Showing papers by "Nagaaki Ohyama published in 2007"

Maximum a posteriori estimation of spectral reflectance from color image and multipoint spectral measurements

Abstract: Accurate color image reproduction under arbitrary illumination can be realized if the spectral reflectance functions in a scene are obtained. Although multispectral imaging is one of the promising methods to obtain the reflectance of a scene, it is expected to reduce the number of color channels without significant loss of accuracy. This paper presents what we believe to be a new method for estimating spectral reflectance functions from color image and multipoint spectral measurements based on maximum a posteriori (MAP) estimation. Multipoint spectral measurements are utilized as auxiliary information to improve the accuracy of spectral reflectance estimated from image data. Through simulations, it is confirmed that the proposed method improves the estimation accuracy, particularly when a scene includes subjects that belong to various categories.

Digital staining of pathological images: dye amount correction for improved classification performance

Abstract: Physical staining is indispensable in pathology. While physical staining uses chemicals, "digital staining" exploits the differing spectral characteristics of the different tissue components to simulate the effect of physical staining. Digital staining for pathological images involves two basic processes: classification of tissue components and digital colorization whereby the classified tissue components are impressed with colors associated to their reaction to specific dyes. Spectral features, i.e. spectral transmittance, of the different tissue structures are dependent on the staining condition of the tissue slide. Thus, if the staining condition of the test image is different, classification result is affected, and the resulting digitally-stained image may not reflect the desired result. This paper shows that it is possible to obtain robust classification results by correcting the dye amount of each test-image pixel using Beer Lambert's Law. Also the effectiveness of such technique to be incorporated to the current digital staining scheme is investigated as well.