Unsupervised Pre-trained, Texture Aware And Lightweight Model for Deep Learning-Based Iris Recognition Under Limited Annotated Data
This work addresses the problem of iris recognition for biometric systems in scenarios with scarce annotated data, offering a lightweight and efficient solution.
The paper tackled iris recognition with limited labeled data by proposing an unsupervised pre-training stage and texture-aware architectural modifications, resulting in a model with up to 100x fewer parameters that achieved better recognition performance in within and cross-dataset evaluations.
In this paper, we present a texture aware lightweight deep learning framework for iris recognition. Our contributions are primarily three fold. Firstly, to address the dearth of labelled iris data, we propose a reconstruction loss guided unsupervised pre-training stage followed by supervised refinement. This drives the network weights to focus on discriminative iris texture patterns. Next, we propose several texture aware improvisations inside a Convolution Neural Net to better leverage iris textures. Finally, we show that our systematic training and architectural choices enable us to design an efficient framework with upto 100X fewer parameters than contemporary deep learning baselines yet achieve better recognition performance for within and cross dataset evaluations.