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

Animate vision

A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds. An edge-preserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate estimate of the image gradient. Then, an initial partitioning of the image into primitive regions is produced by applying the watershed transform on the image gradient magnitude. This initial segmentation is the input to a computationally efficient hierarchical (bottom-up) region merging process that produces the final segmentation. The latter process uses the region adjacency graph (RAG) representation of the image regions. At each step, the most similar pair of regions is determined (minimum cost RAG edge), the regions are merged and the RAG is updated. Traditionally, the above is implemented by storing all RAG edges in a priority queue. We propose a significantly faster algorithm, which additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, one-pixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with two-dimensional/three-dimensional (2-D/3-D) magnetic resonance images are presented.

Hybrid image segmentation using watersheds and fast region merging

A general technique for the recovery of significant image features is presented. The technique is based on the mean shift algorithm, a simple nonparametric procedure for estimating density gradients. Drawbacks of the current methods (including robust clustering) are avoided. Feature space of any nature can be processed, and as an example, color image segmentation is discussed. The segmentation is completely autonomous, only its class is chosen by the user. Thus, the same program can produce a high quality edge image, or provide, by extracting all the significant colors, a preprocessor for content-based query systems. A 512/spl times/512 color image is analyzed in less than 10 seconds on a standard workstation. Gray level images are handled as color images having only the lightness coordinate.

Robust analysis of feature spaces: color image segmentation

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

We present an interpretation system which utilizes world knowledge in the form of simple object hypothesis rules, and more complex interpretation strategies attached to object and scene schemata, to reduce the ambiguities in image measurements. These rules involve sets of partially redundant features each of which defines an area of feature space which represents a "vote" for an object. Convergent evidence from multiple interpretation strategies is organized by top-down control mechanisms in the context of a partial interpretation. One such strategy extends a kernel interpretation derived through the selection of object exemplars, which represent the most reliable image specific hypotheses of a general object class, resulting in the extension of partial interpretations from islands of reliability.

J. S. Griffith

Papers

Segmenting Images Using Localized Histograms and Region Merging

Rule based strategies for image interpretation