture of Korea and Turkey should be necessary to study in view of a similar culture of Korea and Turkey due to similarity of oriental culture. Thus, as two nation's dress is investigated, cultural characteristics and dress form of two nations are analyzed with cultural background in detail. Also, comprehension is determinated for the dress color and texture as well as dress culture. In this paper, It is investigated theoretically for the function, type, and class of dress. Also, The form of Korean Po are compared to background of Turkish dress and Sulltans' dress form. To unify a cultural propagation and dress form, technical, inductive contents analytical method as well as literature review are used in positivism. Subject is limited to the Korean Po and Sultans' dress of Turkey. As a results, as the nation's dress reflect to culture and society of the nation, Korean dress have some similarity and differences comparing Turkish dress as followings. In dress form of two nation, rectangular Gil's shape was very similar. Mu's shape was similar too. However, Sultans' dress had outside shape of caftan type and Po had full or partial wrinkles by transforming Mu. Also, Sultans' dress did not have Sup. Korean Po have side slits or back side slits and Jun-Sam but Sultans' dress had only some side slits.

  • PDF

MRI Image Retrieval Using Wavelet with Mahalanobis Distance Measurement

  • Rajakumar, K.;Muttan, S.
    • Journal of Electrical Engineering and Technology
    • /
    • 제8권5호
    • /
    • pp.1188-1193
    • /
    • 2013
  • In content based image retrieval (CBIR) system, the images are represented based upon its feature such as color, texture, shape, and spatial relationship etc. In this paper, we propose a MRI Image Retrieval using wavelet transform with mahalanobis distance measurement. Wavelet transformation can also be easily extended to 2-D (image) or 3-D (volume) data by successively applying 1-D transformation on different dimensions. The proposed algorithm has tested using wavelet transform and performance analysis have done with HH and $H^*$ elimination methods. The retrieval image is the relevance between a query image and any database image, the relevance similarity is ranked according to the closest similar measures computed by the mahalanobis distance measurement. An adaptive similarity synthesis approach based on a linear combination of individual feature level similarities are analyzed and presented in this paper. The feature weights are calculated by considering both the precision and recall rate of the top retrieved relevant images as predicted by our enhanced technique. Hence, to produce effective results the weights are dynamically updated for robust searching process. The experimental results show that the proposed algorithm is easily identifies target object and reduces the influence of background in the image and thus improves the performance of MRI image retrieval.

Baggage Recognition in Occluded Environment using Boosting Technique

  • Khanam, Tahmina;Deb, Kaushik
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제11권11호
    • /
    • pp.5436-5458
    • /
    • 2017
  • Automatic Video Surveillance System (AVSS) has become important to computer vision researchers as crime has increased in the twenty-first century. As a new branch of AVSS, baggage detection has a wide area of security applications. Some of them are, detecting baggage in baggage restricted super shop, detecting unclaimed baggage in public space etc. However, in this paper, a detection & classification framework of baggage is proposed. Initially, background subtraction is performed instead of sliding window approach to speed up the system and HSI model is used to deal with different illumination conditions. Then, a model is introduced to overcome shadow effect. Then, occlusion of objects is detected using proposed mirroring algorithm to track individual objects. Extraction of rotational signal descriptor (SP-RSD-HOG) with support plane from Region of Interest (ROI) add rotation invariance nature in HOG. Finally, dynamic human body parameter setting approach enables the system to detect & classify single or multiple pieces of carried baggage even if some portions of human are absent. In baggage detection, a strong classifier is generated by boosting similarity measure based multi layer Support Vector Machine (SVM)s into HOG based SVM. This boosting technique has been used to deal with various texture patterns of baggage. Experimental results have discovered the system satisfactorily accurate and faster comparative to other alternatives.

GPR 자료 해석에 유용한 속성들 소개 및 적용 사례 분석 (Introduction to Useful Attributes for the Interpretation of GPR Data and an Analysis on Past Cases)

  • 유희은;정인석;임보성;남명진
    • 지구물리와물리탐사
    • /
    • 제24권3호
    • /
    • pp.113-130
    • /
    • 2021
  • 지반 침하, 도로 안전성과 같은 사회적 이슈로 지하 공동 분포를 조사하기 위한 지표투과레이더(ground penetrating radar, GPR) 탐사가 활발히 진행되면서 자료의 양도 함께 증가하고 있다. 하지만 비용과 시간의 효율성을 고려해보았을 때, 모든 자료를 해석할 수 없기 때문에 더욱 직관적이고 정확한 판단이 가능한 해석법이 필요하다. 이러한 문제를 개선하기 위해 정량적 해석이 가능한 속성 분석법이 제안되고 있다. 탄성파 해석에서 많이 사용해온 속성 분석 중 GPR 자료에 적용할 수 있는 속성으로는 복소 트레이스(complex trace)와 유사성(similarity)이 대표적이다. 또한, 최근 영상처리 기술의 발달로 개발된 새로운 속성인 모서리탐지 속성, 이미지 질감 속성 등도 적용성이 있다. 이 논문에서는 GPR 자료 속성분석 연구의 기초를 마련하기 위해, GPR에 적용할 수 있는 속성 분석들을 소개하고 이들의 개념에 대해 기술한 뒤, 속성분석에 기초한 해석법과 다양한 분야에서 활용한 사례를 분석하고자 한다.