Deformable prototypes for encoding shape categories in image databases

Sclaroff, Stan

doi:10.1016/s0031-3203(96)00108-2

Cited by 81 publications

(60 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…375-376). Further solutions to this correspondence problem have been proposed in the computer vision literature (e.g., Belongie, Malik, & Puzicha, 2002;Sclaroff, 1997;Sclaroff & Liu, 2001;Witkin, Terzopoulos, & Kass, 1987; see also Ullman, 1996). It should be noted that the correspondence problem is not specific for the alignment approach to recognition but also arises in (apparent) motion perception and stereoscopic vision (for reviews, see Chen, 2001;Palmer, 1999).…”

Section: Unresolved Issuesmentioning

confidence: 99%

Coordinate transformations in object recognition.

Graf¹

2006

Psychological Bulletin

View full text Add to dashboard Cite

A basic problem of visual perception is how human beings recognize objects after spatial transformations. Three central classes of findings have to be accounted for: (a) Recognition performance varies systematically with orientation, size, and position; (b) recognition latencies are sequentially additive, suggesting analogue transformation processes; and (c) orientation and size congruency effects indicate that recognition involves the adjustment of a reference frame. All 3 classes of findings can be explained by a transformational framework of recognition: Recognition is achieved by an analogue transformation of a perceptual coordinate system that aligns memory and input representations. Coordinate transformations can be implemented neurocomputationally by gain (amplitude) modulation and may be regarded as a general processing principle of the visual cortex.Keywords: alignment, coordinate transformations, gain modulation, object recognition, reference frames How can we recognize objects regardless of spatial transformations such as plane and depth rotation, size scaling, and position changes? This ability is often discussed under the label object constancy or shape constancy. Even young children recognize objects so immediately and effortlessly that it seems to be a rather ordinary and simple task. However, changes in the spatial relation between observer and object lead to large changes of the image that is projected onto the retina. Hence, to recognize objects regardless of orientation, size, and position is not a trivial problem. No computational system proposed so far can successfully recognize objects over wide ranges of object categories and contexts.Several different approaches have been proposed over the years (for reviews, see Palmeri & Gauthier, 2004;Ullman, 1996). A number of models rely on abstract object representations, which predict that recognition performance is typically invariant regarding spatial transformations (e.g., structural description models; see Hummel & Biederman, 1992;Marr & Nishihara, 1978). In contrast, image-based or view-based models propose that object representations are close to the format of the perceptual input and therefore depend systematically on image transformations (e.g.,

show abstract

Section: Unresolved Issuesmentioning

confidence: 99%

Coordinate transformations in object recognition.

Graf¹

2006

Psychological Bulletin

View full text Add to dashboard Cite

show abstract

“…Features for recognizing hand tools were extracted from outer contours provided by the mask images of tools in database [4]. Fig.…”

Section: Feature Extractionmentioning

confidence: 99%

“…Deformable shape descriptions are widely used for pattern recognition [1], [2], [3], [4]. Williams developed a method of recognizing handwritten digits using deformable models [1].…”

Section: Introductionmentioning

confidence: 99%

“…Lanitis et al proposed a method to characterize the underlying variability of the objects iteratively and applied their method to recognizing plant seeds, handwritten characters, and human faces [2]. Sclaroff and Pentland developed a method for establishing correspondences and computing canonical descriptions and applied their method to the recognition of 2D shapes with deformations [3], [4]. Usually, these methods are able to capture deformations with similar shapes; however, they are not good at modeling different shapes belonging to same classes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hidden Markov models with spectral features for 2D shape recognition

Cai

Liu

2001

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

AbstractÐIn this paper, we present a technique using Markov models with spectral features for recognizing 2D shapes. We will analyze the properties of Fourier spectral features derived from closed contours of 2D shapes and use these features for 2D pattern recognition. We develop algorithms for reestimating parameters of hidden Markov models. To demonstrate the effectiveness of our models, we have tested our methods on two image databases: hand-tools and unconstrained handwritten numerals. We are able to achieve high recognition rates of 99.4 percent and 96.7 percent without rejection on these two sets of image data, respectively.

show abstract

“…For instance, in the field of content based image retrieval, simple methods based on global colour distributions have been reasonably effective [19]. However, although attempts have been made to incorporate shape, they are still relatively crude [6,14].…”

Section: Introductionmentioning

confidence: 99%

Straightening and Partitioning Shapes

Rosin

2001

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.A method for partitioning shapes is described based on a global convexity measure. Its advantages are that its global nature makes it robust to noise, and apart from the number of partitioning cuts no parameters are required. In order to ensure that the method operates correctly on bent or undulating shapes a process is developed that identifies the underlying bending and removes it, straightening out the shape. Results are shown on a large range of shapes.

show abstract

Deformable prototypes for encoding shape categories in image databases

Cited by 81 publications

References 44 publications

Coordinate transformations in object recognition.

Coordinate transformations in object recognition.

Hidden Markov models with spectral features for 2D shape recognition

Straightening and Partitioning Shapes

Contact Info

Product

Resources

About