We propose a novel convolutional neural network to verify a match between two images of the human iris. The network is trained end-to-end and validated on three publicly available datasets yielding state-of-the-art results against four baseline methods. The network performs better by a 10% margin to the state-of-the-art method on the CASIA.v4 dataset. In the network, we use a novel layer whose output is interpreted as a normalized response in the complex plane. We show that the layer improves the performance of the model up to 15% on previously-unseen data.
IntroductionIris verification is a biometric technique used for human identification. Given a pair of images of human irises, the task is to decide whether the irises match. Iris verification is applied widely, e.g., in border control, citizen authentication, or in forensics [21].Common iris verification pipeline has three steps -iris detection, feature extraction, and matching (see Fig. 2, interested reader is referred, e.g., to [5]). First, an iris is found and normalized. Second, the normalized iris is typically convolved with Gabor filters and converted into a "bitcode", i.e. a matrix of binary numbers. Third, two bitcodes are compared. The bitcodes match if their Hamming distance is smaller than a given threshold.Feature extraction and matching are highly data-dependent in a common iris verification pipeline and therefore require parameter-tuning. Since the task is not convex, an exhaustive search for parameters is performed. In this paper, we propose a method which replaces the feature extraction and matching part of the iris verification pipeline with a single fully convolutional neural network and a single learning rule -the backward propagation of errors or backpropagation. The network is trained end-to-end using the binary cross-entropy loss function. The input of the network is a pair of normalized irises, the output is a single number which is interpreted as a posterior probability of a match (see Fig. 1).So far, convolutional neural networks were used in iris verification for better feature encoding. To encode the features, standard blocks of convolutions, max-pooling, and batch normalization layers were used. We introduce a novel "Complex-response layer" that replaces the feature extraction step in a common iris verification pipeline and is learned optimally by backpropagation.The contributions of this paper are the following: (i) we propose a novel method of iris verification that replaces feature extraction and matching steps of a commonly used iris verification pipeline. We replace it with a single convolutional neural network (IrisMatch-CNN) trained end-to-end that is robust to changes in the iris image acquisition setup, (ii) we introduce a novel "Complex-response layer" whose output is interpreted as a normalized filter response in the complex plane, (iii) we evaluate the method on three public datasets against four methods achieving state-of-the-art results. * Work performed during an internship at Microsoft Development Center Serbia d.o.o.