Local inter-session variability modelling for object classification

Object classification is plagued by the issue of session variation. Session variation describes any variation that makes one instance of an object look different to another, for instance due to pose or illumination variation. Recent work in the challenging task of face verification has shown that session variability modelling provides a mechanism to overcome some of these limitations. However, for computer vision purposes, it has only been applied in the limited setting of face verification. In this paper we propose a local region based intersession variability (ISV) modelling approach, and apply it to challenging real-world data. We propose a region based session variability modelling approach so that local session variations can be modelled, termed Local ISV. We then demonstrate the efficacy of this technique on a challenging real-world fish image database which includes images taken underwater, providing significant real-world session variations. This Local ISV approach provides a relative performance improvement of, on average, 23% on the challenging MOBIO, Multi-PIE and SCface face databases. It also provides a relative performance improvement of 35% on our challenging fish image dataset.

Random projections on manifolds of symmetric positive definite matrices for image classification

Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance. Taking into account manifold geometry is typically done via (1) embedding the manifolds in tangent spaces, or (2) embedding into Reproducing Kernel Hilbert Spaces (RKHS). While embedding into tangent spaces allows the use of existing Euclidean-based learning algorithms, manifold shape is only approximated which can cause loss of discriminatory information. The RKHS approach retains more of the manifold structure, but may require non-trivial effort to kernelise Euclidean-based learning algorithms. In contrast to the above approaches, in this paper we offer a novel solution that allows SPD matrices to be used with unmodified Euclidean-based learning algorithms, with the true manifold shape well-preserved. Specifically, we propose to project SPD matrices using a set of random projection hyperplanes over RKHS into a random projection space, which leads to representing each matrix as a vector of projection coefficients. Experiments on face recognition, person re-identification and texture classification show that the proposed approach outperforms several recent methods, such as Tensor Sparse Coding, Histogram Plus Epitome, Riemannian Locality Preserving Projection and Relational Divergence Classification.

Dictionary learning and sparse coding on Grassmann manifolds : an extrinsic solution

Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry. In this paper we explore sparse dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds. To this end, we propose to embed Grassmann manifolds into the space of symmetric matrices by an isometric mapping, which enables us to devise a closed-form solution for updating a Grassmann dictionary, atom by atom. Furthermore, to handle non-linearity in data, we propose a kernelised version of the dictionary learning algorithm. Experiments on several classification tasks (face recognition, action recognition, dynamic texture classification) show that the proposed approach achieves considerable improvements in discrimination accuracy, in comparison to state-of-the-art methods such as kernelised Affine Hull Method and graph-embedding Grassmann discriminant analysis.

Improving deep convultional neural networks with unsupervised feature learning

The latest generation of Deep Convolutional Neural Networks (DCNN) have dramatically advanced challenging computer vision tasks, especially in object detection and object classification, achieving state-of-the-art performance in several computer vision tasks including text recognition, sign recognition, face recognition and scene understanding. The depth of these supervised networks has enabled learning deeper and hierarchical representation of features. In parallel, unsupervised deep learning such as Convolutional Deep Belief Network (CDBN) has also achieved state-of-the-art in many computer vision tasks. However, there is very limited research on jointly exploiting the strength of these two approaches. In this paper, we investigate the learning capability of both methods. We compare the output of individual layers and show that many learnt filters and outputs of the corresponding level layer are almost similar for both approaches. Stacking the DCNN on top of unsupervised layers or replacing layers in the DCNN with the corresponding learnt layers in the CDBN can improve the recognition/classification accuracy and training computational expense. We demonstrate the validity of the proposal on ImageNet dataset.

A flexible hierarchical approach for facial age estimation based on multiple features

Age estimation from facial images is increasingly receiving attention to solve age-based access control, age-adaptive targeted marketing, amongst other applications. Since even humans can be induced in error due to the complex biological processes involved, finding a robust method remains a research challenge today. In this paper, we propose a new framework for the integration of Active Appearance Models (AAM), Local Binary Patterns (LBP), Gabor wavelets (GW) and Local Phase Quantization (LPQ) in order to obtain a highly discriminative feature representation which is able to model shape, appearance, wrinkles and skin spots. In addition, this paper proposes a novel flexible hierarchical age estimation approach consisting of a multi-class Support Vector Machine (SVM) to classify a subject into an age group followed by a Support Vector Regression (SVR) to estimate a specific age. The errors that may happen in the classification step, caused by the hard boundaries between age classes, are compensated in the specific age estimation by a flexible overlapping of the age ranges. The performance of the proposed approach was evaluated on FG-NET Aging and MORPH Album 2 datasets and a mean absolute error (MAE) of 4.50 and 5.86 years was achieved respectively. The robustness of the proposed approach was also evaluated on a merge of both datasets and a MAE of 5.20 years was achieved. Furthermore, we have also compared the age estimation made by humans with the proposed approach and it has shown that the machine outperforms humans. The proposed approach is competitive with current state-of-the-art and it provides an additional robustness to blur, lighting and expression variance brought about by the local phase features.

Beyond Gauss: Image-set matching on the Riemannian manifold of PDFs

State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution. Here, we propose to go beyond these representations and model image-sets as probability distribution functions (PDFs) using kernel density estimators. To compare and match image-sets, we exploit Csiszar´ f-divergences, which bear strong connections to the geodesic distance defined on the space of PDFs, i.e., the statistical manifold. Furthermore, we introduce valid positive definite kernels on the statistical manifold, which let us make use of more powerful classification schemes to match image-sets. Finally, we introduce a supervised dimensionality reduction technique that learns a latent space where f-divergences reflect the class labels of the data. Our experiments on diverse problems, such as video-based face recognition and dynamic texture classification, evidence the benefits of our approach over the state-of-the-art image-set matching methods.

Deeper and wider fully convolutional network coupled with conditional random fields for scene labeling

Deep convolutional neural networks (DCNNs) have been employed in many computer vision tasks with great success due to their robustness in feature learning. One of the advantages of DCNNs is their representation robustness to object locations, which is useful for object recognition tasks. However, this also discards spatial information, which is useful when dealing with topological information of the image (e.g. scene labeling, face recognition). In this paper, we propose a deeper and wider network architecture to tackle the scene labeling task. The depth is achieved by incorporating predictions from multiple early layers of the DCNN. The width is achieved by combining multiple outputs of the network. We then further refine the parsing task by adopting graphical models (GMs) as a post-processing step to incorporate spatial and contextual information into the network. The new strategy for a deeper, wider convolutional network coupled with graphical models has shown promising results on the PASCAL-Context dataset.

Covariance profiles: a signature representation for object sets

We consider the problem of extracting a signature representation of similar entities employing covariance descriptors. Covariance descriptors can efficiently represent objects and are robust to scale and pose changes. We posit that covariance descriptors corresponding to similar objects share a common geometrical structure which can be extracted through joint diagonalization. We term this diagonalizing matrix as the Covariance Profile (CP). CP can be used to measure the distance of a novel object to an object set through the diagonality measure. We demonstrate how CP can be employed on images as well as for videos, for applications such as face recognition and object-track clustering.

A NEAR OPTIMAL PROJECTION FOR SPARSE REPRESENTATION BASED CLASSIFICATION

Sparse representation based classification (SRC) is one of the most successful methods that has been developed in recent times for face recognition. Optimal projection for Sparse representation based classification (OPSRC)1] provides a dimensionality reduction map that is supposed to give optimum performance for SRC framework. However, the computational complexity involved in this method is too high. Here, we propose a new projection technique using the data scatter matrix which is computationally superior to the optimal projection method with comparable classification accuracy with respect OPSRC. The performance of the proposed approach is benchmarked with various publicly available face database.

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

利用本征脸方法减少冷原子云吸收成像照片中的干涉条纹

本征脸方法是广泛应用于人脸识别的一种图像处理方法，本文将其引入到原子芯片上囚禁的冷原子云吸收成像照片的图像处理中，以减少其中的干涉条纹，增加信噪比。本文首先介绍了吸收成像照片的标准处理方法以及干涉条纹的产生原因，由于参考照片和吸收成像照片中的干涉条纹会发生随机的相对变化，处理后干涉条纹难以消除。和标准的处理方法相比，本征脸方法不是使用1张而是50张参考照片，利用这些照片重构出一张新的参考照片，这张照片比那50张中的任何一张都更近似于吸收成像照片，因此和只使用1张参考照片相比，处理之后的干涉条纹对比度明显降

Decomposição aleatória de matrizes aplicada ao reconhecimento de faces

Métodos estocásticos oferecem uma poderosa ferramenta para a execução da compressão de dados e decomposições de matrizes. O método estocástico para decomposição de matrizes estudado utiliza amostragem aleatória para identificar um subespaço que captura a imagem de uma matriz de forma aproximada, preservando uma parte de sua informação essencial. Estas aproximações compactam a informação possibilitando a resolução de problemas práticos de maneira eficiente. Nesta dissertação é calculada uma decomposição em valores singulares (SVD) utilizando técnicas estocásticas. Esta SVD aleatória é empregada na tarefa de reconhecimento de faces. O reconhecimento de faces funciona de forma a projetar imagens de faces sobre um espaço de características que melhor descreve a variação de imagens de faces conhecidas. Estas características significantes são conhecidas como autofaces, pois são os autovetores de uma matriz associada a um conjunto de faces. Essa projeção caracteriza aproximadamente a face de um indivíduo por uma soma ponderada das autofaces características. Assim, a tarefa de reconhecimento de uma nova face consiste em comparar os pesos de sua projeção com os pesos da projeção de indivíduos conhecidos. A análise de componentes principais (PCA) é um método muito utilizado para determinar as autofaces características, este fornece as autofaces que representam maior variabilidade de informação de um conjunto de faces. Nesta dissertação verificamos a qualidade das autofaces obtidas pela SVD aleatória (que são os vetores singulares à esquerda de uma matriz contendo as imagens) por comparação de similaridade com as autofaces obtidas pela PCA. Para tanto, foram utilizados dois bancos de imagens, com tamanhos diferentes, e aplicadas diversas amostragens aleatórias sobre a matriz contendo as imagens.

Análise colorimétrica de faces humanas: uma abordagem para auxílio ao reconhecimento de imagens

A quantificação colorimétrica da pele do rosto humano apresenta uma grande dispersão de valores. Esta dispersão varia de acordo com o espaço de cor (HSV ou YCbCr) adotado para a análise e quanto menor a dispersão mais adequado é o espaço ao reconhecimento facial. O objetivo deste trabalho é analisar a distribuição estatística da colorimetria de imagens de rostos digitalizadas. A análise poderá dizer se as coordenadas de cor, tais como saturação, matiz e valor podem auxiliar em técnicas de reconhecimento de faces. Como resultado da análise, espera-se concluir qual dos sistemas de coordenadas de cor (HSV ou YCbCr) é o mais adequado à aplicações em reconhecimento facial. Os resultados obtidos serão apresentados com fundamentação no design da informação. O grande número de amostras fotográficas disponíveis para análise (530) e o correto equilíbrio de iluminação, contraste e temperatura de cor constituem o principal diferencial desse trabalho.