Selecting canonical views for view-based 3-D object recognition

Denton, Trip; Demirci, M. Fatih; Abrahamson, Jeff; Shokoufandeh, Ali; Dickinson, Sven

doi:10.1109/icpr.2004.1334159

Cited by 29 publications

(26 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This problem has been addressed both in psychology [18,5] and computer vision literature [4,7,10,23]. Existing approaches have formulated many different criteria for canonical view selection, some of which are applicable to general and abstract categories (e.g., the canonical view should be similar to many other images in the collection), while others only make sense for objects with a well-defined geometry (e.g., different canonical views should be orthogonal to each other).…”

Section: Related Workmentioning

confidence: 99%

Computing iconic summaries of general visual concepts

Raguram¹,

Lazebnik²

2008

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

This paper considers the problem of selecting iconic images to summarize general visual categories. We define iconic images as high-quality representatives of a large group of images consistent both in appearance and semantics. To find such groups, we perform joint clustering in the space of global image descriptors and latent topic vectors of tags associated with the images. To select the representative iconic images for the joint clusters, we use a quality ranking learned from a large collection of labeled images. For the purposes of visualization, iconic images are grouped by semantic "theme" and multidimensional scaling is used to compute a 2D layout that reflects the relationships between the themes. Results on four large-scale datasets demonstrate the ability of our approach to discover plausible themes and recurring visual motifs for challenging abstract concepts such as "love" and "beauty."

show abstract

Section: Related Workmentioning

confidence: 99%

Computing iconic summaries of general visual concepts

Raguram¹,

Lazebnik²

2008

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

show abstract

“…Aspect graphs are problematic to compute for paper clips because of their lack of self-occlusion. Similarly, feature-based methods (Denton, Demirci, Abrahamson, Shokoufandeh, & Dickinson, 2004) are also difficult to use, since many features of a paper clip are highly unstable because of the sparse wire-frame structure of the object. Foreshortening is easily applicable to these objects and, more important, provides a straightforward means of investigating the contribution of sequence-based terms in determining view canonicality.…”

Section: Methodsmentioning

confidence: 99%

The role of sequence order in determining view canonicality for novel wire-frame objects

Balas

Sinha

2009

Attention, Perception, & Psychophysics

View full text Add to dashboard Cite

Objects are best recognized from so-called "canonical" views. The characteristics of canonical views of arbitrary objects have been qualitatively described using a variety of different criteria, but little is known regarding how these views might be acquired during object learning. We address this issue, in part, by examining the role of object motion in the selection of preferred views of novel objects. Specifically, we adopt a modeling approach to investigate whether or not the sequence of views seen during initial exposure to an object contributes to observers' preferences for particular images in the sequence. In two experiments, we exposed observers to short sequences depicting rigidly rotating novel objects and subsequently collected subjective ratings of view canonicality (Experiment 1) and recall rates for individual views (Experiment 2). Given these two operational definitions of view canonicality, we attempted to fit both sets of behavioral data with a computational model incorporating 3-D shape information (object foreshortening), as well as information relevant to the temporal order of views presented during training (the rate of change for object foreshortening). Both sets of ratings were reasonably well predicted using only 3-D shape; the inclusion of terms that capture sequence order improved model performance significantly.

show abstract

“…Many problems of this type are known to be intractable [5], but they admit good approximation algorithms [7]. In what follows, we will present a brief overview of the problem formulation and its solution (for an in-depth treatment of the problem the reader is referred to [28,3,2]). The input set to the canonical set problem consists of a set of points P = {p 1 , ..., p n }, an associated set of strength (stability) measures {t 1 , ..., t n }, t i ∈ R + , 1 ≤ i ≤ n, and a similarity function W : P × P → R + 0 .…”

Section: Canonical Setsmentioning

confidence: 99%

Combining Different Types of Scale Space Interest Points Using Canonical Sets

Kanters

Denton

Shokoufandeh

et al. 2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Scale space interest points capture important photometric and deep structure information of an image. The information content of such points can be made explicit using image reconstruction. In this paper we will consider the problem of combining multiple types of interest points used for image reconstruction. It is shown that ordering the complete set of points by differential (quadratic) TV-norm (which works for single feature types) does not yield optimal results for combined point sets. The paper presents a method to solve this problem using canonical sets of scale space features. Qualitative and quantitative analysis show improved performance over simple ordering of points using the TV-norm.

show abstract

Selecting canonical views for view-based 3-D object recognition

Abstract: Given a collection of sets of 2-D views of 3-D objects and

Cited by 29 publications

References 11 publications

Computing iconic summaries of general visual concepts

Computing iconic summaries of general visual concepts

The role of sequence order in determining view canonicality for novel wire-frame objects

Combining Different Types of Scale Space Interest Points Using Canonical Sets

Contact Info

Product

Resources

About