A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

In this work, we investigate the visual appearance of real-world surfaces and the dependence of appearance on the geometry of imaging conditions. We discuss a new texture representation called the BTF (bidirectional texture function) which captures the variation in texture with illumination and viewing direction. We present a BTF database with image textures from over 60 different samples, each observed with over 200 different combinations of viewing and illumination directions. We describe the methods involved in collecting the database as well as the importqance and uniqueness of this database for computer graphics. A related quantity to the BTF is the familiar BRDF (bidirectional reflectance distribution function). The measurement methods involved in the BTF database are conducive to simultaneous measurement of the BRDF. Accordingly, we also present a BRDF database with reflectance measurements for over 60 different samples, each observed with over 200 different combinations of viewing and illumination directions. Both of these unique databases are publicly available and have important implications for computer graphics.

/pdf/reflectance-and-texture-of-real-world-surfaces-571ardcyvm.pdf

Reflectance and texture of real-world surfaces

To be diagnostically useful, structural MRI must reliably distinguish Alzheimer's disease (AD) from normal aging in individual scans. Recent advances in statistical learning theory have led to the application of support vector machines to MRI for detection of a variety of disease states. The aims of this study were to assess how successfully support vector machines assigned individual diagnoses and to determine whether data-sets combined from multiple scanners and different centres could be used to obtain effective classification of scans. We used linear support vector machines to classify the grey matter segment of T1-weighted MR scans from pathologically proven AD patients and cognitively normal elderly individuals obtained from two centres with different scanning equipment. Because the clinical diagnosis of mild AD is difficult we also tested the ability of support vector machines to differentiate control scans from patients without post-mortem confirmation. Finally we sought to use these methods to differentiate scans between patients suffering from AD from those with frontotemporal lobar degeneration. Up to 96% of pathologically verified AD patients were correctly classified using whole brain images. Data from different centres were successfully combined achieving comparable results from the separate analyses. Importantly, data from one centre could be used to train a support vector machine to accurately differentiate AD and normal ageing scans obtained from another centre with different subjects and different scanner equipment. Patients with mild, clinically probable AD and age/sex matched controls were correctly separated in 89% of cases which is compatible with published diagnosis rates in the best clinical centres. This method correctly assigned 89% of patients with post-mortem confirmed diagnosis of either AD or frontotemporal lobar degeneration to their respective group. Our study leads to three conclusions: Firstly, support vector machines successfully separate patients with AD from healthy aging subjects. Secondly, they perform well in the differential diagnosis of two different forms of dementia. Thirdly, the method is robust and can be generalized across different centres. This suggests an important role for computer based diagnostic image analysis for clinical practice.

/pdf/automatic-classification-of-mr-scans-in-alzheimer-s-disease-470bmllki1.pdf

Automatic classification of MR scans in Alzheimer's disease

A user can access a common database from a remote communications port, at any qualified location, to generate a map or other positional information which locates selected items of interest, e.g., businesses, stores, architectural sites, and the like. The database contains information representing the items of interest, including, for each of the items of interest, positional coordinates, a geographic vicinity, and a selected category. The positional coordinates discretely locate the vicinity, while the vicinity specifies the exact locations of the items of interest in the selected category. For example, a user in New York can select the display of sporting shops in the area surrounding Chicago O'Hara International Airport selectively. A user can also access a port and display locations of items of interest within the same vicinity as the user and relative to the user's position. The database can be modified from qualified remote locations to change, or add to, the information therein. An advertisement can be tagged to the display or print out as an association with the selected items of interest.

System and methods for remotely accessing a selected group of items of interest from a database

A theory of photometric stereo is proposed for a large class of non-Lambertian reflectance maps. The authors review the different reflectance maps proposed in the literature for modeling reflection from real-world surfaces. From this, they obtain a mathematical class of reflectance maps to which the maps belong. They show that three lights can be sufficient for a unique inversion of the photometric stereo equation for the entire class of reflectance maps. They also obtain a constraint on the positions of light sources for obtaining this solution. They investigate the sufficiency of three light sources to estimate the surface normal and the illuminant strength. The issue of completeness of reconstruction is addressed. They show that if k lights are sufficient for a unique inversion, 2k lights are necessary for a complete inversion. >

A theory of photometric stereo for a class of diffuse non-Lambertian surfaces

Methods and apparatus for fusion of data from optical and radar sensors by error minimization procedure. The method has been applied to the problem of shape reconstruction of an unknown surface at a distance. The method involves deriving an incomplete surface model from an optical sensor. The unknown characteristics of the surface are represented by some parameter. The correct value of the parameter is computed by iteratively generating theoretical predictions of the Radar cross-sections (RCS) of the surface, comparing the predicted and the observed values for the RCS, and improving the surface model from results of the comparison. Theoretical RCS may be computed from the surface model in several ways. One RCS prediction technique is the method of moments. The method of moments can be applied to an unknown surface only if some shape information is available from an independent source. The optical image provides the independent information.

/pdf/method-and-apparatus-for-sensor-fusion-4elapg7jlb.pdf

Method and apparatus for sensor fusion

Single photon emission with computed tomography (SPECT) hexamethylphenylethyleneamineoxime technetium-99 images were analyzed by an optimal interpolative neural network (OINN) algorithm to determine whether the network could discriminate among clinically diagnosed groups of elderly normal, Alzheimer disease (AD), and vascular dementia (VD) subjects. After initial image preprocessing and registration, image features were obtained that were representative of the mean regional tissue uptake. These features were extracted from a given image by averaging the intensities over various regions defined by suitable masks. After training, the network classified independent trials of patients whose clinical diagnoses conformed to published criteria for probable AD or probable/possible VD. For the SPECT data used in the current tests, the OINN agreement was 80 and 86% for probable AD and probable/possible VD, respectively. These results suggest that artificial neural network methods offer potential in diagnoses from brain images and possibly in other areas of scientific research where complex patterns of data may have scientifically meaningful groupings that are not easily identifiable by the researcher.

https://www.pnas.org/content/pnas/92/12/5530.full.pdf

Neural-network-based classification of cognitively normal, demented, Alzheimer disease and vascular dementia from single photon emission with computed tomography image data from brain.

Original Contribution: Efficient learning procedures for optimal interpolative nets

This paper investigates whether the shape of an object and certain parameters of its reflectance map can be simultaneously estimated using photometric stereo. This problem has been addressed in the literature for the case where the Lambertian and non-Lambertian components in the image can be easily separated. No such separability is assumed in this paper. A class of reflectance maps for modeling diffusely reflecting surfaces is proposed. This class is based on the physics of scattering from real world surfaces. Next, the problem of joint estimation of some parameters of the map along with the surface shape is analyzed. A bound is obtained on the number of light sources necessary for a unique solution to the problem. The analysis also reveals that some of the estimates can be obtained by a nonparametric method. The behavior of the estimates in the presence of noise is also investigated. It is shown that simultaneous estimation is ill-posed. Regularizing the estimates yields good reconstructions from real world data.

Rui J. P. deFigueiredo

Papers

A theory of photometric stereo for a class of diffuse non-Lambertian surfaces

Method and apparatus for sensor fusion

Neural-network-based classification of cognitively normal, demented, Alzheimer disease and vascular dementia from single photon emission with computed tomography image data from brain.

Original Contribution: Efficient learning procedures for optimal interpolative nets

Simultaneous estimation of shape and reflectance map from photometric stereo