Evaluation of texture and geometry for dimensional facial expression recognition

Facial expression recognition (FER) algorithms mainly focus on classification into a small discrete set of emotions or representation of emotions using facial action units (AUs). Dimensional representation of emotions as continuous values in an arousal-valence space is relatively less investigated. It is not fully known whether fusion of geometric and texture features will result in better dimensional representation of spontaneous emotions. Moreover, the performance of many previously proposed approaches to dimensional representation has not been evaluated thoroughly on publicly available databases. To address these limitations, this paper presents an evaluation framework for dimensional representation of spontaneous facial expressions using texture and geometric features. SIFT, Gabor and LBP features are extracted around facial fiducial points and fused with FAP distance features. The CFS algorithm is adopted for discriminative texture feature selection. Experimental results evaluated on the publicly accessible NVIE database demonstrate that fusion of texture and geometry does not lead to a much better performance than using texture alone, but does result in a significant performance improvement over geometry alone. LBP features perform the best when fused with geometric features. Distributions of arousal and valence for different emotions obtained via the feature extraction process are compared with those obtained from subjective ground truth values assigned by viewers. Predicted valence is found to have a more similar distribution to ground truth than arousal in terms of covariance or Bhattacharya distance, but it shows a greater distance between the means.

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.

Towards spontaneous facial expression recognition in real-world video

Facial expression is an important channel of human social communication. Facial expression recognition (FER) aims to perceive and understand emotional states of humans based on information in the face. Building robust and high performance FER systems that can work in real-world video is still a challenging task, due to the various unpredictable facial variations and complicated exterior environmental conditions, as well as the difficulty of choosing a suitable type of feature descriptor for extracting discriminative facial information. Facial variations caused by factors such as pose, age, gender, race and occlusion, can exert profound influence on the robustness, while a suitable feature descriptor largely determines the performance. Most present attention on FER has been paid to addressing variations in pose and illumination. No approach has been reported on handling face localization errors and relatively few on overcoming facial occlusions, although the significant impact of these two variations on the performance has been proved and highlighted in many previous studies. Many texture and geometric features have been previously proposed for FER. However, few comparison studies have been conducted to explore the performance differences between different features and examine the performance improvement arisen from fusion of texture and geometry, especially on data with spontaneous emotions. The majority of existing approaches are evaluated on databases with posed or induced facial expressions collected in laboratory environments, whereas little attention has been paid on recognizing naturalistic facial expressions on real-world data. This thesis investigates techniques for building robust and high performance FER systems based on a number of established feature sets. It comprises of contributions towards three main objectives: (1) Robustness to face localization errors and facial occlusions. An approach is proposed to handle face localization errors and facial occlusions using Gabor based templates. Template extraction algorithms are designed to collect a pool of local template features and template matching is then performed to covert these templates into distances, which are robust to localization errors and occlusions. (2) Improvement of performance through feature comparison, selection and fusion. A comparative framework is presented to compare the performance between different features and different feature selection algorithms, and examine the performance improvement arising from fusion of texture and geometry. The framework is evaluated for both discrete and dimensional expression recognition on spontaneous data. (3) Evaluation of performance in the context of real-world applications. A system is selected and applied into discriminating posed versus spontaneous expressions and recognizing naturalistic facial expressions. A database is collected from real-world recordings and is used to explore feature differences between standard database images and real-world images, as well as between real-world images and real-world video frames. The performance evaluations are based on the JAFFE, CK, Feedtum, NVIE, Semaine and self-collected QUT databases. The results demonstrate high robustness of the proposed approach to the simulated localization errors and occlusions. Texture and geometry have different contributions to the performance of discrete and dimensional expression recognition, as well as posed versus spontaneous emotion discrimination. These investigations provide useful insights into enhancing robustness and achieving high performance of FER systems, and putting them into real-world applications.

Bearing Fault Diagnostics Using the Spectral Pattern Recognition

In the field of diagnostics of rolling element bearings, the development of sophisticated techniques, such as Spectral Kurtosis and 2nd Order Cyclostationarity, extended the capability of expert users to identify not only the presence, but also the location of the damage in the bearing. Most of the signal-analysis methods, as the ones previously mentioned, result in a spectrum-like diagram that presents line frequencies or peaks in the neighbourhood of some theoretical characteristic frequencies, in case of damage. These frequencies depend only on damage position, bearing geometry and rotational speed. The major improvement in this field would be the development of algorithms with high degree of automation. This paper aims at this important objective, by discussing for the first time how these peaks can draw away from the theoretical expected frequencies as a function of different working conditions, i.e. speed, torque and lubrication. After providing a brief description of the peak-patterns associated with each type of damage, this paper shows the typical magnitudes of the deviations from the theoretical expected frequencies. The last part of the study presents some remarks about increasing the reliability of the automatic algorithm. The research is based on experimental data obtained by using artificially damaged bearings installed in a gearbox.

Facial expression recognition experiments with data from television broadcasts and the world wide web

Facial expression recognition (FER) systems must ultimately work on real data in uncontrolled environments although most research studies have been conducted on lab-based data with posed or evoked facial expressions obtained in pre-set laboratory environments. It is very difficult to obtain data in real-world situations because privacy laws prevent unauthorized capture and use of video from events such as funerals, birthday parties, marriages etc. It is a challenge to acquire such data on a scale large enough for benchmarking algorithms. Although video obtained from TV or movies or postings on the World Wide Web may also contain ‘acted’ emotions and facial expressions, they may be more ‘realistic’ than lab-based data currently used by most researchers. Or is it? One way of testing this is to compare feature distributions and FER performance. This paper describes a database that has been collected from television broadcasts and the World Wide Web containing a range of environmental and facial variations expected in real conditions and uses it to answer this question. A fully automatic system that uses a fusion based approach for FER on such data is introduced for performance evaluation. Performance improvements arising from the fusion of point-based texture and geometry features, and the robustness to image scale variations are experimentally evaluated on this image and video dataset. Differences in FER performance between lab-based and realistic data, between different feature sets, and between different train-test data splits are investigated.

Random Gabor based templates for facial expression recognition in images with facial occlusion

Robust facial expression recognition (FER) under occluded face conditions is challenging. It requires robust algorithms of feature extraction and investigations into the effects of different types of occlusion on the recognition performance to gain insight. Previous FER studies in this area have been limited. They have spanned recovery strategies for loss of local texture information and testing limited to only a few types of occlusion and predominantly a matched train-test strategy. This paper proposes a robust approach that employs a Monte Carlo algorithm to extract a set of Gabor based part-face templates from gallery images and converts these templates into template match distance features. The resulting feature vectors are robust to occlusion because occluded parts are covered by some but not all of the random templates. The method is evaluated using facial images with occluded regions around the eyes and the mouth, randomly placed occlusion patches of different sizes, and near-realistic occlusion of eyes with clear and solid glasses. Both matched and mis-matched train and test strategies are adopted to analyze the effects of such occlusion. Overall recognition performance and the performance for each facial expression are investigated. Experimental results on the Cohn-Kanade and JAFFE databases demonstrate the high robustness and fast processing speed of our approach, and provide useful insight into the effects of occlusion on FER. The results on the parameter sensitivity demonstrate a certain level of robustness of the approach to changes in the orientation and scale of Gabor filters, the size of templates, and occlusions ratios. Performance comparisons with previous approaches show that the proposed method is more robust to occlusion with lower reductions in accuracy from occlusion of eyes or mouth.

Automated species recognition in environmental recordings

Faunal vocalisations are vital indicators for environmental change and faunal vocalisation analysis can provide information for answering ecological questions. Therefore, automated species recognition in environmental recordings has become a critical research area. This thesis presents an automated species recognition approach named Timed and Probabilistic Automata. A small lexicon for describing animal calls is defined, six algorithms for acoustic component detection are developed, and a series of species recognisers are built and evaluated.The presented automated species recognition approach yields significant improvement on the analysis performance over a real world dataset, and may be transferred to commercial software in the future.

Physical activity recognition from accelerometer data using a multi-scale ensemble method

Accurate and detailed measurement of an individual's physical activity is a key requirement for helping researchers understand the relationship between physical activity and health. Accelerometers have become the method of choice for measuring physical activity due to their small size, low cost, convenience and their ability to provide objective information about physical activity. However, interpreting accelerometer data once it has been collected can be challenging. In this work, we applied machine learning algorithms to the task of physical activity recognition from triaxial accelerometer data. We employed a simple but effective approach of dividing the accelerometer data into short non-overlapping windows, converting each window into a feature vector, and treating each feature vector as an i.i.d training instance for a supervised learning algorithm. In addition, we improved on this simple approach with a multi-scale ensemble method that did not need to commit to a single window size and was able to leverage the fact that physical activities produced time series with repetitive patterns and discriminative features for physical activity occurred at different temporal scales.

Machine learning for activity recognition : hip versus wrist data

Problem addressed Wrist-worn accelerometers are associated with greater compliance. However, validated algorithms for predicting activity type from wrist-worn accelerometer data are lacking. This study compared the activity recognition rates of an activity classifier trained on acceleration signal collected on the wrist and hip. Methodology 52 children and adolescents (mean age 13.7 +/- 3.1 year) completed 12 activity trials that were categorized into 7 activity classes: lying down, sitting, standing, walking, running, basketball, and dancing. During each trial, participants wore an ActiGraph GT3X+ tri-axial accelerometer on the right hip and the non-dominant wrist. Features were extracted from 10-s windows and inputted into a regularized logistic regression model using R (Glmnet + L1). Results Classification accuracy for the hip and wrist was 91.0% +/- 3.1% and 88.4% +/- 3.0%, respectively. The hip model exhibited excellent classification accuracy for sitting (91.3%), standing (95.8%), walking (95.8%), and running (96.8%); acceptable classification accuracy for lying down (88.3%) and basketball (81.9%); and modest accuracy for dance (64.1%). The wrist model exhibited excellent classification accuracy for sitting (93.0%), standing (91.7%), and walking (95.8%); acceptable classification accuracy for basketball (86.0%); and modest accuracy for running (78.8%), lying down (74.6%) and dance (69.4%). Potential Impact Both the hip and wrist algorithms achieved acceptable classification accuracy, allowing researchers to use either placement for activity recognition.

Visual place recognition for persistent robot navigation in changing environments

This thesis demonstrates that robots can learn about how the world changes, and can use this information to recognise where they are, even when the appearance of the environment has changed a great deal. The ability to localise in highly dynamic environments using vision only is a key tool for achieving long-term, autonomous navigation in unstructured outdoor environments. The proposed learning algorithms are designed to be unsupervised, and can be generated by the robot online in response to its observations of the world, without requiring information from a human operator or other external source.

A Likelihood-Maximizing Framework for Enhanced In-Car Speech Recognition Based on Speech Dialog System Interaction

Speech recognition in car environments has been identified as a valuable means for reducing driver distraction when operating noncritical in-car systems. Under such conditions, however, speech recognition accuracy degrades significantly, and techniques such as speech enhancement are required to improve these accuracies. Likelihood-maximizing (LIMA) frameworks optimize speech enhancement algorithms based on recognized state sequences rather than traditional signal-level criteria such as maximizing signal-to-noise ratio. LIMA frameworks typically require calibration utterances to generate optimized enhancement parameters that are used for all subsequent utterances. Under such a scheme, suboptimal recognition performance occurs in noise conditions that are significantly different from that present during the calibration session – a serious problem in rapidly changing noise environments out on the open road. In this chapter, we propose a dialog-based design that allows regular optimization iterations in order to track the ever-changing noise conditions. Experiments using Mel-filterbank noise subtraction (MFNS) are performed to determine the optimization requirements for vehicular environments and show that minimal optimization is required to improve speech recognition, avoid over-optimization, and ultimately assist with semireal-time operation. It is also shown that the proposed design is able to provide improved recognition performance over frameworks incorporating a calibration session only.

Automatic image scaling for place recognition in changing environments

Robustness to variations in environmental conditions and camera viewpoint is essential for long-term place recognition, navigation and SLAM. Existing systems typically solve either of these problems, but invariance to both remains a challenge. This paper presents a training-free approach to lateral viewpoint- and condition-invariant, vision-based place recognition. Our successive frame patch-tracking technique infers average scene depth along traverses and automatically rescales views of the same place at different depths to increase their similarity. We combine our system with the condition-invariant SMART algorithm and demonstrate place recognition between day and night, across entire 4-lane-plus-median-strip roads, where current algorithms fail.

Frequency response function based damage identification using principal component analysis and pattern recognition technique

Pattern recognition is a promising approach for the identification of structural damage using measured dynamic data. Much of the research on pattern recognition has employed artificial neural networks (ANNs) and genetic algorithms as systematic ways of matching pattern features. The selection of a damage-sensitive and noise-insensitive pattern feature is important for all structural damage identification methods. Accordingly, a neural networks-based damage detection method using frequency response function (FRF) data is presented in this paper. This method can effectively consider uncertainties of measured data from which training patterns are generated. The proposed method reduces the dimension of the initial FRF data and transforms it into new damage indices and employs an ANN method for the actual damage localization and quantification using recognized damage patterns from the algorithm. In civil engineering applications, the measurement of dynamic response under field conditions always contains noise components from environmental factors. In order to evaluate the performance of the proposed strategy with noise polluted data, noise contaminated measurements are also introduced to the proposed algorithm. ANNs with optimal architecture give minimum training and testing errors and provide precise damage detection results. In order to maximize damage detection results, the optimal architecture of ANN is identified by defining the number of hidden layers and the number of neurons per hidden layer by a trial and error method. In real testing, the number of measurement points and the measurement locations to obtain the structure response are critical for damage detection. Therefore, optimal sensor placement to improve damage identification is also investigated herein. A finite element model of a two storey framed structure is used to train the neural network. It shows accurate performance and gives low error with simulated and noise-contaminated data for single and multiple damage cases. As a result, the proposed method can be used for structural health monitoring and damage detection, particularly for cases where the measurement data is very large. Furthermore, it is suggested that an optimal ANN architecture can detect damage occurrence with good accuracy and can provide damage quantification with reasonable accuracy under varying levels of damage.

Joint evaluation of multiple speech patterns for speech recognition and training

We are addressing the novel problem of jointly evaluating multiple speech patterns for automatic speech recognition and training. We propose solutions based on both the non-parametric dynamic time warping (DTW) algorithm, and the parametric hidden Markov model (HMM). We show that a hybrid approach is quite effective for the application of noisy speech recognition. We extend the concept to HMM training wherein some patterns may be noisy or distorted. Utilizing the concept of ``virtual pattern'' developed for joint evaluation, we propose selective iterative training of HMMs. Evaluating these algorithms for burst/transient noisy speech and isolated word recognition, significant improvement in recognition accuracy is obtained using the new algorithms over those which do not utilize the joint evaluation strategy.

Learning Feature Trajectories Using Gabor Filter Bank for Human Activity Segmentation and Recognition

We describe a novel method for human activity segmentation and interpretation in surveillance applications based on Gabor filter-bank features. A complex human activity is modeled as a sequence of elementary human actions like walking, running, jogging, boxing, hand-waving etc. Since human silhouette can be modeled by a set of rectangles, the elementary human actions can be modeled as a sequence of a set of rectangles with different orientations and scales. The activity segmentation is based on Gabor filter-bank features and normalized spectral clustering. The feature trajectories of an action category are learnt from training example videos using dynamic time warping. The combined segmentation and the recognition processes are very efficient as both the algorithms share the same framework and Gabor features computed for the former can be used for the later. We have also proposed a simple shadow detection technique to extract good silhouette which is necessary for good accuracy of an action recognition technique.