scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Class representative autoencoder for low resolution multi-spectral gender classification

TL;DR: This work attempts to address the challenging problem of gender classification in multi-spectral low resolution face images by proposing a robust Class Representative Autoencoder model, termed as AutoGen for the same.
Abstract: Gender is one of the most common attributes used to describe an individual. It is used in multiple domains such as human computer interaction, marketing, security, and demographic reports. Research has been performed to automate the task of gender recognition in constrained environment using face images, however, limited attention has been given to gender classification in unconstrained scenarios. This work attempts to address the challenging problem of gender classification in multi-spectral low resolution face images. We propose a robust Class Representative Autoencoder model, termed as AutoGen for the same. The proposed model aims to minimize the intra-class variations while maximizing the inter-class variations for the learned feature representations. Results on visible as well as near infrared spectrum data for different resolutions and multiple databases depict the efficacy of the proposed model. Comparative results with existing approaches and two commercial off-the-shelf systems further motivate the use of class representative features for classification.
Citations
More filters
Journal ArticleDOI
TL;DR: A comprehensive review of techniques incorporating ancillary information in the biometric recognition pipeline is presented in this paper, where the authors provide a comprehensive overview of the role of information fusion in biometrics.

151 citations

Proceedings ArticleDOI
TL;DR: Gender classification from multispectral periocular and iris images is a new topic on soft-biometric research and the fusion of features on different spectral images NIR and VIS allows improve the accuracy.
Abstract: Gender classification from multispectral periocular and iris images is a new topic on soft-biometric research The feature extracted from RGB images and Near Infrared Images shows complementary information independent of the spectrum of the images This paper shows that we canfusion these information improving the accuracy of gender classification Most gender classification methods reported in the literature has used images from face databases and all the features for classification purposes Experimental results suggest: (a) Features extracted in different scales can perform better than using only one feature in a single scale; (b) The periocular images performed better than iris images on VIS and NIR; c) The fusion of features on different spectral images NIR and VIS allows improve the accuracy; (c) The feature selection applied to NIR and VIS allows select relevant features and d) Our accuracy 90% is competitive with the state of the art

15 citations


Cites background from "Class representative autoencoder fo..."

  • ...Most of the papers in the literature for gender classification used images from face databases or cropped the periocular area from faces [15, 25, 24]....

    [...]

Journal ArticleDOI
TL;DR: A novel representation transfer learning approach is presented for prediction of GHBPs that is robust and accurate and may complement other wet lab based methods for identification of novelGHBPs.

6 citations

Journal ArticleDOI
TL;DR: This paper proposes a supervised auto-encoder with an addition classification layer on the representation layer to jointly predict targets and reconstruct inputs, so it can learn discriminative features specifically for classification tasks.
Abstract: Auto-encoders are unsupervised deep learning models, which try to learn hidden representations to reconstruct the inputs. While the learned representations are suitable for applications related to unsupervised reconstruction, they may not be optimal for classification. In this paper, we propose a supervised auto-encoder (SupAE) with an addition classification layer on the representation layer to jointly predict targets and reconstruct inputs, so it can learn discriminative features specifically for classification tasks. We stack several SupAE and apply a greedy layer-by-layer training approach to learn the stacked supervised auto-encoder (SSupAE). Then an adaptive weighted majority voting algorithm is proposed to fuse the prediction results of SupAE and the SSupAE, because each individual SupAE and the final SSupAE can both get the posterior probability information of samples belong to each class, we introduce Shannon entropy to measure the classification ability for different samples based on the posterior probability information, and assign high weight to sample with low entropy, thus more reasonable weights are assigned to different samples adaptively. Finally, we fuse the different results of classification layer with the proposed adaptive weighted majority voting algorithm to get the final recognition results. Experimental results on several classification datasets show that our model can learn discriminative features and improve the classification performance significantly.

1 citations


Cites background from "Class representative autoencoder fo..."

  • ...[22] presented a class representative auto-encoderwhich aimed at learning discriminative features in nature by incorporating inter-class and intra-class variations at the time of feature learning process....

    [...]

Journal ArticleDOI
TL;DR: In this paper, a method based on transfer learning has been proposed to recognize the face along with gender classification and facial expression recognition in NIR spectrum, which consists of three core components, i) training with small scale NIR images, ii) matching NIR-NIR images (homogeneous) and iii) classification.
Abstract: Visible face recognition systems are subjected to failure when recognizing the faces in unconstrained scenarios. So, recognizing faces under variable and low illumination conditions are more important since most of the security breaches happen during night time. Near Infrared (NIR) spectrum enables to acquire high quality images, even without any external source of light and hence it is a good method for solving the problem of illumination. Further, the soft biometric trait, gender classification and non verbal communication, facial expression recognition has also been addressed in the NIR spectrum. In this paper, a method has been proposed to recognize the face along with gender classification and facial expression recognitionin NIR spectrum. The proposed method is based on transfer learning and it consists of three core components, i) training with small scale NIR images ii) matching NIR-NIR images (homogeneous) and iii) classification. Training on NIR images produce features using transfer learning which has been pre-trained on large scale VIS face images. Next, matching is performed between NIR-NIR spectrum of both training and testing faces. Then it is classified using three, separate SVM classifiers, one for face recognition, the second one for gender classification and the third one for facial expression recognition. It has been observed that the method gives state-of-the-art accuracy on the publicly available, challenging, benchmark datasets CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS, PolyU, CBSR, IIT Kh and HITSZ for face recognition. Further, for gender classification the Oulu-CASIA NIR-VIS, PolyU,and IIT Kh has been analyzed and for facial expression the Oulu-CASIA NIR-VIS dataset has been analyzed.

1 citations

References
More filters
Journal ArticleDOI
28 Jul 2006-Science
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Abstract: High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such "autoencoder" networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.

16,717 citations

Journal ArticleDOI
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Abstract: We show how to use "complementary priors" to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modeled by long ravines in the free-energy landscape of the top-level associative memory, and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind.

15,055 citations


"Class representative autoencoder fo..." refers methods in this paper

  • ...In order to compare the performance of the proposed model with existing algorithms, comparison has been drawn with Autoencoders (AE) [26], Denoising Autoencoders (DAE) [27], Deep Belief Networks (DBN) [28], Discriminative Restricted Boltzmann Machine (DRBM) [29], and two CommercialOff-The-Shelf (COTS) systems, Luxand [30] and CNN-based Face++ [31]....

    [...]

  • ...While the accuracy of the proposed model reduces by less than 1.5%, the classification performance of DBN reduces by at most 17% (for CMU Multi-PIE)....

    [...]

Journal ArticleDOI
TL;DR: In this paper, a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates is described. But the detection performance is limited to 15 frames per second.
Abstract: This paper describes a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is the introduction of a new image representation called the “Integral Image” which allows the features used by our detector to be computed very quickly. The second is a simple and efficient classifier which is built using the AdaBoost learning algorithm (Freund and Schapire, 1995) to select a small number of critical visual features from a very large set of potential features. The third contribution is a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions. A set of experiments in the domain of face detection is presented. The system yields face detection performance comparable to the best previous systems (Sung and Poggio, 1998; Rowley et al., 1998; Schneiderman and Kanade, 2000; Roth et al., 2000). Implemented on a conventional desktop, face detection proceeds at 15 frames per second.

13,037 citations

Proceedings ArticleDOI
05 Jul 2008
TL;DR: This work introduces and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern.
Abstract: Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We introduce and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. This approach can be used to train autoencoders, and these denoising autoencoders can be stacked to initialize deep architectures. The algorithm can be motivated from a manifold learning and information theoretic perspective or from a generative model perspective. Comparative experiments clearly show the surprising advantage of corrupting the input of autoencoders on a pattern classification benchmark suite.

6,816 citations


"Class representative autoencoder fo..." refers methods in this paper

  • ...In order to compare the performance of the proposed model with existing algorithms, comparison has been drawn with Autoencoders (AE) [26], Denoising Autoencoders (DAE) [27], Deep Belief Networks (DBN) [28], Discriminative Restricted Boltzmann Machine (DRBM) [29], and two CommercialOff-The-Shelf (COTS) systems, Luxand [30] and CNN-based Face++ [31]....

    [...]

Journal Article
TL;DR: Denoising autoencoders as mentioned in this paper are trained locally to denoise corrupted versions of their inputs, which is a straightforward variation on the stacking of ordinary autoencoder.
Abstract: We explore an original strategy for building deep networks, based on stacking layers of denoising autoencoders which are trained locally to denoise corrupted versions of their inputs. The resulting algorithm is a straightforward variation on the stacking of ordinary autoencoders. It is however shown on a benchmark of classification problems to yield significantly lower classification error, thus bridging the performance gap with deep belief networks (DBN), and in several cases surpassing it. Higher level representations learnt in this purely unsupervised fashion also help boost the performance of subsequent SVM classifiers. Qualitative experiments show that, contrary to ordinary autoencoders, denoising autoencoders are able to learn Gabor-like edge detectors from natural image patches and larger stroke detectors from digit images. This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.

4,814 citations

Trending Questions (1)
What are the different types of gender codes that can be used in SPSS?

The provided paper does not mention anything about SPSS or different types of gender codes.