Abstract: A hyperspectral characteristic band selection method and an active hyperspectral imaging device using the same. The method using a virtual dimension algorithm to calculate a number of endmembers of a hyperspectral image of a predetermined disease, and using between 1 time and 2 times the number of endmembers as a number of predetermined selected bands, and then selecting characteristic bands with a number matching the number of selected bands from a plurality of spectral bands in the image. The device comprises a base, light sources and a sensing portion, the light sources are respectively disposed on the base, bands emitted by the light sources are configured according to the characteristic bands calculated by the method. The sensing portion is disposed on the base and spaced apart from the light sources for receiving reflected light from an external target object irradiated by the light sources to obtain a hyperspectral image.

Abstract: The present invention disclosed an iterative analyzing method, which can detect the lesion in the image quickly. In brief, the iterative analysis method of the medical image disclosed by the present invention is roughly as follows: first, the original spectral image cube is expanded into a spectral image cube by a method of nonlinear dimensional-expansion, and then detecting the target's subpixel by the method of constrained energy minimization to produce an abundance image; the abundance image is fed back to the spectral image cube for create another spectral image cube by the nonlinear method. Furthermore, the abundance image is only used for detecting the subpixel of the target and does not include any spatial information, so, in order to obtain the spatial information of spectral image, it obtains the spatial information around the subpixel by using a blurring tool such as a Gaussian filter.

Abstract: The present invention disclosed an iterative analyzing method, which can detect the lesion in the image quickly. In brief, the iterative analysis method of the medical image disclosed by the present invention is roughly as follows: first, the original spectral image cube is expanded into a spectral image cube by a method of nonlinear dimensional-expansion, and then detecting the target's subpixel by the method of constrained energy minimization to produce an abundance image; the abundance image is fed back to the spectral image cube for create another spectral image cube by the nonlinear method. Furthermore, the abundance image is only used for detecting the subpixel of the target and does not include any spatial information, so, in order to obtain the spatial information of spectral image, it obtains the spatial information around the subpixel by using a blurring tool such as a Gaussian filter.