• Title/Summary/Keyword: 색상 분할

Search Result 387, Processing Time 0.022 seconds

Face and Hand Tracking Algorithm for Sign Language Recognition (수화 인식을 위한 얼굴과 손 추적 알고리즘)

  • Park, Ho-Sik;Bae, Cheol-Soo
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.31 no.11C
    • /
    • pp.1071-1076
    • /
    • 2006
  • In this paper, we develop face and hand tracking for sign language recognition system. The system is divided into two stages; the initial and tracking stages. In initial stage, we use the skin feature to localize face and hands of signer. The ellipse model on CbCr space is constructed and used to detect skin color. After the skin regions have been segmented, face and hand blobs are defined by using size and facial feature with the assumption that the movement of face is less than that of hands in this signing scenario. In tracking stage, the motion estimation is applied only hand blobs, in which first and second derivative are used to compute the position of prediction of hands. We observed that there are errors in the value of tracking position between two consecutive frames in which velocity has changed abruptly. To improve the tracking performance, our proposed algorithm compensates the error of tracking position by using adaptive search area to re-compute the hand blobs. The experimental results indicate that our proposed method is able to decrease the prediction error up to 96.87% with negligible increase in computational complexity of up to 4%.

Implementation of Computerized Assistant Diagnosis Software for Tongue Diagnosis in the Oriental Medicine (한방 설진을 위한 컴퓨터 지원 진단 소프트웨어 구현)

  • Lee, Woo Beom
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.51 no.6
    • /
    • pp.175-182
    • /
    • 2014
  • Development of an objective diagnosis index for diagnosing a the beginning nature of a disease is the most one of tongue diagnosis in the oriental medicine. However, previous systems have a difficult problem in the creation of objective diagnosis index, and focused on the expert system that can diagnose automatically without an oriental doctor behavior. Therefore, computerized assistant diagnosis software for calculating an optimized diagnosis index is proposed in this paper. This software is operated by the diagnosing behavior of oriental doctor. As developed software is a semi-automatic system, manual method is used to segment a tongue body. Futhermore, numerical diagnosis indices including the color information of non-tongue coating and tongue coating, WTCI are provided to oriental doctor automatically and real-timely. Also, probability estimation value for classifying no coating, thin coating, and thick coating is presented by using the tongue coating area ratio, and EMR chart can use for convenience of diagnosis. In order to evaluate the effectiveness of the our developed software, after building a various tongue image from 60 subjects, we experimented on diagnosis image with our software. As a result, the developed software showed the 95% use-effectiveness of subjects.

Motion Estimation Method by Using Depth Camera (깊이 카메라를 이용한 움직임 추정 방법)

  • Kwon, Soon-Kak;Kim, Seong-Woo
    • Journal of Broadcast Engineering
    • /
    • v.17 no.4
    • /
    • pp.676-683
    • /
    • 2012
  • Motion estimation in video coding greatly affects implementation complexity. In this paper, a reducing method of the complexity in motion estimation is proposed by using both the depth and color cameras. We obtain object information with video sequence from distance information calculated by depth camera, then perform labeling for grouping pixels within similar distances as the same object. Three search regions (background, inside-object, boundary) are determined adaptively for each of motion estimation blocks within current and reference pictures. If a current block is the inside-object region, then motion is searched within the inside-object region of reference picture. Also if a current block is the background region, then motion is searched within the background region of reference picture. From simulation results, we can see that the proposed method compared to the full search method remains the almost same as the motion estimated difference signal and significantly reduces the searching complexity.

Spatiotemporal Saliency-Based Video Summarization on a Smartphone (스마트폰에서의 시공간적 중요도 기반의 비디오 요약)

  • Lee, Won Beom;Williem, Williem;Park, In Kyu
    • Journal of Broadcast Engineering
    • /
    • v.18 no.2
    • /
    • pp.185-195
    • /
    • 2013
  • In this paper, we propose a video summarization technique on a smartphone, based on spatiotemporal saliency. The proposed technique detects scene changes by computing the difference of the color histogram, which is robust to camera and object motion. Then the similarity between adjacent frames, face region, and frame saliency are computed to analyze the spatiotemporal saliency in a video clip. Over-segmented hierarchical tree is created using scene changes and is updated iteratively using mergence and maintenance energies computed during the analysis procedure. In the updated hierarchical tree, segmented frames are extracted by applying a greedy algorithm on the node with high saliency when it satisfies the reduction ratio and the minimum interval requested by the user. Experimental result shows that the proposed method summaries a 2 minute-length video in about 10 seconds on a commercial smartphone. The summarization quality is superior to the commercial video editing software, Muvee.

Colorimetric and Chemical Characteristics of Grey Leaf Tobacco (Grey 증상 잎담배의 색채 및 화학성분 특성)

  • 이철환;진정의
    • KOREAN JOURNAL OF CROP SCIENCE
    • /
    • v.40 no.3
    • /
    • pp.359-364
    • /
    • 1995
  • This experiment was conducted to get the fundamental information about the difference in color and some chemical components of grey flue-cured tobacco cultivated in paddy field to compare with normal tobacco. Cured leaves of NC82 were separated with visual characters into three classes of slight, fair and severe symptoms of grey leaf by percentage of grey parts to whole leaf area, and compared to normal ones. Occurrence of grey leaves tended to be higher in lower stalk position than in upper ones. Cl, Mn and Fe content of grey leaves was much higher when it compared with normal leaves, and within the same leaf, grey parts were increased in Fe, Mn and Cl content than in those of normal parts but there was no appearent difference in total sugar, nicotine and Ca contents. Chemical analysis of grey leaf samples indicated that they contained more Fe, Mn and Cl contents than those of normal leaves. These tendencies in chemical traits were accordance with the degree of grey symptoms. Grey leaves showed remarkably lower b*value and slightly lower L*value than those of normal leaves, while a*value was mostly higher in grey leaves. In general, grey appearence of grey flue-curd tobacco seemed to be from less yellowish color, poorer brightness with more brownish or reddish color.

  • PDF

Classification of Brain Magnetic Resonance Images using 2 Level Decision Tree Learning (2 단계 결정트리 학습을 이용한 뇌 자기공명영상 분류)

  • Kim, Hyung-Il;Kim, Yong-Uk
    • Journal of KIISE:Software and Applications
    • /
    • v.34 no.1
    • /
    • pp.18-29
    • /
    • 2007
  • In this paper we present a system that classifies brain MR images by using 2 level decision tree learning. There are two kinds of information that can be obtained from images. One is the low-level features such as size, color, texture, and contour that can be acquired directly from the raw images, and the other is the high-level features such as existence of certain object, spatial relations between different parts that must be obtained through the interpretation of segmented images. Learning and classification should be performed based on the high-level features to classify images according to their semantic meaning. The proposed system applies decision tree learning to each level separately, and the high-level features are synthesized from the results of low-level classification. The experimental results with a set of brain MR images with tumor are discussed. Several experimental results that show the effectiveness of the proposed system are also presented.

Changes in Physicochemical Characteristics of Mature-Green Mume (Prunus mume Sieb. et Zucc) Fruits as Influenced by the Thickness of Packaging Material (포장재 두께에 따른 청매실의 이화학적 특성 변화)

  • 차환수;정명수
    • Food Science and Preservation
    • /
    • v.9 no.2
    • /
    • pp.148-153
    • /
    • 2002
  • Effect of the thickness of low density polyethylene(LDPE) Film as packaging material on changes in physicochemical characteristics of mature-green mume (Prunus mume Sieb. et Zucc) fruits during storage at different temperatures(0, 10 and 25$\^{C}$) were investigated. Fruit samples stored in pouches with 30㎛ thickness of LDPE film maintained well not only external qualities such as Shape and firmness, but also internal chemical properties such as pH, acidity, the content of soluble solid and chlorophyll, and color, comparing with samples stored without packaging material or in other pouches with different film thickness(20 and 40㎛). From the results, it was found that the maintenance of quality of mature-green mume fruits during storage at 0, 10 and 25$\^{C}$ closely related to the changes in respiratory conditions for fruits affected by the film thickness of the packaging material.

Quality Characteristics of Julpyun added with Silkworm Powder (누에분말을 첨가한 절편의 영양성분 및 품질 특성)

  • 임영희;김애정;김명희;김미원
    • Journal of the East Asian Society of Dietary Life
    • /
    • v.12 no.2
    • /
    • pp.129-134
    • /
    • 2002
  • Julpyun(traditional Korean rice cake) was prepared by adding silkworm powder(SP) in the ratio of 0%, 3%, 6%, 9% of rice flour, and tested by proximate composition, sensory evaluation, chromaticity and rheological properties. In proximate composition, as the SP increased, amounts of moisture, crude protein and ash increased proportionally. In sensory evaluation test, 6% SP added Julpyun showed the highest score in color, Julpyun added with 3% SP gave the strongest flavor. From the scores of taste, texture and overall quality, 3% SP added Julpyun was evaluated as the best. In rheometer test, hardness increased as the amount of SP increased. Gumminess and brittleness tended to decrease as the ratio of SP increased and 3% SP added Julpyun showed the high value in them.

  • PDF

Cut detection methods of real-time image sequences using color characteristics (컬러 특성을 이용한 실시간 동영상의 cut detection 기법)

  • Park, Jin-Nam;Lee, Jae-Duck;Huh, Young
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.39 no.1
    • /
    • pp.67-74
    • /
    • 2002
  • A study on image searching and management techniques is actively developed by user requirements for multimedia information that are existing as images, audios, texts data from various information processing devices. If we can automatically detect and segment changing scenes from real-time image sequences, we can improve an effectiveness of image searching systems. In this paper, we propose cut detection techniques based on image color distribution and we evaluated its performance on various real-time image sequences. Results of experiments show that the proposed method are robust on various image patterns than color histogram method using statistical informations of images. Also, these methods can be used for cut detection on real-time image sequences.

Quality changes in Rubus coreanus Miquel during Frozen Storage (냉동 저장 중 복분자딸기(Rubus coreanus Miq.)의 품질 변화)

  • Youn, Aye-Ree;Kwon, Ki-Hyun;Kim, Byeong-Sam;Noh, Bong-Soo;Cha, Hwan-Soo
    • Food Science and Preservation
    • /
    • v.16 no.5
    • /
    • pp.618-622
    • /
    • 2009
  • Ripened Rubus coreanus Miquel harvested at Gochang was stored for 8 months at $-20{\pm}2^{\circ}C$, and quality changes were investigated at intervals of 2-3 months. Soluble solid concentration increased slightly, but acidity fell during frozen storage. The lightness (L value) and red color index (a value) of ripened R. coreanus Miquel decreased during storage. The vitamin C and ellagic acid contents were 30.79 mg/100 g and $155.12\;{\mu}g/100\;mg$ mg before storage, respectively, but fell to 17.03 mg/100g and $140.11\;{\mu}g/100\;mg$ after 8 months of storage. However, the total anthocyanin content was 39.45 mg/100 g before storage, and this remained unchanged from 2 to 8 months of storage.