A Simple Non-Invasive Automated Heart Rate Monitoring System Using Facial Images

A Simple Non-Invasive Automated Heart Rate Monitoring System Using Facial Images

Humaira Nisar (Universiti Tunku Abdul Rahman, Malaysia), Zhen Yao Lim (Universiti Tunku Abdul Rahman, Malaysia) and Kim Ho Yeap (Universiti Tunku Abdul Rahman, Malaysia)
DOI: 10.4018/978-1-4666-8811-7.ch005
OnDemand PDF Download:
No Current Special Offers


In this chapter we will discuss a simple non invasive automated heart rate monitoring method. Commonly heart rate is measured by using heart rate monitor devices. Many patients do not feel comfortable when they use contact devices for diagnostic purposes. Our algorithm gives a non-invasive way of heart rate measurement. The first step is to record a video. After 5 frames of the video are captured, the face is detected. A total of 300 frames will be used for further processing. At this stage, ROI (part of forehead) will be cropped out automatically. All image frames are in RGB color model, so these will be separated into 3 channels. For analysis, graph normalization is applied, which uses mean and standard deviation. Fast Fourier transform is used to plot the power spectrum of the traces. This power spectrum will have a peak if the heart rate is detected. We used RGB, HSI, YCbCr, YIQ, and CIE LAB color models for analysis. The best result is achieved with RGB color model followed by CIELab. The average accuracy is 95.32%.
Chapter Preview


In recent years, due to development in computer technology and imaging devices, image based, non-invasive measurement techniques have been developed. These methods are very popular as they provide a fast alternative and objective solution to many health related problems for which only a subjective way of treatment is available. These methods use an imaging device along with highly advanced computer algorithms for non-invasive measurement. A typical example is face and facial expression recognition methods, human activity recognition (Aamir Malik, Tae-Sun Choi, Humaira Nisar, 2012), segmentation of dermatological skin lesions like Melanoma and Eczema. Nakajima et al. recorded the images in real time to measure the respiratory rate based on changes in the posture for a subject in bed (Nakajima, K., Matsumoto, Y., & Tamura, T, 2001). Takano et al. used imaging techniques to develop a non-contact measuring method for collecting heart and respiratory rates (Takano, C., & Ohta, Y, 2007).

Heart rate measurement is done by health care providers to measure the physiological state of a human being. Heart rate is a critical parameter to assess the well-being of patients in hospitals and in a home care environment. It is also measured frequently to ensure the general well-being of an individual as a preventive measure. The term heart rate is defined as a measurement of the frequency with which the heart pumps blood. It is measured in the units of beats per minute (bpm). Traditionally, people put their fingers on the wrist to feel the pulse in a period of 1 minute or 30 seconds. With the advancement in technology, heart rate monitoring devices had been introduced. For example, early in patient devices consist of wrist receiver and chest strap transmitter. These devices may cause discomfort as well as skin irritation. Chest strap transmitter calculates the electrocardiogram (ECG) and sends it to wrist receiver. Later improved versions of these devices only used the wrist device to calculate the heart rate. These devices are normally used in sports and also at homes, and can be used without any difficulty. Another commonly used device is pulse oxymeter (J Mix, R Viala, 2010). The sensors of oxymeter are attached to the finger tips or ear lobes. Hence are inconvenient for patients as the clips can cause pain in the respective areas if used for a long period of time.

Existing in patient heart rate measurement techniques include elctrocardiography (ECG) and pulse oximetry based on photoplethysmography (PPG) (Hertzman, A. B., 1938). These techniques are reliable and inexpensive. However there are several disadvantages in the sense that because both are contact devices that use adhesive sensors. Placement and removal of the sensors is a source of discomfort to the patient. It may also cause stress, pain and sometimes epidermal stripping especially in the case of infants in the neonatal care unit. The obstruction caused by the wire impairs bonding between patient and care givers, especially maternal separation has a negative impact on cognitive development of the infants (Anand, K. J. S., & Scalzo, F. M., 2000). Another study by Chen et al. indicates that repetitive application and removal of the patches adversely affects the infants well being and developmental outcome (Chen W et al., 2010)

Complete Chapter List

Search this Book: