Qijun Zhao

A DCNN Based Fingerprint Liveness Detection Algorithm with Voting Strategy

The concern of the safety of fingerprint authentication system is rising with its widely using for it is easy to be attacked by spoof (fake) fingerprints. Fake fingerprints are usually made of Ploy-Doh, silicon or other artifacts. So most current approaches rely on fingerprint liveness detection as main anti-spoofing mechanisms. Recently, researchers propose to use local feature descriptor for fingerprint liveness detection, but the results are still not satisfying the real world application requirement. Inspired by the newly trend of application of Deep Convolution Neural Network (DCNN) in computer vision field and its outstanding performance in face detection and image classification, we propose a novel fingerprint liveness detection method based on DCNN and voting strategy, which performs better than handcraft feature and optimize the process of feature extraction and classifier training simultaneously. The experimental results on the datasets of LivDet2011 and LivDet2013 show that the proposed algorithm has great improvement compare to the former state-of-the-art algorithm, and keep highly real-time performance at the same time.

The CFVD Reflection-Type Finger-Vein Image Database with Evaluation Baseline

In this paper, we describe the reflection-type finger-vein image database named by CFVD for biometrics research, including its acquisition, contents and evaluation baseline. The main contributions of this work include the following points: providing the worldwide researchers with reflection-type finger-vein recognition uniform database and ground-truth evaluation baseline. Currently, the CFVD database contains 1345 images of 130 fingers from 13 individuals ( 10 males and 3 females ). Based on this database, the researchers can evaluate the performance of their algorithms for reflection-type finger-vein recognition. As the first reflection-type finger-vein image database available in the public domain, we believe that it will promote the development of finger-vein recognition techniques. We are keeping enlarging this database by including the finger-vein data of additional people.

Facial Ethnicity Classification with Deep Convolutional Neural Networks

As an important attribute of human beings, ethnicity plays a very basic and crucial role in biometric recognition. In this paper, we propose a novel approach to solve the problem of ethnicity classification. Existing methods of ethnicity classification normally consist of two stages: extracting features on face images and training a classifier based on the extracted features. Instead, we tackle the problem via using Deep Convolution Neural Networks to extract features and classify them simultaneously. The proposed method is evaluated in three scenarios: (i) the classification of black and white people, (ii) the classification of Chinese and Non-Chinese people, and (iii) the classification of Han, Uyghurs and Non-Chinese. Experimental results on both public and self-collected databases demonstrate the effectiveness of the proposed method.

Head Pose Estimation with Improved Random Regression Forests

Head pose estimation is an important step in many face related applications. In this paper, we propose to use random regression forests to estimate head poses in 2D face images. Given a 2D face image, Gabor filters are first applied to extract raw high-dimensional features. Linear discriminant analysis (LDA) is then used to reduce the feature dimension. Random regression forests are constructed in the low dimensional feature space. Unlike traditional random forests, when generating tree predictors in the forests we weight the features according to the eigenvalues associated with their corresponding LDA axes. The proposed method has been evaluated on a set of 2D face images synthesized from the BU-3DFE database and on the CMU-PIE database. The experimental results demonstrate the effectiveness of the proposed method.

Finger Vein Recognition Based on Gabor Filter

Finger vein recognition is a promising biometric authentication technique. Finger vein images include a plurality of lines and can be regarded as a type of texture image. This paper proposes the use of 2D Gabor filters to process finger vein images and extract the texture features for better recognition results. Euclidean distance matching is performed. Experimental results demonstrate the effectiveness of this method.

Fingerprint Segmentation via Convolutional Neural Networks

In automatic fingerprint identification systems, it is crucial to segment the fingerprint images. Inspired by the superiority of convolutional neural networks for various classification and regression tasks, we approach fingerprint segmentation as a binary classification problem and propose a convolutional neural network based method for fingerprint segmentation. Given a fingerprint image, we first apply the total variation model to decompose it into cartoon and texture components. Then, the obtained texture component image is divided into overlapping patches, which are classified by the trained convolutional neural network as either foreground or background. Based on the classification results and by applying morphology-based post-processing, we get the final segmentation result for the whole fingerprint image. In the experiments, we investigate the effect of different patch sizes on the segmentation performance, and compare the proposed method with state-of-the-art algorithms on FVC2000, FVC2002 and FVC2004. Experimental results demonstrate that the proposed method outperforms existing algorithms.

Robust Multi-view Face Alignment Based on Cascaded 2D/3D Face Shape Regression

In this paper, we present a cascaded regression algorithm for multi-view face alignment. Our method employs a two-stage cascaded regression framework and estimates 2D and 3D facial feature points simultaneously. In stage one, 2D and 3D facial feature points are roughly detected on the input face image, and head pose analysis is applied based on the 3D facial feature points to estimate its head pose. The face is then classified into one of three categories, namely left profile faces, frontal faces and right profile faces, according to its pose. In stage two, accurate facial feature points are detected by using an appropriate regression model corresponding to the pose category of the input face. Compared with existing face alignment methods, our proposed method can better deal with arbitrary view facial images whose yaw angles range from −90 to \(90^{\circ }\). Moreover, in order to enhance its robustness to facial bounding box variations, we randomly generate multiple bounding boxes according to the statistical distributions of bounding boxes and use them for initialization during training. Extensive experiments on public databases prove the superiority of our proposed method over state-of-the-art methods, especially in aligning large off-angle faces.

Glasses Detection Using Convolutional Neural Networks

Glasses detection plays an important role in face recognition and soft biometrices for person identification. However, automatic glasses detection is still a challenging problem under real application scenarios, because face variations, light conditions, and self-occlusion, have significant influence on its performance. Inspired by the success of Deep Convolutional Neural Networks (DCNN) on face recognition, object detection and image classification, we propose a glasses detection method based on DCNN. Specifically, we devise a Glasses Network (GNet), and pre-train it as a face identification network with a large number of face images. The pre-trained GNet is finally fine-tuned as a glasses detection network by using another set of facial images wearing and not wearing glasses. Evaluation experiments have been done on two public databases, Multi-PIE and LFW. The results demonstrate the superior performance of the proposed method over competing methods.

Matching Depth to RGB for Boosting Face Verification

Low cost RGB-D sensors like Kinect and RealSense enable easy acquisition of both RGB (i.e., texture) and depth images of human faces. Many methods have been proposed to improve the RGB-to-RGB face matcher by fusing it with the Depth-to-Depth face matcher. Yet, few efforts have been devoted to the matching between RGB and Depth face images. In this paper, we propose two deep convolutional neural network (DCNN) based approaches to Depth-to-RGB face recognition, and compare their performance in terms of face verification accuracy. We further combine the Depth-to-RGB matcher with the RGB-to-RGB matcher via score-level fusion. Evaluation experiments on two databases demonstrate that matching depth to RGB does boost face verification accuracy.

A CNN-Based Fingerprint Image Quality Assessment Method

Fingerprint image quality assessment is a very important task as the performance of automatic fingerprint identification systems relies heavily on the quality of fingerprint images. Existing methods have made many efforts to find out more appropriate solutions, but most of them operate either on full regions of a fingerprint image, or on local areas. Unlike previous methods, we divide fingerprint images into blocks, and define the quality levels of the blocks according to the minutiae on them and their ridge orientation certainty. With the manually prepared quality-specific fingerprint image blocks, we train a convolutional neural network (CNN) to fulfill end-to-end quality prediction for fingerprint image blocks. The global quality of a fingerprint image can be obtained by fusing the quality levels of its blocks. We evaluate the proposed method on FVC2002 DB1A and FVC2002 DB2A. Experimental results show that the proposed method can effectively distinguish good quality fingerprints from bad ones, and ensure high fingerprint recognition accuracy.