Background: The paper presents an automatic method for analysis and processing of\nimages from a camera operating in visible light. This analysis applies to images containing\nthe human facial area (body) and enables to measure the blood pulse rate. Special\nattention was paid to the limitations of this measurement method taking into account\nthe possibility of using consumer cameras in real conditions (different types of lighting,\ndifferent camera resolution, camera movement).\nMethods: The proposed new method of image analysis and processing was associated\nwith three stages: (1) image pre-processingââ?¬â?allowing for the image filtration\nand stabilization (object location tracking); (2) main image processingââ?¬â?allowing for\nsegmentation of human skin areas, acquisition of brightness changes; (3) signal analysisââ?¬â?\nfiltration, FFT (Fast Fourier Transformation) analysis, pulse calculation.\nResults and conclusions: The presented algorithm and method for measuring the\npulse rate has the following advantages: (1) it allows for non-contact and non-invasive\nmeasurement; (2) it can be carried out using almost any camera, including webcams;\n(3) it enables to track the object on the stage, which allows for the measurement of the\nheart rate when the patient is moving; (4) for a minimum of 40,000 pixels, it provides\na measurement error of less than Ã?±2 beats per minute for p < 0.01 and sunlight, or a\nslightly larger error (Ã?±3 beats per minute) for artificial lighting; (5) analysis of a single\nimage takes about 40 ms in Matlab Version 7.11.0.584 (R2010b) with Image Processing\nToolbox Version 7.1 (R2010b).
Loading....