Non-Contact Heart Rate Signal Extraction and Identification Based on Speckle Image

Abstract

The biometric technology of heart signal has always been an important research direction of identity recognition. In this paper, we propose a method for heart rate signal extraction and identification based on speckle images. It contains two parts: contactless heart rate signal acquisition and identification. Irradiate the human body with laser to get speckle images, and obtain the heart rate signal by image correlation and filtering. Next, build a dataset with signals and the convolutional neural network model is used to realize the identification. The experimental results show that, the speckle image correlation method can achieve heart rate signal extraction in places where the pulse vibration is weak. In addition, compared with k- Nearest Neighbor and random forest, the convolutional neural model is more accurate in identification. The model achieved an accuracy of 87.33 % on the dataset, which confirms that it is effective for identification based on non-contact heart rate signal.