Most face databases have been created under controlled conditions to facilitate the study of specific parameters on the face recognition problem. These parameters include such variables as position, pose, lighting, background, camera quality, and gender. While there are many applications for face recognition technology in which one can control the parameters of image acquisition, there are also many applications in which the practitioner has little or no control over such parameters. This database, Labeled Faces in the Wild, is provided as an aid in studying the latter, unconstrained, recognition problem. The database contains labeled face photographs spanning the range of conditions typically encountered in everyday life. The database exhibits “natural” variability in factors such as pose, lighting, race, accessories, occlusions, and background. In addition to describing the details of the database, we provide specific experimental paradigms for which the database is suitable. This is done in an effort to make research performed with the database as consistent and comparable as possible. We provide baseline results, including results of a state of the art face recognition system combined with a face alignment system. To facilitate experimentation on the database, we provide several parallel databases, including an aligned version.

/pdf/labeled-faces-in-the-wild-a-database-forstudying-face-2prti1m53k.pdf

Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments

We present a novel statistical and variational approach to image segmentation based on a new algorithm, named region competition. This algorithm is derived by minimizing a generalized Bayes/minimum description length (MDL) criterion using the variational principle. The algorithm is guaranteed to converge to a local minimum and combines aspects of snakes/balloons and region growing. The classic snakes/balloons and region growing algorithms can be directly derived from our approach. We provide theoretical analysis of region competition including accuracy of boundary location, criteria for initial conditions, and the relationship to edge detection using filters. It is straightforward to generalize the algorithm to multiband segmentation and we demonstrate it on gray level images, color images and texture images. The novel color model allows us to eliminate intensity gradients and shadows, thereby obtaining segmentation based on the albedos of objects. It also helps detect highlight regions.

Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation

Device-to-device (D2D) communications was initially proposed in cellular networks as a new paradigm for enhancing network performance. The emergence of new applications such as content distribution and location-aware advertisement introduced new user cases for D2D communications in cellular networks. The initial studies showed that D2D communications has advantages such as increased spectral efficiency and reduced communication delay. However, this communication mode introduces complications in terms of interference control overhead and protocols that are still open research problems. The feasibility of D2D communications in Long-Term Evolution Advanced is being studied by academia, industry, and standardization bodies. To date, there are more than 100 papers available on D2D communications in cellular networks, but there is no survey on this field. In this paper, we provide a taxonomy based on the D2D communicating spectrum and review the available literature extensively under the proposed taxonomy. Moreover, we provide new insights into the over-explored and under-explored areas that lead us to identify open research problems of D2D communications in cellular networks.

https://eprints.networks.imdea.org/id/document/2488

A Survey on Device-to-Device Communication in Cellular Networks

Animate vision

Although the study of visual perception has made more progress in the past 40 years than any other area of cognitive science, there remain major disagreements as to how closely vision is tied to cognition. This target article sets out some of the arguments for both sides (arguments from computer vision, neuroscience, psychophysics, perceptual learning, and other areas of vision science) and defends the position that an important part of visual perception, corresponding to what some people have called early vision, is prohibited from accessing relevant expectations, knowledge, and utilities in determining the function it computes - in other words, it is cognitively im- penetrable. That part of vision is complex and involves top-down interactions that are internal to the early vision system. Its function is to provide a structured representation of the 3-D surfaces of objects sufficient to serve as an index into memory, with somewhat differ- ent outputs being made available to other systems such as those dealing with motor control. The paper also addresses certain concep- tual and methodological issues raised by this claim, such as whether signal detection theory and event-related potentials can be used to assess cognitive penetration of vision. A distinction is made among several stages in visual processing, including, in addition to the inflexible early-vision stage, a pre-per- ceptual attention-allocation stage and a post-perceptual evaluation, selection, and inference stage, which accesses long-term memory. These two stages provide the primary ways in which cognition can affect the outcome of visual perception. The paper discusses argu- ments from computer vision and psychology showing that vision is "intelligent" and involves elements of "problem solving." The cases of apparently intelligent interpretation sometimes cited in support of this claim do not show cognitive penetration; rather, they show that certain natural constraints on interpretation, concerned primarily with optical and geometrical properties of the world, have been com- piled into the visual system. The paper also examines a number of examples where instructions and "hints" are alleged to affect what is seen. In each case it is concluded that the evidence is more readily assimilated to the view that when cognitive effects are found, they have a locus outside early vision, in such processes as the allocation of focal attention and the identification of the stimulus.

/pdf/is-vision-continuous-with-cognition-the-case-for-cognitive-t2qx5udnjk.pdf

Is vision continuous with cognition? The case for cognitive impenetrability of visual perception

THIS PAPER DESCRIBES A WORKING SYSTEM FOR SEGMENTING IMAGES OF COMPLEX SCENES. THE SYSTEM HAS EVOLVED OUT OF MANY YEARS OF RESEARCH IN LOW-LEVEL IMAGE SEGMENTATION AT THE UNIVERSITY OF MASSACHUSETTS. SEGMENTATIONS PRODUCED BY THE SYSTEM ARE USED EXTENSIVELY IN THE IMAGE INTERPRETATION WORK HERE. THE SYSTEM FIRST PRODUCES SEGMENTATIONS BASED UPON AN ANALYSIS OF SPATIALLY LOCALIZED FEATURE HISTOGRAMS. THESE SEGMENTATIONS ARE THEN POST-PROCESSED WITH A REGION MERGING ALGORITHM. A SIMPLE EXTENSION OF THE LOCAL HISTOGRAM ALGORITHM TO MULTIPLE FEATURES IS PRESENTED. ISSUES OF PARAMETER SELECTION FOR THE LOCAL HISTOGRAM SEGMENTATION ALGORITHM ARE ADDRESSED BY PRESENTING A MAPPING FROM THE MULTI-DIMENSIONAL PARAMETER SPACE TO A ONE DIMENSIONAL `SENSITIVITY'' SPACE. RESULTS ARE INCLUDED WHICH DEMONSTRATE THE ROBUST CHARACTER OF THE ALGORITHMS WHEN APPLIED TO OUTDOOR AND AERIAL IMAGERY.

Segmenting Images Using Localized Histograms and Region Merging

The authors report on the system and methods used by UMass Mobile Robot Project. Model-based processing of the visual sensory data is the primary mechanism used for controlling movement of an autonomous land vehicle through the environment, measuring progress towards a given goal, and avoiding obstacles. Goal-oriented navigation takes place through a partially modeled, unchanging environment that contains no unmodeled obstacles; this simplified environment provides a foundation for research in more complicated domains. The navigation system integrates perception, planning, and execution of actions. Of particular importance is that the planning processes are reactive and reason about landmarks that should be perceived at various stages of task execution. Correspondence between image features and expected landmark locations are used at several abstraction levels to ensure proper plan execution. The system and some experiments that demonstrate the performance of its components is described. >

Model-directed mobile robot navigation

Local search is a well established and highly effective method for solving complex combinatorial optimization problems. Here, local search is adapted to solve difficult geometric matching problems. Matching is posed as the problem of finding the optimal many-to-many correspondence mapping between a line segment model and image line segments. Image data is assumed to be fragmented, noisy, and cluttered. The algorithms presented have been used for robot navigation, photo interpretation, and scene understanding. This paper explores how local search performs as model complexity increases, image clutter increases, and additional model instances are added to the image data. Expected run-times to find optimal matches with 95 percent confidence are determined for 48 distinct problems involving six models. Nonlinear regression is used to estimate run-time growth as a function of problem size. Both polynomial and exponential growth models are fit to the run-time data. For problems with random clutter, the polynomial model fits better and growth is comparable to that for tree search. For problems involving symmetric models and multiple model instances, where tree search is exponential, the polynomial growth model is superior to the exponential growth model for one search algorithm and comparable for another.

/pdf/how-easy-is-matching-2d-line-models-using-local-search-2h2i3ds9as.pdf

How easy is matching 2D line models using local search

Expert system technology, especially techniques for rule-based knowledge engineering, has been successfully applied to many practical problems. Although there are inherent limitations in the complexity and power that can be achieved with traditional expert system approaches (Davis 1982), particularly when the number of rules is not constrained, there has been little evidence of its application to image interpretation. Typically, vision systems are highly system or application dependent and consequently it has been difficult to transfer them to different task domains. For example, there have been several systems developed for applications with aerial or satellite images (Bajcsy and Tavakoli 1976; Ballard et al. 1978; Faugeras and Price 1981; Nagao and Matsuyama 1980) but these systems have not been applied to other domains such as industrial scenes, medical applications, or road scenes. Only a few research efforts (Brooks 1981; Hanson and Riseman 1978c) have attempted to bridge task domains. We believe that a system employing a general methodology will be required if a large number of industrial applications are to be solved without requiring the construction of a customized system for each application. The bulk of this chapter will use results from outdoor scenes, specifically house scenes. However, we believe that our methodology can be applied in a straightforward manner to complex industrial applications by changing the knowledge base associated with the set of objects to be recognized. In an effort to motivate the reader to provide a sense of the potential, in the next section we have included the output of low-level algorithms applied to images of industrial parts.

A methodology for the development of general knowledge-based vision systems

An important and difficult problem in computer vision is to determine 2D image feature correspondences over a set of images. In this paper, two new affinity measures for image points and lines from different images are presented, and are used to construct unweighted and weighted bipartite graphs. It is shown that the image feature matching problem can be reduced to an unweighted matching problem in the bipartite graphs. It is further shown that the problem can be formulated as the general maximum-weight bipartite matching problem, thus generalizing the above unweighted bipartite matching technique.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Edward M. Riseman

Papers

Segmenting Images Using Localized Histograms and Region Merging

Model-directed mobile robot navigation

How easy is matching 2D line models using local search

A methodology for the development of general knowledge-based vision systems

Maximum-weight bipartite matching technique and its application in image feature matching