This thesis focuses on the problem of increasing flexibility in the acquisition and application of biometric recognition systems based on the ocular region. While the ocular area is one of the oldest and most widely studied biometric regions thanks to its rich and discriminative elements and characteristics, most modalities such as retina, iris, eye movements, or oculomotor plant have limitations regarding data acquisition. Some require a specific type of illumination like the iris, a limited distance range like eye movements, or specific sensors and user collaboration like the retina. In this context, this thesis focuses on the periocular region, which stands out as the ocular modality with the fewest acquisition constraints. 

The first part focuses on using middle-layers' deep representation of pre-trained CNNs as a one-shot learning method, along with simple distance-based metrics and similarity scores for periocular recognition. This approach tackles the issue of limited data availability and collection for biometric recognition systems by eliminating the need to train the models for the target data. Furthermore, it allows seamless transitions between identification and verification scenarios with a single model, and tackles the problem of the open-world setting and training bias of CNNs. We demonstrate that off-the-shelf features from middle-layers can outperform CNNs trained for the target domain that followed a more extensive training strategy when target data is limited.

The second part of the thesis analyzes traditional methods for biometric systems in the context of periocular recognition. Nowadays, these methods are often overlooked in favor of deep learning solutions. However, we show that they can still outperform heavily trained CNNs in closed-world and open-world settings and can be used in conjunction with CNNs to further improve recognition performance. Moreover, we investigate the use of the complex structure tensor as a handcrafted texture extractor at the input of CNNs. We show that CNNs can benefit from this explicit textural information in terms of performance and convergence, offering the potential for network compression and explainability of the features used. We demonstrate that CNNs may not easily access the orientation information present in the images that are exploited in some more traditional approaches.

The final part of the thesis addresses the analysis of periocular recognition under different light spectra and the cross-spectral scenario. More specifically, we analyze the performance of the proposed methods under different light spectra. We also investigate the cross-spectral scenario for one-shot learning with middle-layers' deep representations and explore the possibility of bridging the domain gap in the cross-spectral scenario by training generative networks. This allows using simpler models and algorithms trained on a single spectrum.