Jacek Naruniec

Deep Alignment Network: A Convolutional Neural Network for Robust Face Alignment

In this paper, we propose Deep Alignment Network (DAN), a robust face alignment method based on a deep neural network architecture. DAN consists of multiple stages, where each stage improves the locations of the facial landmarks estimated by the previous stage. Our method uses entire face images at all stages, contrary to the recently proposed face alignment methods that rely on local patches. This is possible thanks to the use of landmark heatmaps which provide visual information about landmark locations estimated at the previous stages of the algorithm. The use of entire face images rather than patches allows DAN to handle face images with large variation in head pose and difficult initializations. An extensive evaluation on two publicly available datasets shows that DAN reduces the state-of-the-art failure rate by up to 70%. Our method has also been submitted for evaluation as part of the Menpo challenge.

Face detection by discrete Gabor jets and reference graph of fiducial points

A novel face detection scheme is described. The facial feature extraction algorithm is based on discrete approximation of Gabor Transform, called Discrete Gabor Jets (DGJ), evaluated in fiducial face points. DGJ is computed using integral image for fast summations in arbitrary windows, and by FFT operations on short contrast signals. Contrasting is performed along radial directions while frequency analysis along angular direction. Fourier coefficients for a small number rings create a long vector which is next reduced to few LDA components. Four fiducial points are only considered: two eye corners and two nose corners. Fiducial points detection is based on face/nonface classifier using distance to point dependent LDA center and threshold corresponding to equal error rate on ROC. Finally, the reference graph is used to detect the whole face. The proposed method is compared with the popular AdaBoost technique and its advantages and disadvantages are discussed.

Live Scan3D: A Fast and Inexpensive 3D Data Acquisition System for Multiple Kinect v2 Sensors

LiveScan3D is a free, open source system for live, 3D data acquisition using multiple Kinect v2 sensors. It allows the user to place any number of sensors in any physical configuration and start gathering data at real time speed. The freedom of placing the sensors in any configuration allows for many possible acquisition scenarios such as: capturing a single object from many viewpoints or creating 3D panoramas with multiple devices located close to each other. Thanks to the off-the-shelf Kinect v2 sensor the system is both accurate and inexpensive, opening 3D acquisition up to more recipients. In the paper we describe our system with the algorithms it is using and show its effectiveness in multiple scenarios including head shape reconstruction and 3D reconstruction of dynamic scenes.

Using a Probabilistic Neural Network for lip-based biometric verification

In classical recognition techniques only raw features of objects are employed. Our approach allows use the composed features so called Sim coefficients and landmarks which determine the area where biometric features should be searched. Biometric composed features are associated with appropriate similarity coefficients. Such approach brings significant advantages recognition level of objects is higher compared to method based on the raw data. In this paper, a novel and effective lip-based biometric recognition approach with the Probabilistic Neural Network (PNN) is proposed. Lip based recognition has been less developed than the recognition of other human physical attributes such as the fingerprint, voice patterns, blood vessel patterns, or the face. For this reason, achieved results on this field are still improved and new recognition techniques are searched. Results achieved by PNN were improved by the Particle Swarm Optimization (PSO) technique.In the first step, lip area is restricted to a Region Of Interest (ROI) and in the second step, features extracted from ROI are specifically modeled by dedicated image processing algorithms. Extracted lip features are then an input data of neural network. All experiments were confirmed in the ten-fold cross validation fashion on three diverse datasets, Multi-PIE Face Dataset, PUT database and our own faces dataset. Obtained in researches result show that proposed approach achieves an average classification accuracy of 86.95%, 87.14%, and 87.26%, on these three datasets, respectively. Announced results were verified in the comparative studies and confirm the efficacy of the proposed lip based biometrics learned by PSO technique. We proposed a novel biometric system based on lip geometrical features measurements.Each lip feature is paired with a similarity measure and form a composed feature.The set of the most discriminative lip composed features is determined.Probabilistic Neural Network classifier is used for lip verification. Display Omitted

Face Alignment Using K-Cluster Regression Forests With Weighted Splitting

In this letter, we present a face alignment pipeline based on two novel methods: weighted splitting for K-cluster Regression Forests (KRF) and three-dimensional Affine Pose Regression (3D-APR) for face shape initialization. Our face alignment method is based on the Local Binary Feature (LBF) framework, where instead of standard regression forests and pixel difference features used in the original method, we use our K-Cluster Regression Forests with Weighted Splitting (KRFWS) and Pyramid Histogram of Oriented Gradients (PHOG) features. We also use KRFWS to perform APR and 3D-APR, which intend to improve the face shape initialization. APR applies a rigid 2-D transform to the initial face shape that compensates for inaccuracy in the initial face location, size, and in-plane rotation. 3D-APR estimates the parameters of a 3-D transform that additionally compensates for out-of-plane rotation. The resulting pipeline, consisting of APR and 3D-APR followed by face alignment, shows an improvement of 20% over standard LBF on the challenging Intelligent Behaviour Understanding Group (IBUG) dataset, and state-of-the-art accuracy on the entire 300-W dataset.

On-line range images registration with GPGPU

This paper concerns implementation of algorithms in the two important aspects of modern 3D data processing: data registration and segmentation. Solution proposed for the first topic is based on the 3D space decomposition, while the latter on image processing and local neighbourhood search. Data processing is implemented by using NVIDIA compute unified device architecture (NIVIDIA CUDA) parallel computation. The result of the segmentation is a coloured map where different colours correspond to different objects, such as walls, floor and stairs. The research is related to the problem of collecting 3D data with a RGB-D camera mounted on a rotated head, to be used in mobile robot applications. Performance of the data registration algorithm is aimed for on-line processing. The iterative closest point (ICP) approach is chosen as a registration method. Computations are based on the parallel fast nearest neighbour search. This procedure decomposes 3D space into cubic buckets and, therefore, the time of the matching is deterministic. First technique of the data segmentation uses accele-rometers integrated with a RGB-D sensor to obtain rotation compensation and image processing method for defining pre-requisites of the known categories. The second technique uses the adapted nearest neighbour search procedure for obtaining normal vectors for each range point.

Face Detection Using Discrete Gabor Jets and a Probabilistic Model of Colored Image Patches

Face detection allows to recognize and detect human faces and provides information about their location in a given image. Many applications such as biometrics, face recognition, and video surveillance employ face detection as one of their main modules. Therefore, improvement in the performance of existing face detection systems and new achievements in this field of research are of significant importance. In this paper a hierarchical classification approach for face detection is presented. In the first step, discrete Gabor jets (DGJ) are used for extracting features related to the brightness information of images and a preliminary classification is made. Afterwards, a skin detection algorithm, based on modeling of colored image patches, is employed as a post-processing of the results of DGJ-based classification. It is shown that the use of color efficiently reduces the number of false positives while maintaining a high true positive rate. A comparison is made with the OpenCV implementation of the Viola and Jones face detector and it is concluded that higher correct classification rates can be attained using the proposed face detector.

Open source robotic 3D mapping framework with ROS — Robot Operating System, PCL — Point Cloud Library and Cloud Compare

We propose an open source robotic 3D mapping framework based on Robot Operating System, Point Cloud Library and Cloud Compare software extended by functionality of importing and exporting datasets. The added value is an integrated solution for robotic 3D mapping and new publicly available datasets (accurate 3D maps with geodetic precision) for evaluation purpose Datasets were gathered by mobile robot in stop scan fashion. Presented results are a variety of tools for working with such datasets, for task such as: preprocessing (filtering, down sampling), data registration (ICP, NDT), graph optimization (ELCH, LUM), tools for validation (comparison of 3D maps and trajectories), performance evaluation (plots of various outputs of algorithms). The tools form a complete pipeline for 3D data processing. We use this framework as a reference methodology in recent work on SLAM algorithms.

3D face data acquisition and modelling based on an RGBD camera matrix

This paper describes a novel system for building morphable 3D head models. In contrast to most of the previous approaches that need several seconds to capture each scan, we acquire the data using a matrix of calibrated RGBD cameras, enabling real time face scanning. We localize the face and its 68 characteristic points on an orthogonal projection image, and use the detected points to align multiple scans. We use a Delaunay triangulation of the 68 characteristic points to obtain dense head shapes with point to point correspondence across all 3D head shapes. In the last step we create a morphable model in a way that is similar to the original procedure by Blanz and Vetter. We demonstrate the functionality of our model, created on just five people, in a real-time application. The novelty of this article lies mostly in the method of defining correspondences of the characteristic points in 3D, that leads to a realistic three-dimensional model and blendshapes.

Evaluation of active appearance models in varying background conditions

In this paper we present an evaluation of the chosen versions of Active Appearance Models (AAM) in varying background conditions. Algorithms were tested on a subset of the CMU PIE database and chosen background im- ages. Our experiments prove, that the accuracy of those methods is strictly correlated with the used background, where the differences in the success rate differ even up to 50%.