As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
In the expression recognition with multi-classifier fusion, fuzzy integral is a more commonly used fusion method. The key to applying fuzzy integral is how to determine the fuzzy density. At present, the methods of determining the fuzzy density are mainly by constructing the confusion matrix by using the prior knowledge of the training samples, without taking into account the dynamic information contained in each classifier when identifying specific target. Aiming at this problem, after obtaining the fuzzy density of each classifier by using the confusion matrix, this paper adjusts it by measuring the consistency of the recognition results of the testing object. The experimental results show that the method can obtain better fusion effect than traditional fuzzy density assignment method when used in facial expression recognition, and improve the accuracy of expression recognition.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.