Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos

We present results of a study into the performance of a variety of different image transform-based feature types for speaker-independent visual speech recognition of isolated digits. This includes the first reported use of features extracted using a discrete curvelet transform. The study will show a comparison of some methods for selecting features of each feature type and show the relative benefits of both static and dynamic visual features. The performance of the features will be tested on both clean video data and also video data corrupted in a variety of ways to assess each feature type's robustness to potential real-world conditions. One of the test conditions involves a novel form of video corruption we call jitter which simulates camera and/or head movement during recording.

Formal and informal care utilisation amongst elderly persons with visual impairment.

OBJECTIVE: To examine the determinants of formal and informal care utilisation amongst persons with age-related macular degeneration (AMD). DESIGN: Cross-sectional hospital-based study. SETTING: Hospital eye clinic in Northern Ireland. PARTICIPANTS: 284 persons aged >or=50 years. MAIN OUTCOME MEASURES: Participants were questioned about their care, living arrangements, eyesight-related ability to self-care, and eyesight-related need to be more careful whilst undertaking everyday tasks. RESULTS: The percentage of older persons receiving formal and informal care rose with the level of visual impairment. 34.9% and 37.3% of those with no visual impairment received formal and informal care, respectively, compared with 51.6% and 69.9% of those with moderate visual impairment and 55.6% and 88.9% of those with severe visual impairment. Three factors (age, best corrected distance visual acuity in the better eye and living alone) were significant predictors (p

The effect of simultaneous contractions of ipsilateral muscles on changes in corticospinal excitability induced by paired associative stimulation (PAS)

Consideration was given to means of increasing the reliability and muscle specificity of paired associative stimulation (PAS) by utilising the phenomenon of crossed-facilitation. Eight participants completed three separate sessions: isometric flexor contractions of the left wrist at 20% of maximum voluntary contraction (MVC) simultaneously with PAS (20s intervals; 14 min duration) delivered at the right median nerve and left primary motor cortex (MI); isometric contractions at 20% of MVC: and PAS only ( 14 min). Eight further participants completed two sessions of longer duration PAS (28 min): either alone or in conjunction with flexion contractions of the left wrist. Thirty motor potentials (MEPs) were evoked in the right flexor (rFCR) and extensor (rECR) carpi radialis muscles by magnetic stimulation of left M1 Prior to the interventions, immediately post-intervention, and 10 min post-intervention. Both 14 and 28 min of combined PAS and (left wrist flexion) contractions resulted in reliable increases in rFCR MEP amplitude, which were not present in rECR. In the PAS only conditions, 14 min of stimulation gave rise to unreliable increases in MEP amplitudes in rFCR and rECR, whereas 28 min of PAS induced small (unreliable) changes only for rFCR. These results support the conclusion that changes in the excitability of the corticospinal pathway induced by PAS interact with those associated with contraction of the muscles ipsilateral to the site of cortical stimulation. Furthermore, focal contractions applied by the opposite limb increase the extent and muscle specificity of the induced changes in excitability associated with PAS. (C) 2008 Elsevier Ireland Ltd. All rights reserved.

Generalisation between opposing visuomotor rotations when each is associated with visual targets and movements of different amplitude

Previous studies have attempted to identify sources of contextual information which can facilitate dual adaptation to two variants of a novel environment, which are normally prone to interference. The type of contextual information previously used can be grouped into two broad categories: that which is arbitrary to the motor system, such as a colour cue, and that which is based on an internal property of the motor system, such as a change in movement effector. The experiments reported here examined whether associating visuomotor rotations to visual targets and movements of different amplitude would serve as an appropriate source of contextual information to enable dual adaptation. The results indicated that visual target and movement amplitude is not a suitable source of contextual information to enable dual adaptation in our task. Interference was observed in groups who were exposed to opposing visuomotor rotations, or a visuomotor rotation and no rotation, both when the onset of the visuomotor rotations was sudden, or occurred gradually over the course of training. Furthermore, the pattern of interference indicated that the inability to dual adapt was a result of the generalisation of learning between the two visuomotor mappings associated with each of the visual target and movement amplitudes. (C) 2008 Elsevier B.V. All rights reserved.

The contribution of visual feedback to visuomotor adaptation: How much and when?

We investigated the role of visual feedback in adapting to novel visuomotor environments. Participants produced isometric elbow torques to move a cursor towards visual targets. Following trials with no rotation, participants adapted to a 60 degrees rotation of the visual feedback before returning to the non-rotated condition. Participants received continuous visual feedback (CF) of cursor position during task execution or post-trial visual feedback (PF). With training, reductions of the angular deviations of the cursor path occurred to a similar extent and at a similar rate for CF and PF groups. However, upon re-exposure to the non-rotated environment only CF participants exhibited post-training aftereffects, manifested as increased angular deviation of the cursor path, with respect to the pre-rotation trials. These aftereffects occurred despite colour cues permitting identification of the change in environment. The results show that concurrent feedback permits automatic recalibration of the visuomotor mapping while post-trial feedback permits performance improvement via a cognitive strategy. (C) 2008 Elsevier B.V. All rights reserved.

Muscle-specific variations in use-dependent crossed-facilitation of corticospinal pathways mediated by transcranial direct current (DC) stimulation

The tendency for contractions of muscles in the upper limb to give rise to increases in the excitability of corticospinal projections to the homologous muscles of the opposite limb is well known. Although the suppression of this tendency is integral to tasks of daily living, its exploitation may prove to be critical in the rehabilitation of acquired hemiplegias. Transcranial direct current (DC) stimulation induces changes in cortical excitability that outlast the period of application. We present evidence that changes in the reactivity of the corticospinal pathway induced by DC stimulation of the motor cortex interact systematically with those brought about by contraction of the muscles of the ipsilateral limb. During the application of flexion torques (up to 50% of maximum) applied at the left wrist, motor evoked potentials (MEPs) were evoked in the quiescent muscles of the right arm by magnetic stimulation of the left motor cortex (M1). The MEPs were obtained prior to and following 10 min of anodal, cathodal or sham DC stimulation of left M1. Cathodal stimulation counteracted increases in the crossed-facilitation of projections to the (right) wrist flexors that otherwise occurred as a result of repeated flexion contractions at the left wrist. In addition, cathodal stimulation markedly decreased the excitability of corticospinal projections to the wrist extensors of the right limb. Thus changes in corticospinal excitability induced by DC stimulation can be shaped (i.e. differentiated by muscle group) by focal contractions of muscles in the limb ipsilateral to the site of stimulation. (C) 2008 Elsevier Ireland Ltd. All rights reserved.

Reliability of the input-output properties of the cortico-spinal pathway obtained from transcranial magnetic and electrical stimulation

The purpose of this experiment was to assess the test-retest reliability of input-output parameters of the cortico-spinal pathway derived from transcranial magnetic (TMS) and electrical (TES) stimulation at rest and during muscle contraction. Motor evoked potentials (MEPs) were recorded from the first dorsal interosseous muscle of eight individuals on three separate days. The intensity of TMS at rest was varied from 5% below threshold to the maximal output of the stimulator. During trials in which the muscle was active, TMS and TES intensities were selected that elicited MEPs of between 150 and 300 X at rest. MEPs were evoked while the participants exerted torques up to 50% of their maximum capacity. The relationship between MEP size and stimulus intensity at rest was sigmoidal (R-2 = 0.97). Intra-class correlation coefficients (ICC) ranged between 0.47 and 0.81 for the parameters of the sigmoid function. For the active trials, the slope and intercept of regression equations of MEP size on level of background contraction were obtained more reliably for TES (ICC = 0.63 and 0.78, respectively) than for TMS (ICC = 0.50 and 0.53, respectively), These results suggest that input-output parameters of the cortico-spinal pathway may be reliably obtained via transcranial stimulation during longitudinal investigations of cortico-spinal plasticity. (C) 2001 Elsevier Science B.V. All rights reserved.

The hierarchy of directional interactions in visual motion processing

It is well known that context influences our perception of visual motion direction. For example, spatial and temporal context manipulations can be used to induce two well-known motion illusions: direction repulsion and the direction after-effect (DAE). Both result in inaccurate perception of direction when a moving pattern is either superimposed on (direction repulsion), or presented following adaptation to (DAE), another pattern moving in a different direction. Remarkable similarities in tuning characteristics suggest that common processes underlie the two illusions. What is not clear, however, is whether the processes driving the two illusions are expressions of the same or different neural substrates. Here we report two experiments demonstrating that direction repulsion and the DAE are, in fact, expressions of different neural substrates. Our strategy was to use each of the illusions to create a distorted perceptual representation upon which the mechanisms generating the other illusion could potentially operate. We found that the processes mediating direction repulsion did indeed access the distorted perceptual representation induced by the DAE. Conversely, the DAE was unaffected by direction repulsion. Thus parallels in perceptual phenomenology do not necessarily imply common neural substrates. Our results also demonstrate that the neural processes driving the DAE occur at an earlier stage of motion processing than those underlying direction repulsion.

Hidden Conditional Random Fields for Visual Speech Recognition

In this paper we present the application of Hidden Conditional Random Fields (HCRFs) to modelling speech for visual speech recognition. HCRFs may be easily adapted to model long range dependencies across an observation sequence. As a result visual word recognition performance can be improved as the model is able to take more of a contextual approach to generating state sequences. Results are presented from a speaker-dependent, isolated digit, visual speech recognition task using comparisons with a baseline HMM system. We firstly illustrate that word recognition rates on clean video using HCRFs can be improved by increasing the number of past and future observations being taken into account by each state. Secondly we compare model performances using various levels of video compression on the test set. As far as we are aware this is the first attempted use of HCRFs for visual speech recognition.