Learn More
We present two novel methods for face verification. Our first method – " attribute " classifiers – uses binary classi-fiers trained to recognize the presence or absence of de-scribable aspects of visual appearance (e.g., gender, race, and age). Our second method – " simile " classifiers – removes the manual labeling required for attribute classification and(More)
We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a nonparametric set of global models for the part locations based on over 1,000 hand-labeled exemplar images. By assuming that the global models generate the part locations as hidden variables, we derive a Bayesian objective(More)
We introduce the use of describable visual attributes for face verification and image search. Describable visual attributes are labels that can be given to an image to describe its appearance. This paper focuses on images of faces and the attributes used to describe them, although the concepts also apply to other domains. Examples of face attributes include(More)
In this paper, we present a complete system for automatic face replacement in images. Our system uses a large library of face images created automatically by downloading images from the internet, extracting faces using face detection software, and aligning each extracted face to a common coordinate system. This library is constructed off-line, once, and can(More)
We have created the first image search engine based entirely on faces. Using simple text queries such as " smiling men with blond hair and mustaches, " users can search through over 3.1 million faces which have been automatically labeled on the basis of several facial attributes. Faces in our database have been extracted and aligned from images down-loaded(More)
We describe the first mobile app for identifying plant species using automatic visual recognition. The system – called Leafsnap – identifies tree species from photographs of their leaves. Key to this system are computer vision components for discarding non-leaf images, segmenting the leaf from an untextured background, extracting features representing the(More)
Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in(More)
Many computer vision algorithms require searching a set of images for similar patches, which is a very expensive operation. In this work, we compare and evaluate a number of nearest neighbors algorithms for speeding up this task. Since image patches follow very different distributions from the uniform and Gaussian distributions that are typically used to(More)
must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Abstract For identity related problems, descriptive(More)
The authenticated key agreement protocol is an important security protocol for the session initiation protocol, which allows the and the server to authenticate each other and generate a shared session key for privacy, integrity , and non-repudiation in their communications. Recently, Zhang et al. proposed a new authenticated key agreement protocol for the(More)