Old people nursing demand identification method based on SURF algorithm

Abstract

The invention discloses an elderly nursing demand identification method based on an SURF algorithm. The method comprises the following steps: acquiring facial expression images of old people, and generating a training set and a test set; performing feature extraction on the training set by using an SURF feature extraction algorithm, and determining an expression type; clustering the feature vectors extracted from all the images of the training set by adopting a bag-of-words model in combination with a K-means clustering algorithm, taking each clustering center as a visual word, and collecting the visual words corresponding to all the clustering centers to form a codebook; mapping the SURF feature vectors of the same image to a codebook to generate Bow vectors; putting a codebook formed by visual word sequences generated by clustering all feature vectors of the training set into an SVM (Support Vector Machine) for training; sURF features of test images in a test set are extracted and mapped into Bow vectors to serve as test data, and a classification result is obtained through an SVM algorithm. According to the invention, the real-time performance and accuracy of old people nursing demand identification are improved.

Description

technical field [0001] The invention relates to the technical field of machine vision and image recognition, in particular to a method for identifying nursing needs of the elderly based on SURF algorithm. Background technique [0002] As the problem of population aging increases, the care of the elderly has become an important issue. The degeneration of the elderly's body and the prevalence of cardiovascular diseases in recent years have aggravated the inconvenience of the elderly's expression and movement, resulting in some elderly people who can only stay in bed for a long time and cannot express clearly. In the case of shortage of nursing resources, when there is a physiological need to go to the toilet, incontinence is often caused by untimely assistance, which is very cumbersome and harmful to the elderly. Therefore, it is very important to effectively identify the nursing needs of the elderly through machine facial recognition when the elderly have the need to go to t...

AI Technical Summary

Problems solved by technology

However, this method requires human intervention and requires the elderly to make specified actions, which is difficult for some elderly people who have difficulty understanding the specified requirements.

Images