Surveillance video face recognition with single sample per person based on 3D modeling and blurring

Three-dimensional human face modeling is a very popular topic with many applications,such as facial animation, face recognition and model-based facial video communication. Therefore, how to model the facial geometry, texture intensity and illumination variation is important in computer vision and graphics. Previous works on 3D head modeling from a single face image utilized prior information on 3D head models. However, it is difficult to accurately reconstruct the 3D face model from a single face image with expression since the facial expression induces 3D face model deformation in a complex manner. The main challenge is the coupling of the neutral 3D face model and the 3D deformation due to expression, thus making the 3D model estimation from a single face image with expression very challenging. On the other hand, the illumination condition also makes the problem more difficult. In this thesis,we focus on developing a 3D face model reconstruction system including surface registration and training of 3D face models with expressional deformations as well as the estimation of the 3D neutral shape and the 3D expressional deformation from a single face image. The proposed reconstruction algorithm integrates the linear and non-linear subspace representations for a prior 3D neutral morphable model and the probabilistic manifold-based 3D expressional deformation. We incorporate the face geometry, expression deformation, texture and illumination information into the problem so that it is well constrained. The reconstructed 3D face models can also be further extended and applied to many real-world applications.

Face recognition with single training sample has the problem that the sample is single and face pattern is changeable. The rate of traditional face recognition methods declines seriously in the case of single training sample. Thus, studying the face recognition method which is appropriate for single training sample is challenging in face recognition field. In this paper, in order to solve the problem of single training sample, sample extension method is adopted to expand fourteen virtual samples. And for the problem of changeable face pattern, like pose, expressions, illumination etc., this paper uses image blocking and applies weighted two-directional 2DPCA to extract the local feature information of face image. Further, fuse the local feature information of sub-image to face recognition. The experimental results on ORL and YALE face database show that the method in this paper achieves good recognition effect.

Face recognition in video has gained wide attention due to its role in designing surveillance systems. One of the main advantages of video over still frames is that evidence accumulation over multiple frames can provide better face recognition performance. However, surveillance videos are generally of low resolution containing faces mostly in non-frontal poses. Consequently, face recognition in video poses serious challenges to state-of-the-art face recognition systems. Use of 3D face models has been suggested as a way to compensate for low resolution, poor contrast and non-frontal pose. We propose to overcome the pose problem by automatically (i) reconstructing a 3D face model from multiple non-frontal frames in a video, (ii) generating a frontal view from the derived 3D model, and (iii) using a commercial 2D face recognition engine to recognize the synthesized frontal view. A factorization-based structure from motion algorithm is used for 3D face reconstruction. The proposed scheme has been tested on CMU's Face In Action (FIA) video database with 221 subjects. Experimental results show a 40% improvement in matching performance as a result of using the 3D models.

A single gallery-based face recognition using extended joint sparse representation

Due to its wide applications in practice, face recognition has been an active research topic. With the availability of adequate training samples, many machine learning methods could yield high face recognition accuracy. However, under the circumstance of inadequate training samples, especially the extreme case of having only a single training sample, face recognition becomes challenging. How to deal with conflicting concerns of the small sample size and high dimensionality in one-sample face recognition is critical for its achievable recognition accuracy and feasibility in practice. Being different from the conventional methods for global face recognition based on generalization ability promotion and local face recognition depending on image segmentation, a single-sample face recognition algorithm based on locality preserving projection (LPP) feature transfer is proposed here. First, transfer sources are screened to obtain the selective sample source using the whitened cosine similarity metric. Second, we project the vectors of source faces and target faces into feature subspace by LPP, respectively, and calculate the feature transfer matrix to approximate the mapping relationship on source faces and target faces in subspace. Then, the feature transfer matrix is used on training samples to transfer the original macro characteristics to target macro characteristics. Finally, the nearest neighbor classifier is used for face recognition. Our results based on popular databases FERET, ORL, and Yale demonstrate the superiority of the proposed LPP feature transfer-based one-sample face recognition algorithm when compared with popular single-sample face recognition algorithms, such as (PC) $^{2}\text{A}$ and Block FLDA.

Latent face model for across-media face recognition

Non-linear dictionary representation of deep features for face recognition from a single sample per person

This paper presents estimation of head pose angles from a single 2D face image using a 3D face model morphed from a reference face model. A reference model refers to a 3D face of a person of the same ethnicity and gender as the query subject. The proposed scheme minimizes the disparity between the two sets of prominent facial features on the query face image and the corresponding points on the 3D face model to estimate the head pose angles. The 3D face model used is morphed from a reference model to be more specific to the query face in terms of the depth error at the feature points. The morphing process produces a 3D face model more specific to the query image when multiple 2D face images of the query subject are available for training. The proposed morphing process is computationally efficient since the depth of a 3D face model is adjusted by a scalar depth parameter at feature points. Optimal depth parameters are found by minimizing the disparity between the 2D features of the query face image and the corresponding features on the morphed 3D model projected onto 2D space. The proposed head pose estimation technique was evaluated on two benchmarking databases: 1) the USF Human-ID database for depth estimation and 2) the Pointing'04 database for head pose estimation. Experiment results demonstrate that head pose estimation errors in nodding and shaking angles are as low as 7.93° and 4.65° on average for a single 2D input face image.

We present an algorithm for 3D face modeling from a frontal image and a profile image of a person's face. The algorithm starts by computing the 3D coordinates of automatically extracted facial feature points. The coordinates of the selected feature points are then used to deform a 3D generic face model to obtain a 3D face model for that person. Procrustes analysis is used to minimize globally the distances between the facial feature vertices in the model and the corresponding 3D points obtained from the images. Then, local deformation is performed on the facial feature vertices to obtain a more realistic 3D model for the person. Preliminary experiments to asses the applicability of the models for face recognition show encouraging results.

In this paper, an adaptive approximation image reconstruction method based on orthogonal triangular with column pivoting (QRCP) decomposition algorithm is proposed for single sample problem in face recognition. By using QRCP the single sample and its transpose are decomposed to two sets of basis images. Then an adaptive approximation image reconstruction method is proposed to reconstruct two approximation images from the two basis image sets respectively. The single training sample and its two approximation images of each object form a new training set, which can make the fisher linear discriminant analysis (FLDA) be applied to single sample problem in face recognition. The performance of the proposed method is verified on Yale, FERET, and ORL face databases. The experimental results indicate that the proposed method is efficient and outperforms some existing methods which are proposed to overcome the single sample problem.

Rapid growth of social networks has provided an extraordinary medium to share a large volume of photographs online. This calls for designing efficient face recognition techniques that are applicable to images with low resolutions and arbitrary poses. This paper proposes a new pose invariant face recognition method for low resolution images using only a single training sample. A 3D model, reconstructed using Generic Elastic Model (3D GEM) from a frontal view training sample, is used to generate a set of nonfrontal gallery face images. The face region of the nonfrontal query sample is then extracted using the same landmark detection technique as in the 3D GEM algorithm. Afterwards, a novel texture representation technique called Local Comparative Decimal Pattern (LCDP) is proposed to extract features from each of the training and query samples. A set of experimental results on the ORL, Georgia Tech (GT), and LFW face databases demonstrates the efficiency of the proposed method compared to other state-of-the-art approaches.

We present an approach to identify non-cooperative individuals at a distance from a sequence of images using 3D face models. Most biometric features (such as fingerprints, hand shape, iris or retinal scans) require cooperative subjects in close proximity to the biometric system. Even top 2D face recognition systems today are only reliable at a distance when presented with frontal images. Our approach is accomplished by processing images acquired with an ultra-high resolution video camera, inferring the location of the subjects' head, using this information to crop the region of interest, building a 3D face model, and using this 3D model to perform biometric identification. To build the 3D model, we use an image sequence, as natural head and body motion provides enough viewpoint variation to perform stereo-motion for 3D face reconstruction. The 3D face model allows the use of true shape invariants for recognition against 3D galleries. Also the 3D model can assist in matching non-frontal faces against 2D galleries by rotating and rendering the 3D reconstruction into a 2D frontal image when only a 2D gallery is available. This approach constitutes a considerable step forward in solving the challenging problem of biometric identification at a distance.

Similarity mapping for robust face recognition via a single training sample per person

Background: The scarcity of 3D facial models presents a significant hurdle for researchers and educators. Gathering such data demands substantial resources. Objective: To introduce an open-source 3D morphing software to generate 3D facial data sets for research and to provide a large sample data set that is based on synthetically generated 3D models. Methods: Software is developed to morph 3D facial models in bulk by altering landmark locations. Twenty synthetic 3D facial models are generated utilizing deep learning tools and 28 landmarks located on each. The measurements of synthetic models are confirmed to be realistic by comparing them with facial statistics. Several facial deformities and types are simulated at various magnitudes on 3D models to generate a large data set. Results: An open-source software and an open-access data set of 980 3D facial models, each with 28 landmark locations, are provided. Since the data set is based on synthetically generated 3D models, no institutional review board approval is required. Conclusion: The 3D morphing software and the large 3D data set are expected to benefit researchers and educators in the field of facial surgery and facial landmark detection.

Cycle-autoencoder based block-sparse joint representation for single sample face recognition