Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.
XIAOQIAN ZHANG1,* , HANSHAN LI1, JUNCHAI GAO1
In order to improve target tracking stability and target recognition rate, this paper proposes a multi-feature fusion recognition algorithm based on BP neural network and D-S evidence theory, extracts the target features by RGB color weighted histogram and Sobel edge weighted histogram, establishes the decision rule model by combing BP neural network and D-S evidence theory, utilizes the BP neural network to evaluate the reliability of evidence source, according to the characteristic of reliability evaluation, obtains the target multi-feature information fusion decision and recognition of the target by the D-S combination rule. Through experimental comparison, the results show that the target recognition rate is about 95.5% and the misjudgement rate is about 4.5% by using multi-feature information fusion decision under the same conditions, in addition, the recognition results validate that the proposed image multi-feature information fusion decision method can improve effectively the target recognition rate..
Information fusion, BP neural network, D-S evidence theory, Multi-feature fusion decision.
XIAOQIAN ZHANG, HANSHAN LI, JUNCHAI GAO, Research on target recognition method based on multi-feature information fusion decision, Optoelectronics and Advanced Materials - Rapid Communications, 12, 11-12, November-December 2018, pp.634-643 (2018).
Submitted at: July 19, 2018
Accepted at: Nov. 29, 2018
Optoelectronics and Advanced Materials - Rapid Communications
(2022): 0.5 - 2022 Journal Citation Reports (Clarivate Analytics, 2023)
Active accounts were imported to the new platform and assigned a random password by default. In order to access your account you need to access the login page and go through the Lost Password dialog (involves the system sending you an email with instructions) in order to reset your password. This step is necessary as passwords are kept in hashed form and the new platform uses modern hashing algorithms incompatible with the previous ones.