an inertial-measurement unit, configured to detect a pitch angle of the portable electronic device;

a camera device, configured to obtain an input image;

a storage device, configured to store an operating system, a wound-measuring program, a CNN (convolutional neural network) model, and an RPN (regional proposal network) model; and

a processor, configured to execute the wound-size measuring program to perform the following steps:

using the CNN model to recognize the input image, and to select a part of the input image with the highest probability of containing a wound as an output wound image; and

calculating an actual height and an actual width of the output wound image according to a lens-focal-length parameter reported by the operating system, a plurality of reference calibration parameters corresponding to the pitch angle, and a pixel-height ratio and a pixel-width ratio of the output wound image;

wherein the processor further performs a machine-learning clustering algorithm to divide the output wound image into a wound region and a normal-skin region,

wherein the processor further calculates a first pixel number in the output wound image and a second pixel number in the wound region, and divides the second pixel number by the first pixel number to obtain a wound-region pixel ratio,

wherein the processor further multiplies the actual height of the output wound image by the actual width of the output wound image to obtain an actual area of the output wound image, and multiplies the actual area by the wound-region pixel ratio to obtain an actual area of the wound region.