David W. Jacobs

Shape Classification Using the Inner-Distance

Part structure and articulation are of fundamental importance in computer and human vision. We propose using the inner-distance to build shape descriptors that are robust to articulation and capture part structure. The inner-distance is defined as the length of the shortest path between landmark points within the shape silhouette. We show that it is articulation insensitive and more effective at capturing part structures than the Euclidean distance. This suggests that the inner-distance can be used as a replacement for the Euclidean distance to build more accurate descriptors for complex shapes, especially for those with articulated parts. In addition, texture information along the shortest path can be used to further improve shape classification. With this idea, we propose three approaches to using the inner-distance. The first method combines the inner-distance and multidimensional scaling (MDS) to build articulation invariant signatures for articulated shapes. The second method uses the inner-distance to build a new shape descriptor based on shape contexts. The third one extends the second one by considering the texture information along shortest paths. The proposed approaches have been tested on a variety of shape databases, including an articulated shape data set, MPEG7 CE-Shape-1, Kimia silhouettes, the ETH-80 data set, two leaf data sets, and a human motion silhouette data set. In all the experiments, our methods demonstrate effective performance compared with other algorithms

Mesh saliency

Research over the last decade has built a solid mathematical foundation for representation and analysis of 3D meshes in graphics and geometric modeling. Much of this work however does not explicitly incorporate models of low-level human visual attention. In this paper we introduce the idea of mesh saliency as a measure of regional importance for graphics meshes. Our notion of saliency is inspired by low-level human visual system cues. We define mesh saliency in a scale-dependent manner using a center-surround operator on Gaussian-weighted mean curvatures. We observe that such a definition of mesh saliency is able to capture what most would classify as visually interesting regions on a mesh. The human-perception-inspired importance measure computed by our mesh saliency operator results in more visually pleasing results in processing and viewing of 3D meshes. compared to using a purely geometric measure of shape. such as curvature. We discuss how mesh saliency can be incorporated in graphics applications such as mesh simplification and viewpoint selection and present examples that show visually appealing results from using mesh saliency.

Localizing parts of faces using a consensus of exemplars

We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a non-parametric set of global models for the part locations based on over one thousand hand-labeled exemplar images. By assuming that the global models generate the part locations as hidden variables, we derive a Bayesian objective function. This function is optimized using a consensus of models for these hidden variables. The resulting localizer handles a much wider range of expression, pose, lighting and occlusion than prior ones. We show excellent performance on a new dataset gathered from the internet and show that our localizer achieves state-of-the-art performance on the less challenging BioID dataset.

Automatic thumbnail cropping and its effectiveness

Thumbnail images provide users of image retrieval and browsing systems with a method for quickly scanning large numbers of images. Recognizing the objects in an image is important in many retrieval tasks, but thumbnails generated by shrinking the original image often render objects illegible. We study the ability of computer vision systems to detect key components of images so that automated cropping, prior to shrinking, can render objects more recognizable. We evaluate automatic cropping techniques 1) based on a general method that detects salient portions of images, and 2) based on automatic face detection. Our user study shows that these methods result in small thumbnails that are substantially more recognizable and easier to find in the context of visual search.

Stochastic completion fields: a neural model of illusory contour shape and salience

We describe an algorithm and representation-level theory of illusory contour shape and salience. Unlike previous theories, our model is derived from a single assumption: that the prior probability distribution of boundary completion shape can be modeled by a random walk in a lattice whose points are positions and orientations in the image plane (i.e., the space that one can reasonably assume is represented by neurons of the mammalian visual cortex). Our model does not employ numerical relaxation or other explicit minimization, but instead relies on the fact that the probability that a particle following a random walk will pass through a given position and orientation on a path joining two boundary fragments can be computed directly as the product of two vector-field convolutions. We show that for the random walk we define, the maximum likelihood paths are curves of least energy, that is, on average, random walks follow paths commonly assumed to model the shape of illusory contours. A computer model is demonstrated on numerous illusory contour stimuli from the literature.

Generalized Multiview Analysis: A discriminative latent space

This paper presents a general multi-view feature extraction approach that we call Generalized Multiview Analysis or GMA. GMA has all the desirable properties required for cross-view classification and retrieval: it is supervised, it allows generalization to unseen classes, it is multi-view and kernelizable, it affords an efficient eigenvalue based solution and is applicable to any domain. GMA exploits the fact that most popular supervised and unsupervised feature extraction techniques are the solution of a special form of a quadratic constrained quadratic program (QCQP), which can be solved efficiently as a generalized eigenvalue problem. GMA solves a joint, relaxed QCQP over different feature spaces to obtain a single (non)linear subspace. Intuitively, GMA is a supervised extension of Canonical Correlational Analysis (CCA), which is useful for cross-view classification and retrieval. The proposed approach is general and has the potential to replace CCA whenever classification or retrieval is the purpose and label information is available. We outperform previous approaches for textimage retrieval on Pascal and Wiki text-image data. We report state-of-the-art results for pose and lighting invariant face recognition on the MultiPIE face dataset, significantly outperforming other approaches.

In search of illumination invariants

We consider the problem of determining functions of an image of an object that are insensitive to illumination changes. We first show that for an object with Lambertian reflectance there are no discriminative functions that are invariant to illumination. This result leads as to adopt a probabilistic approach in which we analytically determine a probability distribution for the image gradient as a function of the surfaces geometry and reflectance. Our distribution reveals that the direction of the image gradient is insensitive to changes in illumination direction. We verify this empirically by constructing a distribution for the image gradient from more than 20 million samples of gradients in a database of 1,280 images of 20 inanimate objects taken under varying lighting condition. Using this distribution we develop an illumination insensitive measure of image comparison and test it on the problem of face recognition.

Leafsnap: a computer vision system for automatic plant species identification

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 curvature of the leafs contour over multiple scales, and identifying the species from a dataset of the 184 trees in the Northeastern United States. Our system obtains state-of-the-art performance on the real-world images from the new Leafsnap Dataset --- the largest of its kind. Throughout the paper, we document many of the practical steps needed to produce a computer vision system such as ours, which currently has nearly a million users.

Photometric Stereo with General, Unknown Lighting

Work on photometric stereo has shown how to recover the shape and reflectance properties of an object using multiple images taken with a fixed viewpoint and variable lighting conditions. This work has primarily relied on known lighting conditions or the presence of a single point source of light in each image. In this paper we show how to perform photometric stereo assuming that all lights in a scene are distant from the object but otherwise unconstrained. Lighting in each image may be an unknown and may include arbitrary combination of diffuse, point and extended sources. Our work is based on recent results showing that for Lambertian objects, general lighting conditions can be represented using low order spherical harmonics. Using this representation we can recover shape by performing a simple optimization in a low-dimensional space. We also analyze the shape ambiguities that arise in such a representation. We demonstrate our method by reconstructing the shape of objects from images obtained under a variety of lightings. We further compare the reconstructed shapes against shapes obtained with a laser scanner.

Determining the similarity of deformable shapes

Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify objects. The exact properties of human shape similarity judgements are not well understood yet, and this task is particularly difficult in domains where the shapes are not related by rigid transformation. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the contours of the shapes, through elastic matching. Special attention is devoted to objects that possess articulations, i.e. articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show that similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of importance, since although parts appear to play a significant role in visual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyhedral shapes with the same method. Finally, we describe shape similarity effects that cannot be handled by current approaches.