Norimichi Tsumura

Chiba University, Tiba, Chiba, Japan

Are you Norimichi Tsumura?

Claim your profile

Publications (187)45.76 Total impact

  • Misa Hirose, Yuri Tatsuzawa, Saori Toyota, Norimichi Tsumura
    [Show abstract] [Hide abstract]
    ABSTRACT: In this research, we evaluate the visibility of age spot and freckle with changing the blood volume based on the actual facial color images and compare the result with that of pigmentation patterns generated by simulated spectral reflectance. We acquire the concentration distribution of melanin, hemoglobin and shading components by applying the independent component analysis on a facial color image. We reconstruct images by using the obtained melanin and shading concentration and the changed hemoglobin concentration to generate facial images with changing the blood volume. Finally, we evaluate the visibility of pigmentations using these images and compare with the result of pigmentation patterns based on simulated reflectance. In our previous study, we have already evaluated the visibility of pigmentation patterns, and the visibility became lower as the blood volume increases. However, we can see that a specific blood volume reduce the visibility of the actual pigmentations from the result of evaluating the skin color images.
    Color and Imaging Conference. 11/2014;
  • [Show abstract] [Hide abstract]
    ABSTRACT: We present a rendering method to reproduce translucent appearances in real-time. Since the translucency is caused by complicated light behavior such as scattering and absorption, reproducing translucent material requires computationally expensive cost. Due to its computational cost, it is difficult to apply the digital mock-up with the computer graphics for the purpose of cost reduction and acceleration of developing products. In order to reproduce the translucent appearance rapidly, we focus on the contrast-reversing image processing. We embed this simple image processing method to the reflection model. Our proposed method can reproduce in real-time with almost the same appearance compared to commercial rendering software.
    Color and Imaging Conference. 11/2014;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Abstract In this article, principal component analysis is applied to pigmentation distribution in the whole face to obtain feature values, and the relationship between the obtained feature vectors and age is estimated by multiple regression analysis to simulate the changes of facial images in women of ages 10 to 80. Since the human face receives more attention than other body parts, a change of a small quantity of the features in a face makes a large difference to its appearance. We can divide the features into two categories. One category is physical features such as skin condition and shape, and the other is physiological features, which are influenced by age and health. In the beauty industry, the synthesis of skin texture is based on these two kinds of feature values. Previous works have analyzed only small areas of skin texture. By morphing the shapes of facial images to that of an average face and extending the analyzed area to the whole face, the authors’ method can analyze pigmentation distributions in the whole face and simulate the appearance of a face as a function of changing the person’s age.
    Biocontrol Science and Technology 01/2014; 58(2). · 0.71 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we apply principal component analysis to pigmentation distribution in whole face and obtain feature values. Furthermore, we estimate the relationship between the obtained vectors and the ages and simulate the changes of women facial image from in her 20s to in her any age by multiple regression analysis. Human faces is the well-known part which receive a lot of attention in the body. Changing the small quantity of the features in faces make large differences in their appearance. The features which we can receive divide broadly into two categories. One is the physical feature such as skin condition and its shape, and another one is the psychological features such as the ages and the health. In the beauty industry it is required to synthesize the skin texture based on the two kinds of the feature values. Previous works remain in the analysis of the skin texture using small area. By morphing shape of facial images to that of average face and extending the analyzed area to whole face, our method can analyze pigmentation distribution in whole face and simulate appearance of face by changing the age.
    Color and Imaging Conference. 01/2013;
  • Kimiyoshi Miyata, Norimichi Tsumura
    [Show abstract] [Hide abstract]
    ABSTRACT: A concept of image quality metamerism as an expansion of conventional metamerism defined in color science is introduced, and it is applied to segment similar color areas in a cultural property. The image quality metamerism can unify different image quality attributes based on an index showing the degree of image quality metamerism proposed. As a basic research step, the index is consisted of color and texture information and examined to investigate a cultural property. The property investigated is a pair of folding screen paintings that depict the thriving city of Kyoto designated as a nationally important cultural property in Japan. Gold-colored areas painted by using high granularity colorants compared with other color areas are evaluated based on the image quality metamerism index locally, then the index is visualized as a map showing the possibility of the image quality metamer to the reference pixel set in the same image. This visualization means a segmentation of areas where color is similar but texture is different. The experimental result showed that the proposed method was effective to show areas of gold color areas in the property.
    Journal of Electronic Imaging 01/2013; · 1.06 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose using earth mover’s distance (EMD) to obtain the appropriate similarity between each histogram for segmentation of abnormal liver regions with mapping of the distances by multidimensional scaling. Conventionally, the similarity between each histogram is calculated by integrating the difference between each bin of the histograms. However, this similarity is unsuitable for appropriate comparison of the histograms because the number of bins for calculating the local histograms of computed tomography images varies. We used EMD to resolve this problem regarding the difference in bin numbers, and the obtained distances are used for mapping the local histograms by multidimensional scaling to low-dimensional space. In the low-dimensional space, the abnormal liver region was well segmented by support vector machine in the test datasets.
    Artificial Life and Robotics 01/2013;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Since metabolic syndrome is a cause of lifestyle-related diseases, and its early diagnosis and an evaluation of visceral fat are important, this study proposes a new method of estimating the amount of fat. The goal of this study is to estimate visceral fat from estimation of subcutaneous fat and total fat. The subcutaneous fat is estimated from the elasticity of the lumbar area, and the total fat is estimated from body information such as the abdominal vertical and lateral width, and body weight. Finally, the estimated subcutaneous fat is subtracted from the estimated total fat to calculate the visceral fat. Measurement tests conducted to verify the constructed visceral fat estimation model showed good results, with a correlation of 0.96 between the visceral fat area estimated by the proposed method and the actual measured area. The reproducibility of the estimation model was also verified by the cross validation method.
    Artificial Life and Robotics 01/2013;
  • [Show abstract] [Hide abstract]
    ABSTRACT: We measured the oxygen saturation of skin at various ages by iterating our previously proposed method that can rapidly simulate skin spectral reflectance with high accuracy. Oxygen saturation is commonly measured by a pulse oximeter to evaluate oxygen delivery for monitoring the functions of heart and lungs at a specific time. On the other hand, oxygen saturation of skin is expected to assess peripheral conditions. Our previously proposed method, the optical path-length matrix method (OPLM), is based on a Monte Carlo model of steady-state light transport in multi-layered tissue (MCML), but can simulate skin spectral reflectance 27,000 times faster than MCML. In this study, we implemented an iterative OPLM with a nonlinear optimization technique such that this method can also be used for estimating hemoglobin concentration and oxygen saturation from the measured skin spectral reflectance. The iterative OPLM was over 25,000 times faster than the MCML with 95 % accuracy. Before measurements in clinic, stability of oxygen saturation among measuring pressure was confirmed. Then, the skin reflectance spectra of 72 outpatients aged between 20 and 86 years were measured by a spectrophotometer. Three points were measured for each subject: the forearm, the thenar eminence, and the intermediate phalanx. The result showed that the oxygen saturation of skin remained constant at each point as the age varied.
    Artificial Life and Robotics 01/2013; 18.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this article, we propose a new method—the optical path-length matrix method (OPLM)—as a faster alternative to the Monte Carlo for multi-layered media (MCML), which is often used to simulate the skin spectrum. Theoretically, peripheral oxygen saturation can be estimated by iterating MCML, but it is not a realistic strategy because it requires huge computation time. The optical path-length matrix is obtained as the probabilistic density histograms of the optical path length in skin using MCML, and once the matrix is obtained, skin spectral reflectance can be calculated by accumulating all combinations of elements in the matrix and by setting an absorption coefficient based on the Beer-Lambert law. The computational time of OPLM was approximately 26,000 times faster than that of MCML.
    Optical Review. 11/2012; 19(6):361-365.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Conventional 3-dimensional color spaces such as L*a*b* or L*C*h have a limitation in that colors of materials can only be separated on the same hyperplane. Therefore, it would be useful to find appropriate axes for dental color analysis by analyzing spectral data itself, rather than conventional 3-dimensional color spaces. Hyperspectral data are detailed color spectra with narrow spectral bands over a continuous spectral range. We acquired hyperspectral data of the shade guides without specular reflection, and standardized them as reflectance data. Then, reflectance data were weighed by luminous efficiency function, and used in principal component analysis (PCA). Principal components (PCs) and their contribution, and values of respective shades to respective PCs were calculated as PC scores. Cumulate contribution rate of 1st to 3rd PCs were approximately 100%, which meant shade colors were very similar to each other. Respective PCs showed specific figures, and values of shades showed sequences unique to each PC, which were independent of each other; values to the 1st PC showed gradual changes with change in shade numbering, values to the 2nd PC showed relatively high scores on opaque shades, values to the 4th PC showed lower scores on B and C group shades, and values to the 6th PC showed differences between manufacturers. Using PCA, we could find axes independent of the conventional 3-dimensional color spaces. These axes reflected certain changes which are not detected on conventional color spaces. Our methods are taking into account color matching under any illumination by focusing on the spectra themselves, and we can discuss about components of the teeth from spectra of resulting principal components. By applying our method to conventional systems, it would help diagnose color differences of dental materials.
    Dental materials: official publication of the Academy of Dental Materials 04/2012; 28(7):736-42. · 2.88 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We measured the oxygen saturation of skin at various ages using our previously proposed method that can rapidly simulate skin spectral reflectance with high accuracy. Oxygen saturation is commonly measured by a pulse oximeter to evaluate oxygen delivery for monitoring the functions of heart and lungs at a specific time. On the other hand, oxygen saturation of skin is expected to assess peripheral conditions. Our previously proposed method, the optical path-length matrix method (OPLM), is based on a Monte Carlo for multi-layered media (MCML), but can simulate skin spectral reflectance 27,000 times faster than MCML. In this study, we implemented an iterative simulation of OPLM with a nonlinear optimization technique such that this method can also be used for estimating hemoglobin concentration and oxygen saturation from the measured skin spectral reflectance. In the experiments, the skin reflectance spectra of 72 outpatients aged between 20 and 86 years were measured by a spectrophotometer. Three points were measured for each subject: the forearm, the thenar eminence, and the intermediate phalanx. The result showed that the oxygen saturation of skin remained constant at each point as the age varied.
    Proc SPIE 02/2012;
  • [Show abstract] [Hide abstract]
    ABSTRACT: — In this paper, the relative influences of misalignment such as cross-talk, vertical shift, and motion blur on visual fatigue by using a binocular stereoscopic display has been verified. Experiments were conducted for two cases: a still image and a motion image. They were evaluated by using the simulator sickness questionnaire (SSQ). By changing the disparity angle, cross-talk, and vertical shift in the still-image experiment, it was found that the SSQ score of each parameter increased as the amount of each factor increased. With a two-sample t-test between the presence and absence of each factor, a significant difference was found for the case of a more than 36-arcmin disparity, more than 20% cross-talk, and more than 10% vertical shift. In the motion-image experiment, in which motion speed and the misalignment were varied, it was found that movement of the disparity angle caused much more visual fatigue in comparison with the misalignment factors, which were cross-talk and vertical shift. In contrast, motion images in addition to the cross-talk and/or vertical shift had a slight but unnoticeable relationship to an increase in visual fatigue. Therefore, it was concluded that vertical shift dominated the evaluation for still images, and the movement itself dominated the evaluation for motion images. The results suggest that it is necessary to evaluate visual fatigue according to the representing case, still or motion images, of a 3-D stereoscopic display.
    Journal of the Society for Information Display. 02/2012; 20(2).
  • [Show abstract] [Hide abstract]
    ABSTRACT: In Kampo medicine (Japanese traditional herbal medicine), the appearance of the tongue contains a lot of useful information for diagnosis. However, an inspection of the tongue is not considered to be important in modern medical diagnosis, since the skills applied in the examination are difficult to understand. Thus, we developed an imaging system and algorithm for quantitative analysis of the tongue to provide the traditional techniques of Kampo with greater objectivity. Tongue images were taken from 9 healthy subjects for 3 consecutive weeks (5 days/week), 12 times a day, with 300 images taken successively within 30 s each time. Then, the temporal color changes in 30 s, 1 day, and 3 weeks were measured in the device-independent International Commission on Illumination (CIE) 1976 L*a*b* color space. The tongue color change in 30 s varied between individuals, and it was mainly classified into 3 patterns. This image acquisition system and valid color management should help all tongue-related research, and the 30-s temporal color change might be an important target for further tongue analysis. We were able to acquire tongue images without specular reflection and with valid color reproduction, and the color change in 30 s was found to vary. Tongue color changes have not been mentioned in the classics of Kampo medicine, since they were certainly impossible to discriminate by the naked eye. The change during 30 s is a new finding based on the electronic devices, and together they are expected to become a new criterion for tongue analysis.
    Forschende Komplementärmedizin / Research in Complementary Medicine 01/2012; 19(2):80-5. · 1.65 Impact Factor
  • Kimiyoshi Miyata, Norimichi Tsumura
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we introduce a concept of the image quality metamerism as an expanded version of the metamerism defined in the color science. The concept is used to unify different image quality attributes, and applied to introduce a metric showing the degree of image quality metamerism to analyze a cultural property. Our global goal is to build a metric to evaluate total quality of images acquired by different imaging systems and observed under different viewing conditions. As the basic step to the global goal, the metric is consisted of color, spectral and texture information in this research, and applied to detect image quality metamers to investigate the cultural property. The property investigated is the oldest extant version of folding screen paintings that depict the thriving city of Kyoto designated as a nationally important cultural property in Japan. Gold colored areas painted by using high granularity colorants compared with other color areas in the property are evaluated based on the metric, then the metric is visualized as a map showing the possibility of the image quality metamer to the reference pixel.
    Proc SPIE 01/2012;
  • Osama Ouda, Norimichi Tsumura, Toshiya Nakaguchi
    [Show abstract] [Hide abstract]
    ABSTRACT: Improving the security of biometric template protection techniques is a key prerequisite for the widespread deployment of biometric technologies. BioEncoding is a recently proposed template protection scheme, based on the concept of cancelable biometrics, for protecting biometric templates represented as binary strings such as iris codes. The main advantage of BioEncoding over other template protection schemes is that it does not require user-specific keys and/or tokens during verification. Besides, it satisfies all the requirements of the cancelable biometrics construct without deteriorating the matching accuracy. However, although it has been shown that BioEncoding is secure enough against simple brute-force search attacks, the security of BioEncoded templates against more smart attacks, such as record multiplicity attacks, has not been sufficiently investigated. In this paper, a rigorous security analysis of BioEncoding is presented. Firstly, resistance of BioEncoded templates against brute-force attacks is revisited thoroughly. Secondly, we show that although the cancelable transformation employed in BioEncoding might be non-invertible for a single protected template, the original iris code could be inverted by correlating several templates used in different applications but created from the same iris. Accordingly, we propose an important modification to the BioEncoding transformation process in order to hinder attackers from exploiting this type of attacks. The effectiveness of adopting the suggested modification is validated and its impact on the matching accuracy is investigated empirically using CASIA-IrisV3-Interval dataset. Experimental results confirm the efficacy of the proposed approach and show that it preserves the matching accuracy of the unprotected iris recognition system.
    Proc SPIE 05/2011;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Kampo medicine (Japanese traditional herbal medicine) contains concepts useful for preventive medicine. For example, "Mibyou" (disease-oriented state) aims to prevent illness by early recognition. Kampo diagnosis is based on subjective examinations, such as tongue inspection, by trained specialist physicians. An objective metric of the tongue color spectrum was developed as a surrogate for subjective visual inspection. Tongue images were acquired with a hyperspectral imaging system, and the uncoated tongue region was segmented automatically. The spectral information of the uncoated tongue area was analyzed by principal component analysis (PCA). The component vector most representative of each clinical symptom was found by rotating the vector on a plane spanned by two arbitrary principal component vectors. The system was tested in human volunteers. Forty-four hyperspectral images were acquired from 30 healthy male subjects for initial testing. The Oketsu (blood stagnation) score was determined by an experienced clinician in Kampo medicine from 27 of 30 subjects. The correlation between respective principal components and Oketsu score was 0.67 at maximum, and increased to 0.73 by linear combination, while it was -0.75 by vector rotation. Significant correlations for many disorders were demonstrated, and vector rotation showed better correlation than linear combination. A PCA-based algorithm was developed to objectively evaluate patients using color images of the tongue surface. Testing showed that this method was a feasible surrogate for expert visual tongue analysis. This tool should help non-trained people identify "Mibyou" health status for individuals. The algorithm is free of empirical criteria, and it may be it applicable to many hyperspectral image types.
    International Journal of Computer Assisted Radiology and Surgery 03/2011; 6(2):209-15. · 1.36 Impact Factor
  • Ahmed Afifi, Toshiya Nakaguchi, Norimichi Tsumura
    [Show abstract] [Hide abstract]
    ABSTRACT: In this work, we propose a shape-based liver segmentation approach using a patient specific knowledge. In which, we exploit the relation between consequent slices in multi-slice CT images to update the shape template that initially determined by the user. Then, the updated shape template is integrated with the graph cuts algorithm to segment the liver in each CT slice. The statistical parameters of the liver and non-liver tissues are initially determined according to the initial shape template and it is consequently updated from the nearby slices. The proposed approach does not require any prior training and it uses a single phase CT images; however, it is talented to deal with complex shape and intensity variations. The proposed approach is evaluated on 20 CT images with different kinds of liver abnormalities, tumors and cysts, and it achieves an average volumetric overlap error of 6.4% and average symmetric surface distance (ASD) of 0.8 compared to the manual segmentation.
    Proc SPIE 03/2011;
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose optical path-length matrix method for high-speed simulation of photon migration in human skin. The optical path-length matrix is defined as the probability density distribution of optical pathlength in the skin. Generally, Monte Carlo simulation is used to simulate a skin reflectance, since it can simulate the reflectance accurately. However, it requires a huge computation time, thus this is not easily applicable in practical imaging system with large number of pixels. On the other hand, the proposed optical path-length matrix method achieves the simulation in shorter time. The skin model was assumed to be two-layered media of the epidermal and dermal layers. For obtaining the path-length matrix, photon migration in the model without any absorption was simulated only once by Monte Carlo simulation for each wavelength, and the probabilistic density histograms of the optical path-length at each layer were acquired and stored in the optical path-length matrix. Skin spectral reflectance for arbitrary absorption can be calculated easily by accumulating all combination of an element in the above pre-recomputed path-length matrix and absorption coefficient based on the Beer-Lambert law. Our proposed method was compared with the conventional Monte Carlo simulation. Computational time of the proposed method was approximately two minutes; while that of the conventional method was 15 hours. In addition, error margin of the proposed method was approximately less than 1.6%. This method would applied to skin spectral image analysis for skin chromophore quantification.
    Proc SPIE 02/2011;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a method for efficient gonio-imaging of optically variable devices (OVDs), which are applied as a counterfeit deterrence for valuable documents. A compound-eye image-capturing system composed by a microlens array, a signal separator, and an image sensor was used to capture directionally distributed light from OVDs after being collimated by a convex lens. Multiple images corresponding to different observation angles were obtained in the individual eyes of the system, simultaneously and independently. A demonstration involving a holographic grating provided 100 gonio images that exhibited sensitive color changes of the diffracted light according to the observation angle.
    Optics Express 02/2011; 19(4):3353-62. · 3.55 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Uneven distribution of skin color is one of the biggest concerns about facial skin appearance. Recently several techniques to analyze skin color have been introduced by separating skin color information into chromophore components, such as melanin and hemoglobin. However, there are not many reports on quantitative analysis of unevenness of skin color by considering type of chromophore, clusters of different sizes and concentration of the each chromophore. We propose a new image analysis and simulation method based on chromophore analysis and spatial frequency analysis. This method is mainly composed of three techniques: independent component analysis (ICA) to extract hemoglobin and melanin chromophores from a single skin color image, an image pyramid technique which decomposes each chromophore into multi-resolution images, which can be used for identifying different sizes of clusters or spatial frequencies, and analysis of the histogram obtained from each multi-resolution image to extract unevenness parameters. As the application of the method, we also introduce an image processing technique to change unevenness of melanin component. As the result, the method showed high capabilities to analyze unevenness of each skin chromophore: 1) Vague unevenness on skin could be discriminated from noticeable pigmentation such as freckles or acne. 2) By analyzing the unevenness parameters obtained from each multi-resolution image for Japanese ladies, agerelated changes were observed in the parameters of middle spatial frequency. 3) An image processing system modulating the parameters was proposed to change unevenness of skin images along the axis of the obtained age-related change in real time.
    Proc SPIE 02/2011;

Publication Stats

627 Citations
45.76 Total Impact Points

Institutions

  • 1995–2013
    • Chiba University
      • • Graduate School of Advanced Integration Science
      • • Graduate School of Medicine
      • • Division of Information Sciences
      • • Graduate School of Science and Technology
      • • Department of Information Processing and Computer Science
      Tiba, Chiba, Japan
  • 2011–2012
    • Keio University
      • Center for Kampo Medicine
      Tokyo, Tokyo-to, Japan
  • 2003
    • Kao Corporation
      Edo, Tōkyō, Japan
  • 1993
    • Osaka University
      • Department of Applied Physics
      Suika, Ōsaka, Japan