Probabilistic visual learning for object detection

Moghaddam, B.; Pentland, Alex

doi:10.1109/iccv.1995.466858

Cited by 286 publications

(200 citation statements)

References 10 publications

Supporting

Mentioning

198

Contrasting

Unclassified

Order By: Relevance

“…Note that this use of mixture models for matching differs from that of Moghaddam and Pentland (1995) who use mixture models to group, or classify, training data in the space of the coefficients.…”

Section: Outliers and Multiple Matchesmentioning

confidence: 99%

“…This amounts to a correlation-style matching. Moghaddam and Pentland (1995) extended this global search idea to include scale in a straightforward way by matching the input at different scales using the standard eigenspace approach. These exhaustive search techniques may be used to provide a coarse initial guess about the transformation between the eigenspace and the image.…”

Section: Related Workmentioning

confidence: 99%

“…It is either assumed that the object can be detected by simple thresholding (Murase and Nayar, 1995), through some other feature detection process (Moghaddam and Pentland, 1995), or through global search (Moghaddam and Pentland, 1995;Turk and Pentland, 1991). Turk and Pentland (1991) showed that eigenspace matching could be used to perform a global search under translation simply by comparing the eigenspace with the input image at every image location.…”

Section: Related Workmentioning

confidence: 99%

“…For example, face databases typically store representations of people's heads in the standard upright orientation at a particular scale. If a test image contains a head that is tilted and at a different scale, the image must first be transformed into the canonical position (Moghaddam and Pentland, 1995). In previous work this has been viewed as a preprocessing step.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

EigenTracking: Robust matching and tracking of articulated objects using a view-based representation

Black

Jepson

1996

Lecture Notes in Computer Science

579

812

View full text Add to dashboard Cite

Abstract. This paper describes an approach for tracking rigid and articulated objects using a view-based representation. The approach builds on and extends work on eigenspace representations, robust estimation techniques, and parameterized optical flow estimation. First, we note that the least-squares image reconstruction of standard eigenspace techniques has a number of problems and we reformulate the reconstruction problem as one of robust estimation. Second we define a "subspace constancy assumption" that allows us to exploit techniques for parameterized optical flow estimation to solve for both the view of an object and the affine transformation between the eigenspace and the image. To account for large affine transformations between the eigenspace and the image we define a multi-scale eigenspace representation and a coarse-to-fine matching strategy. Finally, we use these techniques to track objects over long image sequences in which the objects simultaneously undergo both affine image motions and changes of view. In particular we use this "EigenTracking" technique to track and recognize the gestures of a moving hand.

show abstract

Section: Outliers and Multiple Matchesmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

EigenTracking: Robust matching and tracking of articulated objects using a view-based representation

Black

Jepson

1996

Lecture Notes in Computer Science

579

812

View full text Add to dashboard Cite

show abstract

“…Any new image can then be represented as a linear combination of these eigen faces. Similar ideas are then used in many specific problems like object detection [14], object matching and tracking [15] and visual surveillance [16]. The idea of expanding query in terms of some other queries is also popular in Concept Based Multimedia Retrieval (CBMR).…”

Section: Related Workmentioning

confidence: 99%

Image Retrieval Using Eigen Queries

Raval

Tonge

Jawahar

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

Abstract. Category based image search, where the goal is to retrieve images of a specific category from a large database, is becoming increasingly popular. In such a setting, the query is often a classifier. However, the complexity of the classifiers (often SVMs) used for this purpose hinders the use of such a solution in practice. Problem becomes paramount when the database is huge and/or the dimensionality of the feature representation is also very large. In this paper, we address this issue by proposing a novel method which decomposes the query classifier into set of known eigen queries. We use their precomputed results (or scores) for computing the ranked list corresponding to novel queries. We also propose an approximate algorithm which accesses only a fraction of the data to perform fast retrieval. Experiments on various datasets show that our method reports high accuracy and efficiency. Apart from retrieval, the proposed method can also be used to discover interesting new concepts from the given dataset.

show abstract

Stable recognition of specular objects by the eigenwindow method

Ohba

Ikeuchi

1998

Syst. Comp. Jpn.

View full text Add to dashboard Cite

This paper proposes a recognition method for partially occluded objects in bin‐picking tasks using principal component analysis. Although it is well known to be effective in recognizing an isolated object, as was shown by Murase and Nayar, the current method cannot be applied to partially occluded objects that are typical in bin‐picking tasks. The analysis also requires that the object be centered in an image before recognition. These limitations of eigenspace analysis are due to the fact that the whole appearance of an object is utilized as a template for the analysis. We propose a new method, referred to as the “eigenwindow” method, that stores multiple partial appearances of an object in an eigenspace. Such partial appearances require a large amount of memory space. Three measurements, detectability, uniqueness, and reliability, among windows are developed to eliminate redundant windows and thereby reduce memory requirements. Using a pose‐clustering method among windows, the method determines the pose of an object and the object type of itself. We have implemented the method and verified its validity with recognition of multispecularity objects. © 1998 Scripta Technica, Syst Comp Jpn, 29(7): 12–20, 1998

show abstract

Probabilistic visual learning for object detection

Cited by 286 publications

References 10 publications

EigenTracking: Robust matching and tracking of articulated objects using a view-based representation

EigenTracking: Robust matching and tracking of articulated objects using a view-based representation

Image Retrieval Using Eigen Queries

Stable recognition of specular objects by the eigenwindow method

Contact Info

Product

Resources

About