The invention provides a method and
system for assisting in recognizing submucosal blood vessels under an
endoscope, and belongs to the technical field of
blood vessel recognition. The method comprises the steps that a
time sequence image, collected in real time, of a to-be-detected part is preprocessed, and the pixel value of the
time sequence image is converted into a
zero mean value and a unit variance; based on the imaging type photoplethysmography technology,
blood volume waves are extracted from the preprocessed
time sequence images, and the corresponding
blood volume fluctuation frequency is determined; based on an imaging type photoplethysmography technology, a pixel change value of each pixel point is extracted from the preprocessed time sequence image, and a pixel fluctuation frequency of the corresponding pixel point is determined; and according to the
blood volume wave, the blood volume fluctuation frequency, the pixel change value and the pixel fluctuation frequency, the submucosal
blood vessel coverage area is determined. According to the method, in the operation process of the
endoscope, on the premise that no extra equipment is used and the
operation time is not prolonged, alimentary canal
blood flow information can be accurately extracted in real time, submucosal blood vessels can be accurately recognized, and
operation safety is guaranteed.