Results 1 - 10
of
31
X.: Fusing robust face region descriptors via multiple metric learning for face recognition
- in the wild. In: Computer Vision and Pattern Recognition (CVPR), IEEE
, 2013
"... In many real-world face recognition scenarios, face images can hardly be aligned accurately due to complex ap-pearance variations or low-quality images. To address this issue, we propose a new approach to extract robust face re-gion descriptors. Specifically, we divide each image (resp. video) into ..."
Abstract
-
Cited by 35 (4 self)
- Add to MetaCart
(Show Context)
In many real-world face recognition scenarios, face images can hardly be aligned accurately due to complex ap-pearance variations or low-quality images. To address this issue, we propose a new approach to extract robust face re-gion descriptors. Specifically, we divide each image (resp. video) into several spatial blocks (resp. spatial-temporal volumes) and then represent each block (resp. volume) by sum-pooling the nonnegative sparse codes of position-free patches sampled within the block (resp. volume). Whitened Principal Component Analysis (WPCA) is further utilized to reduce the feature dimension, which leads to our Spatial Face Region Descriptor (SFRD) (resp. Spatial-Temporal Face Region Descriptor, STFRD) for images (resp. videos). Moreover, we develop a new distance metric learning method for face verification called Pairwise-constrained Multiple Metric Learning (PMML) to effectively integrate the face region descriptors of all blocks (resp. volumes) from an image (resp. a video). Our work achieves the state-of-the-art performances on two real-world datasets LFW and YouTube Faces (YTF) according to the restricted pro-tocol. 1.
Pcanet: A simple deep learning baseline for image classification?” arXiv preprint arXiv:1404.3606
, 2014
"... Abstract — In this paper, we propose a very simple deep learning network for image classification that is based on very basic data processing components: 1) cascaded principal com-ponent analysis (PCA); 2) binary hashing; and 3) blockwise histograms. In the proposed architecture, the PCA is employed ..."
Abstract
-
Cited by 10 (0 self)
- Add to MetaCart
Abstract — In this paper, we propose a very simple deep learning network for image classification that is based on very basic data processing components: 1) cascaded principal com-ponent analysis (PCA); 2) binary hashing; and 3) blockwise histograms. In the proposed architecture, the PCA is employed to learn multistage filter banks. This is followed by simple binary hashing and block histograms for indexing and pooling. This architecture is thus called the PCA network (PCANet) and can be extremely easily and efficiently designed and learned. For comparison and to provide a better understanding, we also introduce and study two simple variations of PCANet: 1) RandNet and 2) LDANet. They share the same topology as PCANet, but their cascaded filters are either randomly selected or learned from linear discriminant analysis. We have extensively tested these basic networks on many benchmark visual data sets
Discriminatively trained dense surface normal estimation
- In Proc. of ECCV (2014
"... Abstract. In this work we propose the method for a rather unexplored problem of computer vision- discriminatively trained dense surface nor-mal estimation from a single image. Our method combines contextual and segment-based cues and builds a regressor in a boosting framework by transforming the pro ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
(Show Context)
Abstract. In this work we propose the method for a rather unexplored problem of computer vision- discriminatively trained dense surface nor-mal estimation from a single image. Our method combines contextual and segment-based cues and builds a regressor in a boosting framework by transforming the problem into the regression of coefficients of a local coding. We apply our method to two challenging data sets containing images of man-made environments, the indoor NYU2 data set and the outdoor KITTI data set. Our surface normal predictor achieves results better than initially expected, significantly outperforming state-of-the-art. 1
Subtasks of Unconstrained Face Recognition
"... Abstract: Unconstrained face recognition remains a challenging computer vision problem despite recent exceptionally high results ( ∼ 95 % accuracy) on the current gold standard evaluation dataset: Labeled Faces in the Wild (LFW) (Huang et al., 2008; Chen et al., 2013). We offer a decomposition of th ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
Abstract: Unconstrained face recognition remains a challenging computer vision problem despite recent exceptionally high results ( ∼ 95 % accuracy) on the current gold standard evaluation dataset: Labeled Faces in the Wild (LFW) (Huang et al., 2008; Chen et al., 2013). We offer a decomposition of the unconstrained problem into subtasks based on the idea that invariance to identity-preserving transformations is the crux of recognition. Each of the subtasks in the Subtasks of Unconstrained Face Recognition (SUFR) challenge consists of a same-different face-matching problem on a set of 400 individual synthetic faces rendered so as to isolate a specific transformation or set of transformations. We characterized the performance of 9 different models (8 previously published) on each of the subtasks. One notable finding was that the HMAX-C2 feature was not nearly as clutter-resistant as had been suggested by previous publications (Leibo et al., 2010; Pinto et al., 2011). Next we considered LFW and argued that it is too easy of a task to continue to be regarded as a measure of progress on unconstrained face recognition. In particular, strong performance on LFW requires almost no invariance, yet it cannot be considered a fair approximation of the outcome of a detection→alignment pipeline since it does not contain the kinds of variability that realistic alignment systems produce when working on non-frontal faces. We offer a new, more difficult, natural image dataset: SUFR-in-the-Wild (SUFR-W), which we created using a protocol that was similar to LFW, but with a few differences designed to produce more need for transformation invariance. We present baseline results for eight different face recognition systems on the new dataset and argue that it is time to retire LFW and move on to more difficult evaluations for unconstrained face recognition. 1
Face recognition via archetype hull ranking
- In Proc. ICCV
, 2013
"... The archetype hull model is playing an important role in large-scale data analytics and mining, but rarely applied to vision problems. In this paper, we migrate such a geometric model to address face recognition and verification together through proposing a unified archetype hull ranking frame-work. ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
The archetype hull model is playing an important role in large-scale data analytics and mining, but rarely applied to vision problems. In this paper, we migrate such a geometric model to address face recognition and verification together through proposing a unified archetype hull ranking frame-work. Upon a scalable graph characterized by a compact set of archetype exemplars whose convex hull encompasses most of the training images, the proposed framework ex-plicitly captures the relevance between any query and the stored archetypes, yielding a rank vector over the archetype hull. The archetype hull ranking is then executed on ev-ery block of face images to generate a blockwise similarity measure that is achieved by comparing two different rank vectors with respect to the same archetype hull. After inte-grating blockwise similarity measurements with learned im-portance weights, we accomplish a sensible face similarity measure which can support robust and effective face recog-nition and verification. We evaluate the face similarity mea-sure in terms of experiments performed on three benchmark face databases Multi-PIE, Pubfig83, and LFW, demonstrat-ing its performance superior to the state-of-the-arts. 1.
HUSSAIN ET. AL: FACE RECOGNITION USING LOCAL QUANTIZED PATTERNS 1 Face Recognition using Local Quantized Patterns
, 2013
"... HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte p ..."
Abstract
- Add to MetaCart
(Show Context)
HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
The Invariance Hypothesis and the Ventral Stream
, 2014
"... Unlike Athena, the new ventral stream theory foreshadowed in these pages did not spring fully-formed from the head of Zeus. We: primarily Tomaso Poggio, Fabio Anselmi, Lorenzo Rosasco, Jim Mutch, Andrea Tacchetti, and myself, developed it—and continue to refine it—within a context in which the quest ..."
Abstract
- Add to MetaCart
Unlike Athena, the new ventral stream theory foreshadowed in these pages did not spring fully-formed from the head of Zeus. We: primarily Tomaso Poggio, Fabio Anselmi, Lorenzo Rosasco, Jim Mutch, Andrea Tacchetti, and myself, developed it—and continue to refine it—within a context in which the questions considered in this dissertation loom large. Each of its four main chapters can be read independently, but a common thread runs through them. In other manuscripts—some already released, and some currently in preparation—we spin the same thread into the cloth of the new theory. Most of the chapters of this dissertation propose (or analyze) specific models designed to elucidate particular aspects of the ventral stream and the object recognition algorithm it implements. Some of them (chapters two and three) were mostly completed before we knew they were parts of a larger story. Whereas, the work of chapters four and five was undertaken more consciously as part of the larger theory’s development. A version of each chapter has appeared, or soon will appear, as a standalone article. Chapter one, the introduction, has two parts. It begins with a somewhat idiosyncratic
MIGNON, JURIE: RECONSTRUCTING FACES USING RBF REGRESSION 1 Reconstructing Faces from their Signatures using RBF Regression.
"... The increasing popularity of social networks raises critical issues regarding privacy and protection of personal information. One typical example – which is the motivation of the paper – is face images and face recognition, face recognition being ubiquitous on the web now. Assuming someone with bad ..."
Abstract
- Add to MetaCart
(Show Context)
The increasing popularity of social networks raises critical issues regarding privacy and protection of personal information. One typical example – which is the motivation of the paper – is face images and face recognition, face recognition being ubiquitous on the web now. Assuming someone with bad intentions steals a database containing face signatures, would it be possible to reconstruct the corresponding face images, revealing who was in the database? Would these reconstructed images be good enough to allow them to gain access via a face recognition system? This paper brings a contribution to this topic by proposing a face reconstruction algorithm, based on RBF-regression in eigenspace, which is able to reconstruct face images from their signatures (i.e. neither knowing the identity of the persons nor their true facial appearance). We show that in addition to being visually realistic, the images generated by the proposed method can fool a state-of-the-art face recognition algorithm. 1
Face Recognition Using Smoothed High-Dimensional Representation
"... Abstract. Recent studies have underlined the significance of high-dimensional features and their compression for face recognition. Partly motivated by these findings, we propose a novel method for building unsupervised face represen-tations based on binarized descriptors and efficient compression by ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. Recent studies have underlined the significance of high-dimensional features and their compression for face recognition. Partly motivated by these findings, we propose a novel method for building unsupervised face represen-tations based on binarized descriptors and efficient compression by soft assign-ment and unsupervised dimensionality reduction. For binarized descriptors, we consider Binarized Statistical Image Features (BSIF) which is a learning based descriptor computing a binary code for each pixel by thresholding the outputs of a linear projection between a local image patch and a set of independent basis vectors estimated from a training data set using independent component anal-ysis. In this work, we propose application specific learning to train a separate BSIF descriptor for each of the local face regions. Then, our method constructs a high-dimensional representation from an input face by collecting histograms of BSIF codes in a blockwise manner. Before dropping the dimension to get a more compressed representation, an important step in the pipeline of our method is soft feature assignment where the region histograms of the binarized codes are smoothed using kernel density estimation achieved by a simple and fast matrix-vector product. In detail, we provide a thorough evaluation on FERET and LFW benchmarks comparing our face representation method to the state-of-the-art in face recognition showing enhanced performance on FERET and promising re-sults on LFW. 1
