Javier Lorenzo-Navarro

Competition on counter measures to 2-D facial spoofing attacks

Spoofing identities using photographs is one of the most common techniques to attack 2-D face recognition systems. There seems to exist no comparative studies of different techniques using the same protocols and data. The motivation behind this competition is to compare the performance of different state-of-the-art algorithms on the same database using a unique evaluation method. Six different teams from universities around the world have participated in the contest. Use of one or multiple techniques from motion, texture analysis and liveness detection appears to be the common trend in this competition. Most of the algorithms are able to clearly separate spoof attempts from real accesses. The results suggest the investigation of more complex attacks.

The FG 2015 Kinship Verification in the Wild Evaluation

The aim of the Kinship Verification in the Wild Evaluation (held in conjunction with the 2015 IEEE International Conference on Automatic Face and Gesture Recognition, Ljubljana, Slovenia) was to evaluate different kinship verification algorithms. For this task, two datasets were made available and three possible experimental protocols (unsupervised, image-restricted, and image-unrestricted) were designed. Five institutions submitted their results to the evaluation: (i) Politecnico di Torino, Italy; (ii) LIRIS-University of Lyon, France; (iii) Universidad de Las Palmas de Gran Canaria, Spain; (iv) Nanjing University of Aeronautics and Astronautics, China; and (v) Bar Ilan University, Israel. Most of the participants tackled the image-restricted challenge and experimental results demonstrated better kinship verification performance than the baseline methods provided by the organizers.

Multiple face detection at different resolutions for perceptual user interfaces

This paper describes in detail a real-time multiple face detection system for video streams. The system adds to the good performance provided by a window shift approach, the combination of different cues available in video streams due to temporal coherence. The results achieved by this combined solution outperform the basic face detector obtaining a 98% success rate for around 27000 images, providing additionally eye detection and a relation between the successive detections in time by means of detection threads.

Kinship verification in the wild: The first kinship verification competition

Kinship verification from facial images in wild conditions is a relatively new and challenging problem in face analysis. Several datasets and algorithms have been proposed in recent years. However, most existing datasets are of small sizes and one standard evaluation protocol is still lack so that it is difficult to compare the performance of different kinship verification methods. In this paper, we present the Kinship Verification in the Wild Competition: the first kinship verification competition which is held in conjunction with the International Joint Conference on Biometrics 2014, Clearwater, Florida, USA. The key goal of this competition is to compare the performance of different methods on a new-collected dataset with the same evaluation protocol and develop the first standardized benchmark for kinship verification in the wild.

Improving Gender Classification Accuracy in the Wild

In this paper, we focus on gender recognition in challenging large scale scenarios. Firstly, we review the literature results achieved for the problem in large datasets, and select the currently hardest dataset: The Images of Groups. Secondly, we study the extraction of features from the face and its local context to improve the recognition accuracy. Different descriptors, resolutions and classifiers are studied, overcoming previous literature results, reaching an accuracy of 89.8%.

Gender Classification in Large Databases

In this paper, we address the challenge of gender classification using large databases of images with two goals. The first objective is to evaluate whether the error rate decreases compared to smaller databases. The second goal is to determine if the classifier that provides the best classification rate for one database, improves the classification results for other databases, that is, the cross-database performance.

On using periocular biometric for gender classification in the wild

The periocular area is a reliable cue for automatic gender classification (GC).Each local descriptor and grid configuration report different GC accuracy.The score level fusion of local descriptors increases GC performance.Tests carried out in a challenging large and unrestricted dataset.The fusion of periocular and facial GC reduces the classification error in roughly 20%. Display Omitted Gender information may serve to automatically modulate interaction to the user needs, among other applications. Within the Computer Vision community, gender classification (GC) has mainly been accomplished with the facial pattern. Periocular biometrics has recently attracted researchers attention with successful results in the context of identity recognition. But, there is a lack of experimental evaluation of the periocular pattern for GC in the wild. The aim of this paper is to study the performance of this specific facial area in the currently most challenging large dataset for the problem. As expected, the achieved results are slightly worse, roughly 8 percentage points lower, than those obtained by state-of-the-art facial GC, but they suggest the validity of the periocular area particularly in difficult scenarios where the whole face is not visible, or has been altered. A final experiment combines in a multi-scale approach features extracted from the periocular, face and head and shoulders areas, fusing them in a two stage ensemble of classifiers. The accuracy reported beats any previous results on the difficult The Images of Groups dataset, reaching 92.46%, with a GC error reduction of almost 20% compared to the best face based GC results in the literature.

Face and eye detection on hard datasets

Face and eye detection algorithms are deployed in a wide variety of applications. Unfortunately, there has been no quantitative comparison of how these detectors perform under difficult circumstances. We created a dataset of low light and long distance images which possess some of the problems encountered by face and eye detectors solving real world problems. The dataset we created is composed of reimaged images (photohead) and semi-synthetic heads imaged under varying conditions of low light, atmospheric blur, and distances of 3m, 50m, 80m, and 200m. This paper analyzes the detection and localization performance of the participating face and eye algorithms compared with the Viola Jones detector and four leading commercial face detectors. Performance is characterized under the different conditions and parameterized by per-image brightness and contrast. In localization accuracy for eyes, the groups/companies focusing on long-range face detection outperform leading commercial applications.

An study on ear detection and its applications to face detection

OpenCV includes different object detectors based on the Viola-Jones framework. Most of them are specialized to deal with the frontal face pattern and its inner elements: eyes, nose, and mouth. In this paper, we focus on the ear pattern detection, particularly when a head profile or almost profile view is present in the image. We aim at creating real-time ear detectors based on the general object detection framework provided with OpenCV. After training classifiers to detect left ears, right ears, and ears in general, the performance achieved is valid to be used to feed not only a head pose estimation system but also other applications such as those based on ear biometrics.

Automatic clothes segmentation for soft biometrics

During the last decade, researchers have verified that clothing can provide information for gender recognition. However, before extracting features, it is necessary to segment the clothing region. We introduce a new clothes segmentation method based on the application of the GrabCut technique over a trixel mesh, obtaining very promising results for a close to real time system. Finally, the clothing features are combined with facial and head context information to outperform previous results in gender recognition with a public database.