Enhancement method for ultraviolet fluorescence image of skin disease

Abstract

The invention discloses an enhancement method for ultraviolet fluorescence images of skin diseases. The method comprises the following steps: dividing an original fluorescence image into a low-frequency image and a high-frequency image by utilizing wavelet decomposition; processing the low-frequency image by adopting a pixel pair gray stretching algorithm, wherein the number of pixel pairs needing to be counted is greatly reduced at the moment; processing the high-frequency image by using a de-noising method based on weighted TV regularization; and reconstructing a low-frequency enhanced signal and a high-frequency de-noised signal through wavelet inverse transformation. According to the algorithm provided by the invention, the advantages of an enhancement algorithm and a de-noising algorithm are combined to the maximum extent, the singularity of a fluorescence image is reserved, the definition and contrast ratio of the fluorescence image are improved, noise is remarkably weakened, detail information of the fluorescence image is displayed, the excessive enhancement phenomenon does not occur, and the visual effect is good.

Description

technical field [0001] The invention relates to the technical field of fluorescence image processing, in particular to an ultraviolet fluorescence image enhancement algorithm for skin diseases based on pixel-to-gray stretching and weighted TV regularization. Background technique [0002] After the skin is irradiated with ultraviolet light of a specific wavelength, the melanin and dermal collagen in it will absorb the ultraviolet light; then, blue light is emitted as the main color of fluorescence, and different skin lesions can produce fluorescence of different degrees and colors, thus reflecting different degrees and Kinds of skin diseases. This principle can be used to assist doctors to make accurate diagnosis of skin diseases such as pigment abnormalities and skin infections. [0003] Fluorescence radiated from the skin can be imaged under the irradiation of ultraviolet light through ultraviolet fluorescence imaging technology. However, since the fluorescence signal is a...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a fluorescent image enhancement algorithm based on pixel-to-gray stretching and weighted TV regularization, to effectively solve the problems of dark fluorescence images in the background technology, low contrast, loss of details, etc., and improve skin diseases. Excellent diagnostic accuracy and efficiency, to achieve early detection and early treatment of pigmented and infectious skin diseases

Images