No abstract

During the video and fixed image acquisition procedure of an automatic iris recognition system, it is essential to acquire focused iris images. If defocus iris images are acquired, the performance of the iris recognition is degraded, because iris images don't have enough feature information. Therefore it's important to adopt the image quality evaluation method before the image processing. In this paper, it is analyzed and compared four representative quality assessment methods on the MBGC iris database. Through methods, it can fast grade the images and pick out the high quality iris images from the video sequence captured by real-time iris recognition camera. The experimental results of the four methods according to the receiver operating characteristic (ROC) curve are shown. Then the optimal method of quality evaluation that allows better performance in an automatic iris recognition system is founded. This paper also presents an analysis in terms of computation speed of the four methods.

No abstract

To date, research on the iris recognition systems are focused on the optimization and proposals of new stages for uncontrolled environment systems to improve the recognition rate levels. In this paper we propose to exploit the biometric information from video-iris, creating a fusioned normalized template through an image fusion technique. Indeed, this method merges the biometric features of a group of video images getting an enhanced image which therefore improves the recognition rates iris, in terms of Hamming distance, in an uncontrolled environment system. We analyzed seven different methods based on pixel-level and multi-resolution fusion techniques on a subset of images from the MBGC.v2 database. The experimental results show that the PCA method presents the best performance to improve recognition values according to the Hamming distances in 83% of the experiments.

Background Alzheimer's Disease (AD) diagnosis at early stages currently represents an important challenge for the scientific community, which is gradually accentuated due to the global perspective of population aging. Current clinical processes for the diagnosis of this disease are increasingly effective; these include invasive tests of nervous system biomarkers, which are complemented by non‐invasive tests of human cognitive and functional performance, such as the mini‐mental state examination and the analysis of Instrumental Activities of Daily Living (IADLs). Method The present work is centered around the development of technological tools for creating an automated model to support the diagnosis of early AD disease. We present a novel non‐invasive methodology for the development of an Artificial Intelligence‐based model, which analyzes human biomechanical markers of IADLs activities to recognize human functional patterns. For the development of this model, we have built a dataset of egocentric videos containing IADLs activities, organized in four classes, based on the prehensile patterns of the hands: strength and precision, and on the kinematics of the instruments: displacement and manipulation. We have characterized the dataset using mathematical methods to get information to directly emulate the relationship with Lawton and Brody's geriatric test, which is used in clinical protocols to estimate human functional capacity. This characterization relationship between biomechanical markers and human functional patterns represents a benefit for quantitative and objective assessment in support of geriatric evaluation and patient follow‐up. Result Our proposed model results in an accuracy of 73.74% in the recognition of human functional patterns related to the kinematics of the instruments, 59.84% in the analysis of the prehensile pattern of the hands, and 48.5% when the classes were recognized independently. Conclusion This allows us to establish in a quantifiable way performance region benchmarks of human functional capacity for IADLs activities, by obtaining a support model in the diagnostic evaluation of AD disease at early stages. Our proposed model allows us to establish the guideline to improve the automatic recognition of human functional patterns, of which we obtained an acceptable percentage testing instruments kinematics', followed by the hands' prehensile patterns.