Iris segmentation algorithms are a key part of full-fledged iris recognition systems and have a direct effect on the results of iris verification and recognition. But when standard iris segmentation algorithms are used on noisy iris databases that were recorded in unrestricted environments, they are not flexible enough and are not strong enough. Also, there aren't any big iris databases right now, so iris segmentation methods can't take full advantage of the benefits of convolution neural

more »

... ks (CNNs). The problem of iris segmentation in handheld devices is then solved by making a deep learning scheme and coming up with a good way to improve it. Initial comparisons with iris segmentation algorithms that are available to the public show significant performance gains, especially on difficult image datasets that are meant to simulate the quality of images from a handheld device.