2results about How to "Improve the correct recognition rate" patented technology

The application provides a kind of based on the abnormal state alarm monitoring method of lonely old people of intelligent monitoring terminal, it is related to the safety monitoring technical field of old people, including the following steps: current monitoring time period is divided into at least one time section according to the intensity level of movement, and based on each type of vital signs in each time section, determine its abnormal frequency and decoupling index;Based on the attention weight of each vital sign of abnormal frequency and decoupling index, update the attention layer parameter after, then each type of vital signs in current monitoring time period is input into abnormal state recognition model, identify whether the lonely old people exist abnormity, the application is based on the intensity of movement adaptive analysis the abnormal frequency and decoupling index of each vital sign of lonely old people, to adjust the attention layer parameter of abnormal state recognition model, so that abnormal state recognition model will more attention on the vital sign of high abnormal degree, significantly improve the correct recognition rate of the abnormal state of lonely old people.

The present invention discloses an iris recognition method based on wavelet packet decomposition. First, human eye images are collected and iris images are preprocessed to obtain processed iris images. Second, diagonal high-frequency information of iris image wavelet packet decomposition is modulated into iris feature codes by using thresholds, and iris features are extracted. Finally, a Hamming distance classifier is used to classify and match iris features. The method determines whether the two feature codes are from the same iris by calculating the similarity between the current iris feature code and the iris code in the iris template library, thereby classifying the iris image. The iris features extracted by the recognition method of the present invention have good classification performance, thereby improving the accuracy of iris recognition.