The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

Sample complexity results from computational learning theory, when applied to neural network learning for pattern classification problems, suggest that for good generalization performance the number of training examples should grow at least linearly with the number of adjustable parameters in the network. Results in this paper show that if a large neural network is used for a pattern classification problem and the learning algorithm finds a network with small weights that has small squared error on the training patterns, then the generalization performance depends on the size of the weights rather than the number of weights. For example, consider a two-layer feedforward network of sigmoid units, in which the sum of the magnitudes of the weights associated with each unit is bounded by A and the input dimension is n. We show that the misclassification probability is no more than a certain error estimate (that is related to squared error on the training set) plus A3 √((log n)/m) (ignoring log A and log m factors), where m is the number of training patterns. This may explain the generalization performance of neural networks, particularly when the number of training examples is considerably smaller than the number of weights. It also supports heuristics (such as weight decay and early stopping) that attempt to keep the weights small during training. The proof techniques appear to be useful for the analysis of other pattern classifiers: when the input domain is a totally bounded metric space, we use the same approach to give upper bounds on misclassification probability for classifiers with decision boundaries that are far from the training examples.

An approach to statistical lip modelling for speaker identification via chromatic feature extraction

This paper presents a novel technique for the tracking of moving lips for the purpose of speaker identification. In our system, a model of the lip contour is formed directly from chromatic information in the lip region. Iterative refinement of contour point estimates is not required. Colour features are extracted from the lips via concatenated profiles taken around the lip contour. Reduction of order in lip features is obtained via principal component analysis (PCA) followed by linear discriminant analysis (LDA). Statistical speaker models are built from the lip features based on the Gaussian mixture model (GMM). Identification experiments performed on the M2VTS¹ database, show encouraging results

Sparse temporal representations for facial expression recognition

In automatic facial expression recognition, an increasing number of techniques had been proposed for in the literature that exploits the temporal nature of facial expressions. As all facial expressions are known to evolve over time, it is crucially important for a classifier to be capable of modelling their dynamics. We establish that the method of sparse representation (SR) classifiers proves to be a suitable candidate for this purpose, and subsequently propose a framework for expression dynamics to be efficiently incorporated into its current formulation. We additionally show that for the SR method to be applied effectively, then a certain threshold on image dimensionality must be enforced (unlike in facial recognition problems). Thirdly, we determined that recognition rates may be significantly influenced by the size of the projection matrix \Phi. To demonstrate these, a battery of experiments had been conducted on the CK+ dataset for the recognition of the seven prototypic expressions - anger, contempt, disgust, fear, happiness, sadness and surprise - and comparisons have been made between the proposed temporal-SR against the static-SR framework and state-of-the-art support vector machine.

On the behaviour of higher-order spectral features for object recognition in the presence of various types of noise

This paper presents results on the robustness of higher-order spectral features to Gaussian, Rayleigh, and uniform distributed noise. Based on cluster plots and accuracy results for various signal to noise conditions, the higher-order spectral features are shown to be better than moment invariant features.

Acoustic component detection for automatic species recognition in environmental monitoring

Automatic species recognition plays an important role in assisting ecologists to monitor the environment. One critical issue in this research area is that software developers need prior knowledge of specific targets people are interested in to build templates for these targets. This paper proposes a novel approach for automatic species recognition based on generic knowledge about acoustic events to detect species. Acoustic component detection is the most critical and fundamental part of this proposed approach. This paper gives clear definitions of acoustic components and presents three clustering algorithms for detecting four acoustic components in sound recordings; whistles, clicks, slurs, and blocks. The experiment result demonstrates that these acoustic component recognisers have achieved high precision and recall rate.

Integrating collaborative filtering and search-based techniques for personalized online product recommendation

The existing Collaborative Filtering (CF) technique that has been widely applied by e-commerce sites requires a large amount of ratings data to make meaningful recommendations. It is not directly applicable for recommending products that are not frequently purchased by users, such as cars and houses, as it is difficult to collect rating data for such products from the users. Many of the e-commerce sites for infrequently purchased products are still using basic search-based techniques whereby the products that match with the attributes given in the target user's query are retrieved and recommended to the user. However, search-based recommenders cannot provide personalized recommendations. For different users, the recommendations will be the same if they provide the same query regardless of any difference in their online navigation behaviour. This paper proposes to integrate collaborative filtering and search-based techniques to provide personalized recommendations for infrequently purchased products. Two different techniques are proposed, namely CFRRobin and CFAg Query. Instead of using the target user's query to search for products as normal search based systems do, the CFRRobin technique uses the products in which the target user's neighbours have shown interest as queries to retrieve relevant products, and then recommends to the target user a list of products by merging and ranking the returned products using the Round Robin method. The CFAg Query technique uses the products that the user's neighbours have shown interest in to derive an aggregated query, which is then used to retrieve products to recommend to the target user. Experiments conducted on a real e-commerce dataset show that both the proposed techniques CFRRobin and CFAg Query perform better than the standard Collaborative Filtering (CF) and the Basic Search (BS) approaches, which are widely applied by the current e-commerce applications. The CFRRobin and CFAg Query approaches also outperform the e- isting query expansion (QE) technique that was proposed for recommending infrequently purchased products.

Feature-domain super-resolution framework for gabor-based face and iris recognition

The low resolution of images has been one of the major limitations in recognising humans from a distance using their biometric traits, such as face and iris. Superresolution has been employed to improve the resolution and the recognition performance simultaneously, however the majority of techniques employed operate in the pixel domain, such that the biometric feature vectors are extracted from a super-resolved input image. Feature-domain superresolution has been proposed for face and iris, and is shown to further improve recognition performance by capitalising on direct super-resolving the features which are used for recognition. However, current feature-domain superresolution approaches are limited to simple linear features such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), which are not the most discriminant features for biometrics. Gabor-based features have been shown to be one of the most discriminant features for biometrics including face and iris. This paper proposes a framework to conduct super-resolution in the non-linear Gabor feature domain to further improve the recognition performance of biometric systems. Experiments have confirmed the validity of the proposed approach, demonstrating superior performance to existing linear approaches for both face and iris biometrics.

Improved facial expression recognition via uni-hyperplane classification

Large margin learning approaches, such as support vector machines (SVM), have been successfully applied to numerous classification tasks, especially for automatic facial expression recognition. The risk of such approaches however, is their sensitivity to large margin losses due to the influence from noisy training examples and outliers which is a common problem in the area of affective computing (i.e., manual coding at the frame level is tedious so coarse labels are normally assigned). In this paper, we leverage the relaxation of the parallel-hyperplanes constraint and propose the use of modified correlation filters (MCF). The MCF is similar in spirit to SVMs and correlation filters, but with the key difference of optimizing only a single hyperplane. We demonstrate the superiority of MCF over current techniques on a battery of experiments.

HMM triangle relative entropy concepts in sequential change detection applied to vision-based dim target manoeuvre detection

The quick detection of abrupt (unknown) parameter changes in an observed hidden Markov model (HMM) is important in several applications. Motivated by the recent application of relative entropy concepts in the robust sequential change detection problem (and the related model selection problem), this paper proposes a sequential unknown change detection algorithm based on a relative entropy based HMM parameter estimator. Our proposed approach is able to overcome the lack of knowledge of post-change parameters, and is illustrated to have similar performance to the popular cumulative sum (CUSUM) algorithm (which requires knowledge of the post-change parameter values) when examined, on both simulated and real data, in a vision-based aircraft manoeuvre detection problem.

A toolbox for animal call recognition

Monitoring the natural environment is increasingly important as habit degradation and climate change reduce theworld’s biodiversity.We have developed software tools and applications to assist ecologists with the collection and analysis of acoustic data at large spatial and temporal scales.One of our key objectives is automated animal call recognition, and our approach has three novel attributes. First, we work with raw environmental audio, contaminated by noise and artefacts and containing calls that vary greatly in volume depending on the animal’s proximity to the microphone. Second, initial experimentation suggested that no single recognizer could dealwith the enormous variety of calls. Therefore, we developed a toolbox of generic recognizers to extract invariant features for each call type. Third, many species are cryptic and offer little data with which to train a recognizer. Many popular machine learning methods require large volumes of training and validation data and considerable time and expertise to prepare. Consequently we adopt bootstrap techniques that can be initiated with little data and refined subsequently. In this paper, we describe our recognition tools and present results for real ecological problems.

Multiple cameras for audio-visual speech recognition in an automotive environment

Audio-visualspeechrecognition, or the combination of visual lip-reading with traditional acoustic speechrecognition, has been previously shown to provide a considerable improvement over acoustic-only approaches in noisy environments, such as that present in an automotive cabin. The research presented in this paper will extend upon the established audio-visualspeechrecognition literature to show that further improvements in speechrecognition accuracy can be obtained when multiple frontal or near-frontal views of a speaker's face are available. A series of visualspeechrecognition experiments using a four-stream visual synchronous hidden Markov model (SHMM) are conducted on the four-camera AVICAR automotiveaudio-visualspeech database. We study the relative contribution between the side and central orientated cameras in improving visualspeechrecognition accuracy. Finally combination of the four visual streams with a single audio stream in a five-stream SHMM demonstrates a relative improvement of over 56% in word recognition accuracy when compared to the acoustic-only approach in the noisiest conditions of the AVICAR database.

Timed and Probabilistic Automata for Automatic Animal Call Recognition

Automatic Call Recognition is vital for environmental monitoring. Patten recognition has been applied in automatic species recognition for years. However, few studies have applied formal syntactic methods to species call structure analysis. This paper introduces a novel method to adopt timed and probabilistic automata in automatic species recognition based upon acoustic components as the primitives. We demonstrate this through one kind of birds in Australia: Eastern Yellow Robin.

Kernel analysis on Grassmann manifolds for action recognition

Modelling video sequences by subspaces has recently shown promise for recognising human actions. Subspaces are able to accommodate the effects of various image variations and can capture the dynamic properties of actions. Subspaces form a non-Euclidean and curved Riemannian manifold known as a Grassmann manifold. Inference on manifold spaces usually is achieved by embedding the manifolds in higher dimensional Euclidean spaces. In this paper, we instead propose to embed the Grassmann manifolds into reproducing kernel Hilbert spaces and then tackle the problem of discriminant analysis on such manifolds. To achieve efficient machinery, we propose graph-based local discriminant analysis that utilises within-class and between-class similarity graphs to characterise intra-class compactness and inter-class separability, respectively. Experiments on KTH, UCF Sports, and Ballet datasets show that the proposed approach obtains marked improvements in discrimination accuracy in comparison to several state-of-the-art methods, such as the kernel version of affine hull image-set distance, tensor canonical correlation analysis, spatial-temporal words and hierarchy of discriminative space-time neighbourhood features.

Improved foreground detection via block-based classifier cascade with probabilistic decision integration

Background subtraction is a fundamental low-level processing task in numerous computer vision applications. The vast majority of algorithms process images on a pixel-by-pixel basis, where an independent decision is made for each pixel. A general limitation of such processing is that rich contextual information is not taken into account. We propose a block-based method capable of dealing with noise, illumination variations, and dynamic backgrounds, while still obtaining smooth contours of foreground objects. Specifically, image sequences are analyzed on an overlapping block-by-block basis. A low-dimensional texture descriptor obtained from each block is passed through an adaptive classifier cascade, where each stage handles a distinct problem. A probabilistic foreground mask generation approach then exploits block overlaps to integrate interim block-level decisions into final pixel-level foreground segmentation. Unlike many pixel-based methods, ad-hoc postprocessing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed approach obtains on average better results (both qualitatively and quantitatively) than several prominent methods. We furthermore propose the use of tracking performance as an unbiased approach for assessing the practical usefulness of foreground segmentation methods, and show that the proposed approach leads to considerable improvements in tracking accuracy on the CAVIAR dataset.