Investigation into DCT Feature Selection for Visual Lip-Based Biometric Authentication

This paper investigated using lip movements as a behavioural biometric for person authentication. The system was trained, evaluated and tested using the XM2VTS dataset, following the Lausanne Protocol configuration II. Features were selected from the DCT coefficients of the greyscale lip image. This paper investigated the number of DCT coefficients selected, the selection process, and static and dynamic feature combinations. Using a Gaussian Mixture Model - Universal Background Model framework an Equal Error Rate of 2.20% was achieved during evaluation and on an unseen test set a False Acceptance Rate of 1.7% and False Rejection Rate of 3.0% was achieved. This compares favourably with face authentication results on the same dataset whilst not being susceptible to spoofing attacks.

Feature Selection for Pose Invariant Lip Biometrics

For the first time in this paper the authors present results showing the effect of out of plane speaker head pose variation on a lip biometric based speaker verification system. Using appearance DCT based features, they adopt a Mutual Information analysis technique to highlight the class discriminant DCT components most robust to changes in out of plane pose. Experiments are conducted using the initial phase of a new multi view Audio-Visual database designed for research and development of pose-invariant speech and speaker recognition. They show that verification performance can be improved by substituting higher order horizontal DCT components for vertical, particularly in the case of a train/test pose angle mismatch.

Visual target separation determines the extent of generalisation between opposing visuomotor rotations

Here we investigated the influence of angular separation between visual and motor targets on concurrent adaptation to two opposing visuomotor rotations. We inferred the extent of generalisation between opposing visuomotor rotations at individual target locations based on whether interference (negative transfer) was present. Our main finding was that dual adaptation occurred to opposing visuomotor rotations when each was associated with different visual targets but shared a common motor target. Dual adaptation could have been achieved either within a single sensorimotor map (i.e. with different mappings associated with different ranges of visual input), or by forming two different internal models (the selection of which would be based on contextual information provided by target location). In the present case, the pattern of generalisation was dependent on the relative position of the visual targets associated with each rotation. Visual targets nearest the workspace of the opposing visuomotor rotation exhibited the most interference (i.e. generalisation). When the minimum angular separation between visual targets was increased, the extent of interference was reduced. These results suggest that the separation in the range of sensory inputs is the critical requirement to support dual adaptation within a single sensorimotor mapping.

Design characteristic of randomised controlled trials for geographic atrophy in age-related macular degeneration: selection of outcomes and sample size calculation

PurposeThe selection of suitable outcomes and sample size calculation are critical factors in the design of a randomised controlled trial (RCT). The goal of this study was to identify the range of outcomes and information on sample size calculation in RCTs on geographic atrophy (GA).MethodsWe carried out a systematic review of age-related macular degeneration (AMD) RCTs. We searched MEDLINE, EMBASE, Scopus, Cochrane Library, www.controlled-trials.com, and www.ClinicalTrials.gov. Two independent reviewers screened records. One reviewer collected data and the second reviewer appraised 10% of collected data. We scanned references lists of selected papers to include other relevant RCTs.ResultsLiterature and registry search identified 3816 abstracts of journal articles and 493 records from trial registries. From a total of 177 RCTs on all types of AMD, 23 RCTs on GA were included. Eighty-one clinical outcomes were identified. Visual acuity (VA) was the most frequently used outcome, presented in 18 out of 23 RCTs and followed by the measures of lesion area. For sample size analysis, 8 GA RCTs were included. None of them provided sufficient Information on sample size calculations.ConclusionsThis systematic review illustrates a lack of standardisation in terms of outcome reporting in GA trials and issues regarding sample size calculation. These limitations significantly hamper attempts to compare outcomes across studies and also perform meta-analyses.

Distribution and visual impact of postoperative refractive error after cataract surgery in rural China: study of cataract outcomes and up-take of services report 4.

PURPOSE: To model the possible impact of using average-power intraocular lenses (IOLs) and evaluate the postoperative refractive error in patients having cataract surgery in rural China.SETTING: Rural Guangdong, China.METHODS: Patients having cataract surgery by local surgeons were examined and visual function was assessed 10 to 14 months after surgery. Subjective refraction at near and distance was performed bilaterally by an ophthalmologist. Patients had a target refraction of -0.50 diopter (D) based on ocular biometry.RESULTS: Of the 313 eligible patients, 242 (77%) could be contacted and 176 (74% of contacted patients, 56% overall) were examined. Examined patients had a mean age of 69.4 +/- 10.5 years. Of the 211 operated eyes, 73.2% were within +/-1.0 D of the target refraction after surgery. The best presenting distance vision was in patients within +/-1.0 D of plano and the best presenting near vision, in those with mild myopia (<-1.0 D to > or =2.0 D) (P= .005). However, patients with hyperopia (>+1.0 D) reported significantly better adjusted visual function than those with emmetropia or myopia (<-1.0 D). When the predicted use of an average-power IOL (median +21.5 D) was modeled, predicted visual acuity was significantly reduced (P= .001); however, predicted visual function was not significantly altered (P>.3).CONCLUSIONS: Accurate selection of postoperative refractive error was achieved by local surgeons in this rural area. Based on visual function results, aiming for mild postoperative myopia may not be suitable in this setting. Implanting average-power IOLs significantly reduced postoperative presenting vision, but not visual function.