Visual-Context Boosting for Eye Detection

Eye detection plays an important role in many practical applications. This paper presents a novel two-step scheme for eye detection. The first step models an eye by a newly defined visual-context pattern (VCP), and the second step applies semisupervised boosting for precise detection. VCP describes both the space and appearance relations between an eye region (region of eye) and a reference region (region of reference). The context feature of a VCP is extracted by using the integral image. Aiming to reduce the human labeling efforts, we apply semisupervised boosting, which integrates the context feature and the Haar-like features for precise eye detection. Experimental results on several standard face data sets demonstrate that the proposed approach is effective, robust, and efficient. We finally show that this approach is ready for practical applications.

Sharing visual features for multiclass and multiview object detection

We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, at multiple locations and scales. This can be slow and can require a lot of training data, since each classifier requires the computation of many different image features. In particular, for independently trained detectors, the (run-time) computational complexity, and the (training-time) sample complexity, scales linearly with the number of classes to be detected. It seems unlikely that such an approach will scale up to allow recognition of hundreds or thousands of objects. We present a multi-class boosting procedure (joint boosting) that reduces the computational and sample complexity, by finding common features that can be shared across the classes (and/or views). The detectors for each class are trained jointly, rather than independently. For a given performance level, the total number of features required, and therefore the computational cost, is observed to scale approximately logarithmically with the number of classes. The features selected jointly are closer to edges and generic features typical of many natural structures instead of finding specific object parts. Those generic features generalize better and reduce considerably the computational cost of an algorithm for multi-class object detection.

Evaluation of a Passive Millimeter Wave (PMMW) imager for wire detection in degraded visual conditions

Ground vehicle tests have been performed to evaluate the performance of a Passive Millimeter Wave (PMMW) imager in reduced visibility conditions and in particular, the ability to detect power lines and cables. A PMMW imager was
compared with Long Wave Infrared (LWIR) and visible imaging cameras. The three sensors were mounted on a Land Rover, together with GPS and digital recording system. All three sensors plus the GPS data were recorded simultaneously in order to provide direct comparisons. The vehicle collected imagery from a number of sites in the vicinity of Malvern, UK, in January, 2008. Imagery was collected both while the vehicle was stationary at specific sites
and while it was moving. Weather conditions during the data collection included clear, drizzle, rain and fog. Imagery was collected during the day, at night, and during dusk/dawn transition periods. The PMMW imager was a prototype which operated at 94 GHz and was based on a conically scanned folded Schmidt camera and the LWIR and visible sensors were commercial off the shelf items.

Detection of visual-field deterioration by Glaucoma Progression Analysis and Threshold Noiseless Trend programs

BACKGROUND: To compare the ability of Glaucoma Progression Analysis (GPA) and Threshold Noiseless Trend (TNT) programs to detect visual-field deterioration.

METHODS: Patients with open-angle glaucoma followed for a minimum of 2 years and a minimum of seven reliable visual fields were included. Progression was assessed subjectively by four masked glaucoma experts, and compared with GPA and TNT results. Each case was judged to be stable, deteriorated or suspicious of deterioration

RESULTS: A total of 56 eyes of 42 patients were followed with a mean of 7.8 (SD 1.0) tests over an average of 5.5 (1.04) years. Interobserver agreement to detect progression was good (mean kappa = 0.57). Progression was detected in 10-19 eyes by the experts, in six by GPA and in 24 by TNT. Using the consensus expert opinion as the gold standard (four clinicians detected progression), the GPA sensitivity and specificity were 75% and 83%, respectively, while the TNT sensitivity and specificity was 100% and 77%, respectively.

CONCLUSION: TNT showed greater concordance with the experts than GPA in the detection of visual-field deterioration. GPA showed a high specificity but lower sensitivity, mainly detecting cases of high focality and pronounced mean defect slopes.

Improved line/edge detection and visual reconstruction

Lines and edges provide important information for object categorization and recognition. In addition, one brightness model is based on a symbolic interpretation of the cortical multi-scale line/edge representation. In this paper we present an improved scheme for line/edge extraction from simple and complex cells and we illustrate the multi-scale representation. This representation can be used for visual reconstruction, but also for nonphotorealistic rendering. Together with keypoints and a new model of disparity estimation, a 3D wireframe representation of e.g. faces can be obtained in the future.

Visual efficiency detection index : a new composite measure of visual search

Visual search is an important component of our interaction with our surroundings, allowing us to successfully identify external cues that impact our spatial navigation. Previous research has established fixation duration, fixation count, saccade velocity, and saccade amplitude as important indices of visual search. We examined the Visual Efficiency Detection Index (VEDI) comprising multiple aspects of visual search performance into a single measure of global visual performance. Forty participants, 10 adults ages 22-48, and children ages 6, 8, and 10, completed tests of working memory and visual search in response to stimuli relevant to pedestrian decision making. Results indicated VEDI statistically relates to established indices of visual search in relation to their interpretability for human performance. The VEDI was also sensitive to developmental differences in visual search performance, suggesting insight to its utility in the developmental psychological literature.

Motion detection and motion verbs: language affects low-level visual perception

Recent theories propose that semantic representation and sensorimotor processing have a common substrate via simulation. We tested the prediction that comprehension interacts with perception, using a standard psychophysics methodology.While passively listening to verbs that referred to upward or downward motion, and to control verbs that did not refer to motion, 20 subjects performed a motion-detection task, indicating whether or not they saw motion in visual stimuli containing threshold levels of coherent vertical motion. A signal detection analysis revealed that when verbs were directionally incongruent with the motion signal, perceptual sensitivity was impaired. Word comprehension also affected decision criteria and reaction times, but in different ways. The results are discussed with reference to existing explanations of embodied processing and the potential of psychophysical methods for assessing interactions between language and perception.

Robust abandoned object detection integrating wide area visual surveillance and social context

This paper presents a video surveillance framework that robustly and efficiently detects abandoned objects in surveillance scenes. The framework is based on a novel threat assessment algorithm which combines the concept of ownership with automatic understanding of social relations in order to infer abandonment of objects. Implementation is achieved through development of a logic-based inference engine based on Prolog. Threat detection performance is conducted by testing against a range of datasets describing realistic situations and demonstrates a reduction in the number of false alarms generated. The proposed system represents the approach employed in the EU SUBITO project (Surveillance of Unattended Baggage and the Identification and Tracking of the Owner).

In vitro comparison of laser fluorescence performance with visual examination for detection of occlusal caries in permanent and primary molars

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Detection of Listeria sp in meat and meat products using TECRA Listeria visual immunoassay and biocontrol visual immunoprecipitate assay for Listeria immunoassays and a cultural procedure

The routine methods for detecting Listeria sp. in foods are time consuming and involve using selective enrichments and plating on agars. In this study, the presence of Listeria sp. in 120 meat and meat product samples was investigated by two rapid immunoassays (TECRA Listeria Visual Immunoassay [VIA] and BioControl Visual Immunoprecipitate Assay [VIP] for Listeria) and a cultural procedure. The cultural method of detecting Listeria sp. followed Canada's Health Protection Branch Method, and the rapid tests followed the manufacturers' instructions. The agreement between the cultural and the rapid tests was established at a confidence limit of 95%. Seventy-nine samples (65.8%) were Listeria sp. positive in at least one of the three tests. There was no statistically significant difference between the cultural procedure and any of the rapid immunoassays. The agreement rates between the VIA and the cultural method and between the VIP and the cultural method were 87 and 84%, respectively. Both tests - the VIA and VIP - proved to be rapid, efficient and easy to perform.

Laboratorial training of examiners for using a visual caries detection system in epidemiological surveys

Background: In epidemiological surveys, a good reliability among the examiners regarding the caries detection method is essential. However, training and calibrating those examiners is an arduous task because it involves several patients who are examined many times. To facilitate this step, we aimed to propose a laboratory methodology to simulate the examinations performed to detect caries lesions using the International Caries Detection and Assessment System (ICDAS) in epidemiological surveys. Methods: A benchmark examiner conducted all training sessions. A total of 67 exfoliated primary teeth, varying from sound to extensive cavitated, were set in seven arch models to simulate complete mouths in primary dentition. Sixteen examiners (graduate students) evaluated all surfaces of the teeth under illumination using buccal mirrors and ball-ended probe in two occasions, using only coronal primary caries scores of the ICDAS. As reference standard, two different examiners assessed the proximal surfaces by direct visual inspection, classifying them in sound, with non-cavitated or with cavitated lesions. After, teeth were sectioned in the bucco-lingual direction, and the examiners assessed the sections in stereomicroscope, classifying the occlusal and smooth surfaces according to lesion depth. Inter-examiner reproducibility was evaluated using weighted kappa. Sensitivities and specificities were calculated at two thresholds: all lesions and advanced lesions (cavitated lesions in proximal surfaces and lesions reaching the dentine in occlusal and smooth surfaces). Conclusion: The methodology purposed for training and calibration of several examiners designated for epidemiological surveys of dental caries in preschool children using the ICDAS is feasible, permitting the assessment of reliability and accuracy of the examiners previously to the survey´s development.

Performance of laser fluorescence devices, visual and radiographic examination for the detection of occlusal caries in primary molars

The aim of this in vitro study was to compare the performance of two laser fluorescence devices (LF, LFpen), conventional visual criteria (VE), ICDAS and radiographic examination on occlusal surfaces of primary teeth. Thirty-seven primary human molars were selected from a pool of extracted teeth, which were stored frozen at -20°C until use. Teeth were assessed twice by two experienced examiners using laser fluorescence devices (LF and LFpen), conventional visual criteria, ICDAS and bitewing radiographs, with a 2-week interval between measurements. After measurement, the teeth were histologically prepared and assessed for caries extension. The highest sensitivity was observed for ICDAS at D(1) and D(3) thresholds, with no statistically significant difference when compared to the LF devices, except at the D(3) threshold. Bitewing radiographs presented the lowest values of sensitivity. Specificity at D(1) was higher for LFpen (0.90) and for VE at D(3) (0.94). When VE was combined with LFpen the post-test probabilities were the highest (94.0% and 89.2% at D(1) and D(3) thresholds, respectively). High values were observed for the combination of ICDAS and LFpen (92.0% and 80.0%, respectively). LF and LFpen showed the highest values of ICC for interexaminer reproducibility. However, regarding ICDAS, BW and VE, intraexaminer reproducibility was not the same for the two examiners. After primary visual inspection using ICDAS or not, the use of LFpen may aid in the detection of occlusal caries in primary teeth. Bitewing radiographs may be indicated only for approximal caries detection.

In vitro comparison of laser fluorescence performance with visual examination for detection of occlusal caries in permanent and primary molars

The aim of this study was to compare the performance of the DIAGNOdent 2095 with visual examination for occlusal caries detection in permanent and primary molars. The sample comprised 148 permanent human molars and 179 primary human molars. The samples were measured and visually examined three times by two examiners. After measurement, the teeth were histologically prepared and assessed for caries extension. Sensitivity, specificity, accuracy and area under the receiver operating characteristics (ROC) curve were calculated. Intra-class correlation (ICC), unweighted kappa and the Bland and Altman method were used to assess inter- and intra-examiner reproducibility. DIAGNOdent showed higher specificity and lower sensitivity than did visual examination. The ICC values indicated an excellent agreement between the examinations. Kappa values varied from good to excellent for DIAGNOdent but from poor to good for visual examination. In conclusion, the DIAGNOdent may be a useful adjunct to conventional methods for occlusal caries detection.

Effects of age and eccentricity on visual target detection

The aim of this study was to examine the effects of aging and target eccentricity on a visual search task comprising 30 images of everyday life projected into a hemisphere, realizing a ±90° visual field. The task performed binocularly allowed participants to freely move their eyes to scan images for an appearing target or distractor stimulus (presented at 10°; 30°, and 50° eccentricity). The distractor stimulus required no response, while the target stimulus required acknowledgment by pressing the response button. One hundred and seventeen healthy subjects (mean age = 49.63 years, SD = 17.40 years, age range 20–78 years) were studied. The results show that target detection performance decreases with age as well as with increasing eccentricity, especially for older subjects. Reaction time also increases with age and eccentricity, but in contrast to target detection, there is no interaction between age and eccentricity. Eye movement analysis showed that younger subjects exhibited a passive search strategy while older subjects exhibited an active search strategy probably as a compensation for their reduced peripheral detection performance.

Intelligence is related to specific processes in visual change detection: Fixed-links modeling of hit rate and reaction time

By means of fixed-links modeling, the present study identified different processes of visual short-term memory (VSTM) functioning and investigated how these processes are related to intelligence. We conducted an experiment where the participants were presented with a color change detection task. Task complexity was manipulated through varying the number of presented stimuli (set size). We collected hit rate and reaction time (RT) as indicators for the amount of information retained in VSTM and speed of VSTM scanning, respectively. Due to the impurity of these measures, however, the variability in hit rate and RT was assumed to consist not only of genuine variance due to individual differences in VSTM retention and VSTM scanning but also of other, non-experimental portions of variance. Therefore, we identified two qualitatively different types of components for both hit rate and RT: (1) non-experimental components representing processes that remained constant irrespective of set size and (2) experimental components reflecting processes that increased as a function of set size. For RT, intelligence was negatively associated with the non-experimental components, but was unrelated to the experimental components assumed to represent variability in VSTM scanning speed. This finding indicates that individual differences in basic processing speed, rather than in speed of VSTM scanning, differentiates between high- and low-intelligent individuals. For hit rate, the experimental component constituting individual differences in VSTM retention was positively related to intelligence. The non-experimental components of hit rate, representing variability in basal processes, however, were not associated with intelligence. By decomposing VSTM functioning into non-experimental and experimental components, significant associations with intelligence were revealed that otherwise might have been obscured.