Unsteady State Lightweight Iris Certification Based on Multi-Algorithm Parallel Integration

Abstract

Aimed at the one-to-one certification problem of unsteady state iris at different shooting times, a multi-algorithm parallel integration general model structure is proposed in this paper. The iris in the lightweight constrained state affected by defocusing, deflection, and illumination is taken as the research object, the existing algorithms are combined into the model structure effectively, and a one-to-one certification algorithm for lightweight constrained state unsteady iris was designed based on multi-algorithm integration and maximum trusted decision. In this algorithm, a sufficient number of iris internal feature points from the unstable state texture were extracted as effective iris information through the image processing layer composed of various filtering processing algorithms, thereby eliminating defocused interference. In the feature recognition layer, iris deflection interference was excluded by the improved methods of Gabor and Hamming and Haar and BP for the stable features extracted by the image processing layer, and two certification results were obtained by means of parallel recognition. The correct number of certifications for an algorithm under a certain lighting condition were counted. The method with the most correct number was set as the maximum trusted method under this lighting condition, and the results of the maximum trusted method were taken as the final decision, thereby eliminating the effect of illumination. Experiments using the JLU and CASIA iris libraries under the prerequisites in this paper show that the correct recognition rate of the algorithm can reach a high level of 98% or more, indicating that the algorithm can effectively improve the accuracy of the one-to-one certification of lightweight constrained state unsteady iris. Compared with the latest architecture algorithms, such as CNN and deep learning, the proposed algorithm is more suitable for the prerequisites presented in this paper, which has good environmental inclusiveness and can better improve existing traditional algorithms’ effectiveness through the design of a parallel integration model structure.

Tribology of Pore-Textured Hard Surfaces under Physiological Conditions: Effects of Texture Scales

“…In other words, the pore textures artificially render the discontinuity of the constitution of a liquid film at the interface, causing the unstable interfacial contact (i.e., solid–solid contact with a heterogeneous interface caused by the pore textures) for the boundary lubrication regime, giving rise to high COF values. Previously, several works ,− also showed that microtexturing could delay the transition of the lubrication regimes (e.g., with the extension of the boundary lubrication regime) due to the discontinuity of the liquid at the heterogeneous interface caused by the textures, leading to an increase in the COF value under the boundary and mixed lubrication regimes. The present results suggest such effects are still valid even with nanotexturing.…”

Heterogeneous Iris One-to-One Certification with Universal Sensors Based On Quality Fuzzy Inference and Multi-Feature Fusion Lightweight Neural Network

“…Multialgorithm parallel integration: An unsteady state multialgorithm parallel integration decision recognition algorithm in [18]; 6.…”

“…The existing framework is improved and tested through the public iris set, which proves that the framework is feasible, such as iris specific Mask R-CNN [12] and deep learning frameworks such as capsule neural networks under lightweight data structures [13], as well as existing deep learning frameworks specifically for iris recognition, such as DeepIris [14] and DeepIrisNet [15]. In research on the multi-state iris, the unsteady-state features are transformed into steady-state features through image processing and other methods [16], and the iris features are expressed through multiple recognition methods and weighted fusion [17] or the final result is obtained based on a credibility decision [18].…”

Multi-Source Feature Fusion and Entropy Feature Lightweight Neural Network for Constrained Multi-State Heterogeneous Iris Recognition

“…As a result, additional studies have begun to focus attention on the overall relationship and design for the framework, such as iris-specific Mask R-CNN [9], to modify the exist-ing framework, integrate the positioning into the iris recognition process, and publicly test the iris set to prove the feasibility of the framework. In research on the unsteadystate iris, the unsteady-state features are transformed into steady-state features through image processing and other methods [10], and the iris features are expressed through multiple recognition methods and weighted fusion [11] or the final result is obtained based on a credibility decision [12]. For setting of iris concept labels, research on biomimetic cognition [13] is an important direction, i.e., determination of how to first summarize a feasible recognition model in the case of a small number of initial training samples, and with increases in the number of recognitions and available training samples, how to further effectively judge whether the current structure cannot meet the existing situation and requires users to retrain [14].…”