Conrad Sanderson

Shadow detection: A survey and comparative evaluation of recent methods

This paper presents a survey and a comparative evaluation of recent techniques for moving cast shadow detection. We identify shadow removal as a critical step for improving object detection and tracking. The survey covers methods published during the last decade, and places them in a feature-based taxonomy comprised of four categories: chromacity, physical, geometry and textures. A selection of prominent methods across the categories is compared in terms of quantitative performance measures (shadow detection and discrimination rates, colour desaturation) as well as qualitative observations. Furthermore, we propose the use of tracking performance as an unbiased approach for determining the practical usefulness of shadow detection methods. The evaluation indicates that all shadow detection approaches make different contributions and all have individual strength and weaknesses. Out of the selected methods, the geometry-based technique has strict assumptions and is not generalisable to various environments, but it is a straightforward choice when the objects of interest are easy to model and their shadows have different orientation. The chromacity based method is the fastest to implement and run, but it is sensitive to noise and less effective in low saturated scenes. The physical method improves upon the accuracy of the chromacity method by adapting to local shadow models, but fails when the spectral properties of the objects are similar to that of the background. The small-region texture based method is especially robust for pixels whose neighbourhood is textured, but may take longer to implement and is the most computationally expensive. The large-region texture based method produces the most accurate results, but has a significant computational load due to its multiple processing steps.

Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching

A convenient way of dealing with image sets is to represent them as points on Grassmannian manifolds. While several recent studies explored the applicability of discriminant analysis on such manifolds, the conventional formalism of discriminant analysis suffers from not considering the local structure of the data. We propose a discriminant analysis approach on Grassmannian manifolds, based on a graph-embedding framework. We show that by introducing within-class and between-class similarity graphs to characterise intra-class compactness and inter-class separability, the geometrical structure of data can be exploited. Experiments on several image datasets (PIE, BANCA, MoBo, ETH-80) show that the proposed algorithm obtains considerable improvements in discrimination accuracy, in comparison to three recent methods: Grassmann Discriminant Analysis (GDA), Kernel GDA, and the kernel version of Affine Hull Image Set Distance. We further propose a Grassmannian kernel, based on canonical correlation between subspaces, which can increase discrimination accuracy when used in combination with previous Grassmannian kernels.

Fast features for face authentication under illumination direction changes

In this letter we propose a facial feature extraction technique which utilizes polynomial coefficients derived from 2D Discrete Cosine Transform (DCT) coefficients obtained from horizontally and vertically neighbouring blocks. Face authentication results on the VidTIMIT database suggest that the proposed feature set is superior (in terms of robustness to illumination changes and discrimination ability) to features extracted using four popular methods: Principal Component Analysis (PCA), PCA with histogram equalization pre-processing, 2D DCT and 2D Gabor wavelets; the results also suggest that histogram equalization pre-processing increases the error rate and offers no help against illumination changes. Moreover, the proposed feature set is over 80 times faster to compute than features based on Gabor wavelets. Further experiments on the Weizmann database also show that the proposed approach is more robust than 2D Gabor wavelets and 2D DCT coefficients.

Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition

In video based face recognition, face images are typically captured over multiple frames in uncontrolled conditions, where head pose, illumination, shadowing, motion blur and focus change over the sequence. Additionally, inaccuracies in face localisation can also introduce scale and alignment variations. Using all face images, including images of poor quality, can actually degrade face recognition performance. While one solution it to use only the ‘best’ of images, current face selection techniques are incapable of simultaneously handling all of the abovementioned issues. We propose an efficient patch-based face image quality assessment algorithm which quantifies the similarity of a face image to a probabilistic face model, representing an ‘ideal’ face. Image characteristics that affect recognition are taken into account, including variations in geometric alignment (shift, rotation and scale), sharpness, head pose and cast shadows. Experiments on FERET and PIE datasets show that the proposed algorithm is able to identify images which are simultaneously the most frontal, aligned, sharp and well illuminated. Further experiments on a new video surveillance dataset (termed ChokePoint) show that the proposed method provides better face subsets than existing face selection techniques, leading to significant improvements in recognition accuracy.

Identity verification using speech and face information

This article first provides an overview of important concept s in the field of information fusion, followed by a review of milestones in audio-visual person identification and verifi cation. Several recent adaptive and non-adaptive techniques for reaching the verification decision (i.e., to accept or re ject the claimant), based on speech and face information, are then evaluated in clean and noisy audio conditions on a common database; it is shown that in clean conditions most of the non-adaptive approaches provide similar performance and in noisy conditions most exhibit a severe deterioration i n performance; it is also shown that current adaptive approac hes are either inadequate or utilize restrictive assumptio ns. A new category of classifiers is then introduced, where the de cision boundary is fixed but constructed to take into account how the distributions of opinions are likely to change due to noisy conditions; compared to a previously proposed adaptive approach, the proposed classifiers do not make a direct assum ption about the type of noise that causes the mismatch between training and testing conditions.

RcppArmadillo: Accelerating R with high-performance C++ linear algebra

The R statistical environment and language has demonstrated particular strengths for interactive development of statistical algorithms, as well as data modelling and visualisation. Its current implementation has an interpreter at its core which may result in a performance penalty in comparison to directly executing user algorithms in the native machine code of the host CPU. In contrast, the C++ language has no built-in visualisation capabilities, handling of linear algebra or even basic statistical algorithms; however, user programs are converted to high-performance machine code, ahead of execution. A new method avoids possible speed penalties in R by using the Rcpp extension package in conjunction with the Armadillo C++ matrix library. In addition to the inherent performance advantages of compiled code, Armadillo provides an easy-to-use template-based meta-programming framework, allowing the automatic pooling of several linear algebra operations into one, which in turn can lead to further speedups. With the aid of Rcpp and Armadillo, conversion of linear algebra centred algorithms from R to C++ becomes straightforward. The algorithms retain the overall structure as well as readability, all while maintaining a bidirectional link with the host R environment. Empirical timing comparisons of R and C++ implementations of a Kalman filtering algorithm indicate a speedup of several orders of magnitude.

Short Text Authorship Attribution via Sequence Kernels, Markov Chains and Author Unmasking: An Investigation

We present an investigation of recently proposed character and word sequence kernels for the task of authorship attribution based on relatively short texts. Performance is compared with two corresponding probabilistic approaches based on Markov chains. Several configurations of the sequence kernels are studied on a relatively large dataset (50 authors), where each author covered several topics. Utilising Moffat smoothing, the two probabilistic approaches obtain similar performance, which in turn is comparable to that of character sequence kernels and is better than that of word sequence kernels. The results further suggest that when using a realistic setup that takes into account the case of texts which are not written by any hypothesised authors, the amount of training material has more influence on discrimination performance than the amount of test material. Moreover, we show that the recently proposed author unmasking approach is less useful when dealing with short texts.

User authentication via adapted statistical models of face images

It has been previously demonstrated that systems based on local features and relatively complex statistical models, namely, one-dimensional (1-D) hidden Markov models (HMMs) and pseudo-two-dimensional (2-D) HMMs, are suitable for face recognition. Recently, a simpler statistical model, namely, the Gaussian mixture model (GMM), was also shown to perform well. In much of the literature devoted to these models, the experiments were performed with controlled images (manual face localization, controlled lighting, background, pose, etc). However, a practical recognition system has to be robust to more challenging conditions. In this article we evaluate, on the relatively difficult BANCA database, the performance, robustness and complexity of GMM and HMM-based approaches, using both manual and automatic face localization. We extend the GMM approach through the use of local features with embedded positional information, increasing performance without sacrificing its low complexity. Furthermore, we show that the traditionally used maximum likelihood (ML) training approach has problems estimating robust model parameters when there is only a few training images available. Considerably more precise models can be obtained through the use of Maximum a posteriori probability (MAP) training. We also show that face recognition techniques which obtain good performance on manually located faces do not necessarily obtain good performance on automatically located faces, indicating that recognition techniques must be designed from the ground up to handle imperfect localization. Finally, we show that while the pseudo-2-D HMM approach has the best overall performance, authentication time on current hardware makes it impractical. The best tradeoff in terms of authentication time, robustness and discrimination performance is achieved by the extended GMM approach.

Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture

A robust and efficient anomaly detection technique is proposed, capable of dealing with crowded scenes where traditional tracking based approaches tend to fail. Initial foreground segmentation of the input frames confines the analysis to foreground objects and effectively ignores irrelevant background dynamics. Input frames are split into non-overlapping cells, followed by extracting features based on motion, size and texture from each cell. Each feature type is independently analysed for the presence of an anomaly. Unlike most methods, a refined estimate of object motion is achieved by computing the optical flow of only the foreground pixels. The motion and size features are modelled by an approximated version of kernel density estimation, which is computationally efficient even for large training datasets. Texture features are modelled by an adaptively grown code-book, with the number of entries in the codebook selected in an online fashion. Experiments on the recently published UCSD Anomaly Detection dataset show that the proposed method obtains considerably better results than three recent approaches: MPPCA, social force, and mixture of dynamic textures (MDT). The proposed method is also several orders of magnitude faster than MDT, the next best performing method.

Comparison of MLP and GMM classifiers for face verification on XM2VTS

We compare two classifier approaches, namely classifiers based on Multi Layer Perceptrons (MLPs) and Gaussian Mixture Models (GMMs), for use in a face verification system. The comparison is carried out in terms of performance, robustness and practicability. Apart from structural differences, the two approaches use different training criteria; the MLP approach uses a discriminative criterion, while the GMM approach uses a combination of Maximum Likelihood (ML) and Maximum a Posteriori (MAP) criteria. Experiments on the XM2VTS database show that for low resolution faces the MLP approach has slightly lower error rates than the GMM approach; however, the GMM approach easily outperforms the MLP approach for high resolution faces and is significantly more robust to imperfectly located faces. The experiments also show that the computational requirements of the GMM approach can be significantly smaller than the MLP approach at a cost of small loss of performance.