Effective Face Frontalization in Unconstrained Images

Hassner, Tal; Har-El, Shai; Paz, Eran; Enbar, Roee

doi:10.48550/arxiv.1411.7964

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. Note that the type I artefacts are generated by not only our method but also 3D synthesis methods such as [30], [58], [12]. As shown in the top-right side of Fig.…”

Section: B Compositing Artefactsmentioning

confidence: 95%

See 1 more Smart Citation

Frankenstein: Learning Deep Face Representations Using Small Data

Peng²,

Yang³

et al. 2018

IEEE Trans. on Image Process.

115

View full text Add to dashboard Cite

Abstract-Deep convolutional neural networks have recently proven extremely effective for difficult face recognition problems in uncontrolled settings. To train such networks, very large training sets are needed with millions of labeled images. For some applications, such as near-infrared (NIR) face recognition, such large training datasets are not publicly available and difficult to collect. In this work, we propose a method to generate very large training datasets of synthetic images by compositing real face images in a given dataset. We show that this method enables to learn models from as few as 10,000 training images, which perform on par with models trained from 500,000 images. Using our approach we also obtain state-of-the-art results on the CASIA NIR-VIS2.0 heterogeneous face recognition dataset.

show abstract

“…2. Note that the type I artefacts are generated by not only our method but also 3D synthesis methods such as [30], [58], [12]. As shown in the top-right side of Fig.…”

Section: B Compositing Artefactsmentioning

confidence: 95%

“…Our method 3D synthesis illumination pose Fig. 2: Top row: Type I hard boundary artefacts generated by our method (left) and 3D synthesis methods [30], [58], [12] (right). Bottom row: Type II artefacts due to inconsistencies in illumination (left) and pose (right) generated by our method.…”

Section: Face Recognition Pipelinementioning

confidence: 99%

Frankenstein: Learning Deep Face Representations Using Small Data

Peng²,

Yang³

et al. 2018

IEEE Trans. on Image Process.

115

View full text Add to dashboard Cite

show abstract

“…With these exertions, the traditional face recognition problem is re-defined, shifting from the strictly regulated setting to the unconstrained condition with severe intra-variabilities, e.g., the LFW and the YouTube Faces (YTF) images. This evolvement stimulates enormous research on pose-invariant face recognition, e.g., [35][36][37].…”

Section: A Related Workmentioning

confidence: 99%

Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition

Low

Teoh

2019

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

This paper devises a new means of filter diversification, dubbed multi-fold filter convolution ( -FFC), for face recognition. On the assumption that -FFC receives singlescale Gabor filters of varying orientations as input, these filters are self-cross convolved by -fold to instantiate a filter offspring set. The -FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters, and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA and ICA filters thus yields three offspring sets: (1) Gabor filters solely, (2) Gabor-PCA filters, and (3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors. To facilitate a sensible Gabor filter selection for -FFC, the 40 multiscale, multi-orientation Gabor filters are condensed into 8 elementary filters. Aside from that, an average histogram pooling operator is employed to leverage the -FFC histogram features, prior to the final whitening PCA compression. The empirical results substantiate that the 2-FFC descriptors prevail over, or on par with, other face descriptors on both identification and verification tasks. Index Terms-Gaborfilters, PCA filters, ICA filters, filter convolution, face recognition Hong Kong learns from approximately 300,000 images with 13,000 identities; FaceNet [5] by Google trains CNNs from 200M images spanning over 8M identities. These prevailing CNN models, particularly DeepID3 and FaceNet, reportedly achieve accuracies of 99.53% and 99.63%, respectively, on the labeled faces in the wild (LFW) dataset [41], surpassing the human-level performance of 97.53%. On the contrary, the FB approaches, e.g., PCANet [14], discriminant face descriptor (DFD) [15], compact binary face descriptor (CBFD) [16], binarized statistical image features (BSIF) [17-18], DCTNet [20], etc., are typically equipped with a single or two filtering layers. Despite of being simple and easy of use, these CNN simplifications promise the state of the art robustness to the generic image classification problems including face.The earliest FB approaches are reviewed and compared in [6]. They share a common three-stage pipeline, referred to as filter-rectify-filter (FRF): (1) a convolutional stage based on the heuristically designed filter banks, e.g., Laws masks, ring and wedge filters, Gabor filters, wavelet transform, packets and frames, discrete cosine transform (DCT), etc.; or other optimal filters, e.g., principal component analysis (PCA) eigenfilters, Karhunen-Loeve transform, prediction error filters, optimized Gabor filters, etc., (2) a nonlinearity, a. k. a filter response rectification step, e.g., magnitude, squaring, rectified sigmoid, etc., (3) pooling (filtering) operations, e.g., spatial averaging, smoothing, or nonlinear inhibition, to remove the inhomogeneity in the rectified responses within a homogenous region. The local energy function, includes stage (2) and (3), outputs a set of feature images, one per filter, def...

show abstract

“…This ranges from rough centering in Schroff, Florian and Kalenichenko 2015 to the use of a 3D face mask estimate and re-projection of the 2D image as in Hassner, Tal, et al 2014. 5,31 5. DATASETS…”

Section: The State-of-the-art In Facial Recognitionmentioning

confidence: 99%

Deep learning and face recognition: the state of the art

Balaban

2015

SPIE Proceedings

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) have established themselves as a dominant technique in machine learning. DNNs have been top performers on a wide variety of tasks including image classification, speech recognition, and face recognition. 1-3 Convolutional neural networks (CNNs) have been used in nearly all of the top performing methods on the Labeled Faces in the Wild (LFW) dataset. [3][4][5][6] In this talk and accompanying paper, I attempt to provide a review and summary of the deep learning techniques used in the state-of-the-art. In addition, I highlight the need for both larger and more challenging public datasets to benchmark these systems.Despite the ability of DNNs and autoencoders to perform unsupervised feature learning, modern facial recognition pipelines still require domain specific engineering in the form of re-alignment. For example, in Facebook's recent DeepFace paper, a 3D "frontalization" step lies at the beginning of the pipeline. This step creates a 3D face model for the incoming image and then uses a series of affine transformations of the fiducial points to "frontalize" the image. This step enables the DeepFace system to use a neural network architecture with locally connected layers without weight sharing as opposed to standard convolutional layers. 6 Deep learning techniques combined with large datasets have allowed research groups to surpass human level performance on the LFW dataset. 3, 5The high accuracy (99.63% for FaceNet at the time of publishing) and utilization of outside data (hundreds of millions of images in the case of Google's FaceNet) suggest that current face verification benchmarks such as LFW may not be challenging enough, nor provide enough data, for current techniques. 3, 5 There exist a variety of organizations with mobile photo sharing applications that would be capable of releasing a very large scale and highly diverse dataset of facial images captured on mobile devices. Such an "ImageNet for Face Recognition" would likely receive a warm welcome from researchers and practitioners alike.

show abstract

Effective Face Frontalization in Unconstrained Images

Cited by 3 publications

References 0 publications

Frankenstein: Learning Deep Face Representations Using Small Data

Frankenstein: Learning Deep Face Representations Using Small Data

Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition

Deep learning and face recognition: the state of the art

Contact Info

Product

Resources

About