A Comparative Analysis of Two Approaches to Periocular Recognition in Mobile Scenarios Jo˜ ao C. Monteiro 1(B ) , Rui Esteves 2 , Gil Santos 3 , Paulo Torr˜ ao Fiadeiro 4 , Joana Lobo 2 , and Jaime S. Cardoso 1 1 INESC TEC and Faculdade de Engenharia, Universidade do Porto, Campus da FEUP, Rua Dr. Roberto Frias, 378, 4200-465 Porto, Portugal jcmonteiro89@gmail.com 2 Associa¸ c˜ ao Fraunhofer Portugal Research, Rua Alfredo Allen 455/461, 4200-135 Porto, Portugal 3 IT - Instituto de Telecomunicacoes, Lisboa, Portugal 4 Departamento de F´ ısica, Unidade de Detec¸c˜ ao Remota Universidade da Beira Interior, Rua Marquˆ es D’ ´ Avila e Bolama, 6201-001 Covilh˜ a, Portugal Abstract. In recent years, periocular recognition has become a popular alternative to face and iris recognition in less ideal acquisition scenarios. An interesting example of such scenarios is the usage of mobile devices for recognition purposes. With the growing popularity and easy access to such devices, the development of robust biometric recognition algorithms to work under such conditions finds strong motivation. In the present work we assess the performance of extended versions of two state-of- the-art periocular recognition algorithms on the publicly available CSIP database, a recent dataset composed of images acquired under highly unconstrained and multi-sensor mobile scenarios. The achieved results show each algorithm is better fit to tackle different scenarios and appli- cations of the biometric recognition problem. 1 Introduction Over the past few years face and iris have been on the spotlight of many research works in biometrics. The face is a easily acquirable trait with a high degree of uniqueness, while the iris, the coloured part of the eye, is composed by a set of irregular textural patterns resulting from its random morphogenesis during embryonic development [1]. These marked advantages, however, fall short when low-quality images are presented to the system. With the increasing popularity and availability of mobile devices capable of performing the whole biometric recognition framework, from data acquisition to final decision, serves as further motivation for research in the field of unconstrained biometrics [2]. Several recent works have tried to explore alternative hypotheses to overcome this challenge, either by developing more robust algorithms or by exploring new traits to allow or aid in the recognition process. c  Springer International Publishing Switzerland 2015 G. Bebis et al. (Eds.): ISVC 2015, Part II, LNCS 9475, pp. 268–280, 2015. DOI: 10.1007/978-3-319-27863-6 25