Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos

Monocular-based 3-D seafloor reconstruction and ortho-mosaicing by piecewise planar representation

Photo-mosaicing techniques have become popular for seafloor mapping in various marine science applications. However, the common methods cannot accurately map regions with high relief and topographical variations. Ortho-mosaicing borrowed from photogrammetry is an alternative technique that enables taking into account the 3-D shape of the terrain. A serious bottleneck is the volume of elevation information that needs to be estimated from the video data, fused, and processed for the generation of a composite ortho-photo that covers a relatively large seafloor area. We present a framework that combines the advantages of dense depth-map and 3-D feature estimation techniques based on visual motion cues. The main goal is to identify and reconstruct certain key terrain feature points that adequately represent the surface with minimal complexity in the form of piecewise planar patches. The proposed implementation utilizes local depth maps for feature selection, while tracking over several views enables 3-D reconstruction by bundle adjustment. Experimental results with synthetic and real data validate the effectiveness of the proposed approach

Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos

Use of decision trees in colour feature selection: application to object recognition in outdoor scenes

A new method for the automated selection of colour features is described. The algorithm consists of two stages of processing. In the first, a complete set of colour features is calculated for every object of interest in an image. In the second stage, each object is mapped into several n-dimensional feature spaces in order to select the feature set with the smallest variables able to discriminate the remaining objects. The evaluation of the discrimination power for each concrete subset of features is performed by means of decision trees composed of linear discrimination functions. This method can provide valuable help in outdoor scene analysis where no colour space has been demonstrated as being the most suitable. Experiment results recognizing objects in outdoor scenes are reported

Monocular-based 3-D seafloor reconstruction and ortho-mosaicing by piecewise planar representation

Photo-mosaicing techniques have become popular for seafloor mapping in various marine science applications. However, the common methods cannot accurately map regions with high relief and topographical variations. Ortho-mosaicing borrowed from photogrammetry is an alternative technique that enables taking into account the 3-D shape of the terrain. A serious bottleneck is the volume of elevation information that needs to be estimated from the video data, fused, and processed for the generation of a composite ortho-photo that covers a relatively large seafloor area. We present a framework that combines the advantages of dense depth-map and 3-D feature estimation techniques based on visual motion cues. The main goal is to identify and reconstruct certain key terrain feature points that adequately represent the surface with minimal complexity in the form of piecewise planar patches. The proposed implementation utilizes local depth maps for feature selection, while tracking over several views enables 3-D reconstruction by bundle adjustment. Experimental results with synthetic and real data validate the effectiveness of the proposed approach

The role of the amygdala in facial emotional expression during a discrimination task. 'El papel de la am??gdala en una tarea de discriminaci??n de expresiones emocionales'

Resumen tomado de la publicaci??n. Resumen tambi??n en ingl??s

Capacidades de discriminaci??n fon??tica de un contraste voc??lico nativo en el prematuro

Resumen tomado de la publicaci??n

Emoci??n y memoria de reconocimiento : la discriminaci??n de la informaci??n negativa como un proceso adaptativo

Resumen tomado de la publicaci??n

El desenvolupament auditiu : la discriminació de la informació acústica de l'entorn viari. 'El desarrollo auditivo : la discriminación de la información acústica del entorno viario'.

Obtener algunas conclusiones sobre el desarrollo auditivo humano que nos permitan diseñar pautas para la elaboración de un programa de educación vial dirigido a niños de edades comprendidas entre los 6 y los 11 años. 86 niños de 6 años, 67 de 7 años, 80 de 8 años, 46 de 9 años, 72 de 10 años, 48 de 11 años y 128 adultos; la mitad aproximadamente féminas y la mitad hombres; la mitad aproximadamente procedente de zonas rurales y la mitad de zona urbana. Se tuvieron en cuenta fundamentalmente cuatro variables: la edad, el sexo, la zona de residencia y la presencia de algún tipo de hipoacusia (un oído o ambos oídos); se realizó una audiometría a todos los participantes. Se diseñó una batería de pruebas basadas en la discriminación de sonidos, la identificación de sonidos del entorno vial, la asociación de sonidos a ilustraciones, la percepción auditiva del movimiento en distancia, la percepción del riesgo a partir de la información auditiva y la atención visual selectiva. Se administró la batería de pruebas en salas adecuadamente aisladas de sonidos del exterior. Todas las pruebas se realizaron en soportes informáticos que permitían el registro directo del tiempo de reacción y del número de errores; estas dos variables dependientes son las que se utilizaron en el posterior análisis de los datos. Los niños mayores de 8 años obtuvieron umbrales auditivos similares a los de los adultos, los de 6 y 7 años mostraban umbrales significativamente superiores; en las pruebas de reconocimiento y asociación de sonidos a ilustraciones no aparecieron diferencias por edades; en la percepción auditiva de movimiento se formaron tres grupos según su nivel de competencia: 6-7 años, 8-11 años y adultos. Los niños de la zona rural obtenían mejores resultados que los de ciudad, excepto en los cambios de frecuencia, en los que los de ciudad obtenían valores más precisos; los niños no cometen más situaciones arriesgadas que los adultos en una prueba de percepción del riesgo a partir de la información auditiva, sin embargo, desaprovechan más oportunidades de cruzar la calle. El origen de las diferencias comportamentales según la edad parece provenir de la capacidad de percepción auditiva del movimiento en distancia y en la nula competencia de los niños menores de 9 años para usar los cambios tonales.

Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images.

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.

Visual Navigation In The Neotropical Ant Odontomachus Hastatus (formicidae, Ponerinae), A Predominantly Nocturnal, Canopy-dwelling Predator Of The Atlantic Rainforest.

The arboreal ant Odontomachus hastatus nests among roots of epiphytic bromeliads in the sandy forest at Cardoso Island (Brazil). Crepuscular and nocturnal foragers travel up to 8m to search for arthropod prey in the canopy, where silhouettes of leaves and branches potentially provide directional information. We investigated the relevance of visual cues (canopy, horizon patterns) during navigation in O. hastatus. Laboratory experiments using a captive ant colony and a round foraging arena revealed that an artificial canopy pattern above the ants and horizon visual marks are effective orientation cues for homing O. hastatus. On the other hand, foragers that were only given a tridimensional landmark (cylinder) or chemical marks were unable to home correctly. Navigation by visual cues in O. hastatus is in accordance with other diurnal arboreal ants. Nocturnal luminosity (moon, stars) is apparently sufficient to produce contrasting silhouettes from the canopy and surrounding vegetation, thus providing orientation cues. Contrary to the plain floor of the round arena, chemical cues may be important for marking bifurcated arboreal routes. This experimental demonstration of the use of visual cues by a predominantly nocturnal arboreal ant provides important information for comparative studies on the evolution of spatial orientation behavior in ants. This article is part of a Special Issue entitled: Neotropical Behaviour.

Applications Of Visual Evoked Potentials And Fourier-domain Optical Coherence Tomography In Parkinson's Disease: A Controlled Study.

The goal of this cross-sectional observational study was to quantify the pattern-shift visual evoked potentials (VEP) and the thickness as well as the volume of retinal layers using optical coherence tomography (OCT) across a cohort of Parkinson's disease (PD) patients and age-matched controls. Forty-three PD patients and 38 controls were enrolled. All participants underwent a detailed neurological and ophthalmologic evaluation. Idiopathic PD cases were included. Cases with glaucoma or increased intra-ocular pressure were excluded. Patients were assessed by VEP and high-resolution Fourier-domain OCT, which quantified the inner and outer thicknesses of the retinal layers. VEP latencies and the thicknesses of the retinal layers were the main outcome measures. The mean age, with standard deviation (SD), of the PD patients and controls were 63.1 (7.5) and 62.4 (7.2) years, respectively. The patients were predominantly in the initial Hoehn-Yahr (HY) disease stages (34.8% in stage 1 or 1.5, and 55.8 % in stage 2). The VEP latencies and the thicknesses as well as the volumes of the retinal inner and outer layers of the groups were similar. A negative correlation between the retinal thickness and the age was noted in both groups. The thickness of the retinal nerve fibre layer (RNFL) was 102.7 μm in PD patients vs. 104.2 μm in controls. The thicknesses of retinal layers, VEP, and RNFL of PD patients were similar to those of the controls. Despite the use of a representative cohort of PD patients and high-resolution OCT in this study, further studies are required to establish the validity of using OCT and VEP measurements as the anatomic and functional biomarkers for the evaluation of retinal and visual pathways in PD patients.

Physical Activity Interventions For Children And Youth With Visual Impairments.

The authors conducted a systematic literature review on physical activity interventions for children and youth with visual impairment (VI). Five databases were searched to identify studies involving the population of interest and physical activity practices. After evaluating 2,495 records, the authors found 18 original full-text studies published in English they considered eligible. They identified 8 structured exercise-training studies that yielded overall positive effect on physical-fitness and motor-skill outcomes. Five leisure-time-physical-activity and 5 instructional-strategy interventions were also found with promising proposals to engage and instruct children and youth with VI to lead an active lifestyle. However, the current research on physical activity interventions for children and youth with VI is still limited by an absence of high-quality research designs, low sample sizes, use of nonvalidated outcome measures, and lack of generalizability, which need to be addressed in future studies.