AdaBoost Multiple Feature Selection and Combination for Face Recognition

Gabor features have been recognized as one of the most successful face representations. Encouraged by the results given by this approach, other kind of facial representations based on Steerable Gaussian first order kernels and Harris corner detector are proposed in this paper. In order to reduce the high dimensional feature space, PCA and LDA techniques are employed. Once the features have been extracted, AdaBoost learning algorithm is used to select and combine the most representative features. The experimental results on XM2VTS database show an encouraging recognition rate, showing an important improvement with respect to face descriptors only based on Gabor filters.

3D Morphable Model Construction for Robust Ear and Face Recognition

Recent work suggests that the human ear varies significantly between different subjects and can be used for identification. In principle, therefore, using ears in addition to the face within a recognition system could improve accuracy and robustness, particularly for non-frontal views. The paper describes work that investigates this hypothesis using an approach based on the construction of a 3D morphable model of the head and ear. One issue with creating a model that includes the ear is that existing training datasets contain noise and partial occlusion. Rather than exclude these regions manually, a classifier has been developed which automates this process. When combined with a robust registration algorithm the resulting system enables full head morphable models to be constructed efficiently using less constrained datasets. The algorithm has been evaluated using registration consistency, model coverage and minimalism metrics, which together demonstrate the accuracy of the approach. To make it easier to build on this work, the source code has been made available online.

Laughter Type Recognition from Whole Body Motion

Despite the importance of laughter in social interactions it remains little studied in affective computing. Respiratory, auditory, and facial laughter signals have been investigated but laughter-related body movements have received almost no attention. The aim of this study is twofold: first an investigation into observers' perception of laughter states (hilarious, social, awkward, fake, and non-laughter) based on body movements alone, through their categorization of avatars animated with natural and acted motion capture data. Significant differences in torso and limb movements were found between animations perceived as containing laughter and those perceived as nonlaughter. Hilarious laughter also differed from social laughter in the amount of bending of the spine, the amount of shoulder rotation and the amount of hand movement. The body movement features indicative of laughter differed between sitting and standing avatar postures. Based on the positive findings in this perceptual study, the second aim is to investigate the possibility of automatically predicting the distributions of observer's ratings for the laughter states. The findings show that the automated laughter recognition rates approach human rating levels, with the Random Forest method yielding the best performance.

Largest Matching Areas for Illumination and Occlusion Robust Face Recognition

In this paper, we introduce a novel approach to face recognition which simultaneously tackles three combined challenges: 1) uneven illumination; 2) partial occlusion; and 3) limited training data. The new approach performs lighting normalization, occlusion de-emphasis and finally face recognition, based on finding the largest matching area (LMA) at each point on the face, as opposed to traditional fixed-size local area-based approaches. Robustness is achieved with novel approaches for feature extraction, LMA-based face image comparison and unseen data modeling. On the extended YaleB and AR face databases for face identification, our method using only a single training image per person, outperforms other methods using a single training image, and matches or exceeds methods which require multiple training images. On the labeled faces in the wild face verification database, our method outperforms comparable unsupervised methods. We also show that the new method performs competitively even when the training images are corrupted.

Common-sense reasoning for human action recognition

This paper presents a novel method that leverages reasoning capabilities in a computer vision system dedicated to human action recognition. The proposed methodology is decomposed into two stages. First, a machine learning based algorithm - known as bag of words - gives a first estimate of action classification from video sequences, by performing an image feature analysis. Those results are afterward passed to a common-sense reasoning system, which analyses, selects and corrects the initial estimation yielded by the machine learning algorithm. This second stage resorts to the knowledge implicit in the rationality that motivates human behaviour. Experiments are performed in realistic conditions, where poor recognition rates by the machine learning techniques are significantly improved by the second stage in which common-sense knowledge and reasoning capabilities have been leveraged. This demonstrates the value of integrating common-sense capabilities into a computer vision pipeline. © 2012 Elsevier B.V. All rights reserved.

On-line Emotion Recognition in a 3-D Activation-Valence-Time Continuum using Acoustic and Linguistic Cues

For many applications of emotion recognition, such as virtual agents, the system must select responses while the user is speaking. This requires reliable on-line recognition of the user’s affect. However most emotion recognition systems are based on turnwise processing. We present a novel approach to on-line emotion recognition from speech using Long Short-Term Memory Recurrent Neural Networks. Emotion is recognised frame-wise in a two-dimensional valence-activation continuum. In contrast to current state-of-the-art approaches, recognition is performed on low-level signal frames, similar to those used for speech recognition. No statistical functionals are applied to low-level feature contours. Framing at a higher level is therefore unnecessary and regression outputs can be produced in real-time for every low-level input frame. We also investigate the benefits of including linguistic features on the signal frame level obtained by a keyword spotter.

Comparison of teleconsultations and face-to-face consultations:preliminary results of a United Kingdom multicentre teledermatology study

The objective of this multicentre study was to undertake a systematic comparison of face-to-face consultations and teleconsultations performed using low-cost videoconferencing equipment. One hundred and twenty-six patients were enrolled by their general practitioners across three sites. Each patient underwent a teleconsultation with a distant dermatologist followed by a traditional face-to-face consultation with a dermatologist. The main outcome measures were diagnostic concordance rates, management plans and patient and doctor satisfaction. One hundred and fifty-five diagnoses were identified by the face-to-face consultations from the sample of 126 patients. Identical diagnoses were recorded from both types of consultation in 59% of cases. Teledermatology consultations missed a secondary diagnosis in 6% of cases and were unable to make a useful diagnosis in 11% of cases. Wrong diagnoses were made by the teledermatologist in 4% of cases. Dermatologists were able to make a definitive diagnosis by face-to-face consultations in significantly more cases than by teleconsultations (P = 0.001). Where both types of consultation resulted in a single diagnosis there was a high level of agreement (kappa = 0.96, lower 95% confidence limit 0.91-1.00). Overall follow-up rates from both types of consultation were almost identical. Fifty per cent of patients seen could have been managed using a single videoconferenced teleconsultation without any requirement for further specialist intervention. Patients reported high levels of satisfaction with the teleconsultations. General practitioners reported that 75% of the teleconsultations were of educational benefit. This study illustrates the potential of telemedicine to diagnose and manage dermatology cases referred from primary care. Once the problem of image quality has been addressed, further studies will be required to investigate the cost-effectiveness of a teledermatology service and the potential consequences for the provision of dermatological services in the U.K.

Robust Multimodal Person Identification With Limited Training Data

This paper presents a novel method of audio-visual feature-level fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there are limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new multimodal feature representation and a modified cosine similarity are introduced to combine and compare bimodal features with limited training data, as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal dataset created from the SPIDRE speaker recognition database and AR face recognition database with variable noise corruption of speech and occlusion in the face images. The system's speaker identification performance on the SPIDRE database, and facial identification performance on the AR database, is comparable with the literature. Combining both modalities using the new method of multimodal fusion leads to significantly improved accuracy over the unimodal systems, even when both modalities have been corrupted. The new method also shows improved identification accuracy compared with the bimodal systems based on multicondition model training or missing-feature decoding alone.

Prospective information for pass decisional behaviour in Rugby Union

Decision-making requires the perception of relevant information variables that emerge from the player–environment interaction. The purpose of the present article is to empirically assess whether players’ decisional behavior about which type of pass to make is influenced by the spatio-temporal variable tau. Time series positional data of rugby players were analyzed from video footage taken in real match scenarios. The tau of the distance motion gap between attacker and defender was calculated, along with the duration of the next pass. Results revealed that the initial tau value predicted 64% of the variance found in pass duration. A qualitative distinction of tau dynamics between two periods of the approach between the attacker and the defender was also observed. We argue that the time-to-contact between the attacker and the defender may yield information about future pass possibilities. Additionally, the informational fields constraining attacker–defender interaction may be viewed as a convergent channeling of possibilities towards a single pass solution.

An Improvement of Subject Reacquisition by Reasoning and Revision

CCTV systems are broadly deployed in the present world. Despite this, the impact on anti-social and criminal behaviour has been minimal. Subject reacquisition is a fundamental task to ensure in-time reaction for intelligent surveillance. However, traditional reacquisition based on face recognition is not scalable, hence in this paper we use reasoning techniques to reduce the computational effort which deploys the time-of-flight information between interested zones such as airport security corridors. Also, to improve accuracy of reacquisition, we introduce the idea of revision as a method of post-processing.We demonstrate the significance and usefulness of our framework with an experiment which shows much less computational effort and better accuracy.

Hierarchical Task Network Planning with Common-Sense Reasoning for Multiple-People Behaviour Analysis

Safety on public transport is a major concern for the relevant authorities. We
address this issue by proposing an automated surveillance platform which combines data from video, infrared and pressure sensors. Data homogenisation and integration is achieved by a distributed architecture based on communication middleware that resolves interconnection issues, thereby enabling data modelling. A common-sense knowledge base models and encodes knowledge about public-transport platforms and the actions and activities of passengers. Trajectory data from passengers is modelled as a time-series of human activities. Common-sense knowledge and rules are then applied to detect inconsistencies or errors in the data interpretation. Lastly, the rationality that characterises human behaviour is also captured here through a bottom-up Hierarchical Task Network planner that, along with common-sense, corrects misinterpretations to explain passenger behaviour. The system is validated using a simulated bus saloon scenario as a case-study. Eighteen video sequences were recorded with up to six passengers. Four metrics were used to evaluate performance. The system, with an accuracy greater than 90% for each of the four metrics, was found to outperform a rule-base system and a system containing planning alone.

Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction

In this paper, a novel video-based multimodal biometric verification scheme using the subspace-based low-level feature fusion of face and speech is developed for specific speaker recognition for perceptual human--computer interaction (HCI). In the proposed scheme, human face is tracked and face pose is estimated to weight the detected facelike regions in successive frames, where ill-posed faces and false-positive detections are assigned with lower credit to enhance the accuracy. In the audio modality, mel-frequency cepstral coefficients are extracted for voice-based biometric verification. In the fusion step, features from both modalities are projected into nonlinear Laplacian Eigenmap subspace for multimodal speaker recognition and combined at low level. The proposed approach is tested on the video database of ten human subjects, and the results show that the proposed scheme can attain better accuracy in comparison with the conventional multimodal fusion using latent semantic analysis as well as the single-modality verifications. The experiment on MATLAB shows the potential of the proposed scheme to attain the real-time performance for perceptual HCI applications.