Discovering Viewpoint-Invariant Relationships That Characterize Objects
نویسندگان
چکیده
Using an unsupervised learning procedure, a network is trained on an ensemble of images of the same two-dimensional object at different positions, orientations and sizes. Each half of the network "sees" one fragment of the object, and tries to produce as output a set of 4 parameters that have high mutual information with the 4 parameters output by the other half of the network. Given the ensemble of training patterns, the 4 parameters on which the two halves of the network can agree are the position, orientation, and size of the whole object, or some recoding of them. After training, the network can reject instances of other shapes by using the fact that the predictions made by its two halves disagree. If two competing networks are trained on an unlabelled mixture of images of two objects, they cluster the training cases on the basis of the objects' shapes, independently of the position, orientation, and size.
منابع مشابه
∆-TSR: a description of spatial relationships between objects for image retrieval∗
This article presents ∆-TSR, a new image content representation exploiting the spatial relationships existing between its objects of interest. This approach provides two types of descriptions: with ∆-TSR3D, images are represented by geometric relationships between triplets of objects using triangle angles, while ∆-TSR5D enriches ∆-TSR3D by exploiting the orientation of the objects. The approach...
متن کاملClass-Based Grouping in Perspective Images
In any object recognition system a major and primary task is to associate those image features, within an image of a complex scene, that arise from an individual object. The key idea here is that a geometric class deened in 3D induces relationships in the image which must hold between points on the image outline (the perspective projection of the object). The resulting image constraints enable ...
متن کاملPlanar Shape Databases with Affine Invariant Search
Image databases are often used to archive and retrieve images containing man-made 3D objects usually taken from arbitrary viewpoints. These objects generally incorporate planar surfaces containing different kinds of highly curved patterns. It is often the case that the form of such patterns characterizes well the corresponding object. Besides classical retrieval by colour or texture, the databa...
متن کاملShape-based instance detection under arbitrary viewpoint
Shape-based instance detection under arbitrary viewpoint is a very challenging problem. Current approaches for handling viewpoint variation can be divided into two main categories: invariant and non-invariant. Invariant approaches explicitly represent the structural relationships of high-level, view-invariant shape primitives. Non-invariant approaches, on the other hand, create a template for e...
متن کاملEffect of silhouetting and inversion on view invariance in the monkey inferotemporal cortex
We effortlessly recognize objects across changes in viewpoint, but we know relatively little about the features that underlie viewpoint invariance in the brain. Here, we set out to characterize how viewpoint invariance in monkey inferior temporal (IT) neurons is influenced by two image manipulations-silhouetting and inversion. Reducing an object into its silhouette removes internal detail, so t...
متن کامل