Two perceptually motivated strategies for shape classification

Temlyakov, Andrew; Munsell, Brent C.; Waggoner, Jarrell; Wang, Song

doi:10.1109/cvpr.2010.5539912

Cited by 46 publications

(45 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For all our experiments on this dataset, we set Ù , Ð ½½ and once again set Ø ¼ ¿. However, for this dataset, we directly use the IDSC measure as ´Ë Ë µ since the S&S strategy is shown to not have any significant impact on the retrieval accuracy for this dataset [23]. Because we are using the original IDSC measure, we choose the default parameters as reported in [10] for MM-NN.…”

Section: Mpeg-7 Datasetmentioning

confidence: 99%

“…The threshold for finding components is set to Ø ¼ ¿ as explained previously. To illustrate performance improvement, we select the basic S&S+IDSC measure introduced in [23] as the base similarity measure, ´Ë Ë µ. Table 2.…”

Section: Mpeg-7 Datasetmentioning

confidence: 99%

“…Further, Liu et al [15] apply Total Bregman Divergence to characterize the similarity between two shapes and classify them into groups of similar shapes, while Lin et al [12] introduce the Layered Graph Matching algorithm. In addition to these measures, Temlyakov et al [23] present the "strand" and "stretch" strategies (S&S) that simplify the geometry of a given shape to improve the performance of these shape descriptors and similarity measures. These previous works have made significant advancements in quantifying the similarity between a given pair of shapes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Shape and image retrieval by organizing instances using population cues

Temlyakov

Dalal

Waggoner

et al. 2013

2013 IEEE Workshop on Applications of Computer Vision (WACV)

Self Cite

View full text Add to dashboard Cite

Reliably measuring the similarity of two shapes or images (instances) is an important problem for various computer vision applications such as classification, recognition, and retrieval. While pairwise measures take advantage of the geometric differences between two instances to quantify their similarity, recent advances use relationships among the population of instances when quantifying pairwise measures. In this paper, we propose a novel method which refines pairwise similarity measures using population cues by examining the most similar instances shared by the compared shapes or images. We then use this refined measure to organize instances into disjoint components that consist of similar instances. Connectivity is then established between components to avoid hard constraints on what instances can be retrieved, improving retrieval performance. To evaluate the proposed method we conduct experiments on the wellknown MPEG-7 and Swedish Leaf shape datasets as well as the Nister and Stewenius image dataset. We show that the proposed method is versatile, performing very well on its own or in concert with existing methods.

show abstract

Section: Mpeg-7 Datasetmentioning

confidence: 99%

Section: Mpeg-7 Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Shape and image retrieval by organizing instances using population cues

Temlyakov

Dalal

Waggoner

et al. 2013

2013 IEEE Workshop on Applications of Computer Vision (WACV)

Self Cite

View full text Add to dashboard Cite

show abstract

“…A graph diffusion process is utilized for retrieval in Yang et al [3], where a Locally Constraint Diffusion Process (LCDP) is proposed. LCDP has been used in [9] and [14] to improve their results. Graph diffusion has also been utilized for manifold embedding [8].…”

Section: Related Workmentioning

confidence: 99%

Affinity Learning with Diffusion on Tensor Product Graph

Yang

Prasad

Latecki

2013

IEEE Trans. Pattern Anal. Mach. Intell.

139

127

View full text Add to dashboard Cite

Abstract-In many applications, we are given a finite set of data points sampled from a data manifold and represented as a graph with edge weights determined by pairwise similarities of the samples. Often the pairwise similarities (which are also called affinities) are unreliable due to noise or due to intrinsic difficulties in estimating similarity values of the samples. As observed in several recent approaches, more reliable similarities can be obtained if the original similarities are diffused in the context of other data points, where the context of each point is a set of points most similar to it. Compared to the existing methods, our approach differs in two main aspects. First, instead of diffusing the similarity information on the original graph, we propose to utilize the tensor product graph (TPG) obtained by the tensor product of the original graph with itself. Since TPG takes into account higher order information, it is not a surprise that we obtain more reliable similarities. However, it comes at the price of higher order computational complexity and storage requirement. The key contribution of the proposed approach is that the information propagation on TPG can be computed with the same computational complexity and the same amount of storage as the propagation on the original graph. We prove that a graph diffusion process on TPG is equivalent to a novel iterative algorithm on the original graph, which is guaranteed to converge. After its convergence we obtain new edge weights that can be interpreted as new, learned affinities. We stress that the affinities are learned in an unsupervised setting. We illustrate the benefits of the proposed approach for data manifolds composed of shapes, images, and image patches on two very different tasks of image retrieval and image segmentation. With learned affinities, we achieve the bull's eye retrieval score of 99.99 percent on the MPEG-7 shape dataset, which is much higher than the state-of-the-art algorithms. When the data points are image patches, the NCut with the learned affinities not only significantly outperforms the NCut with the original affinities, but it also outperforms state-of-the-art image segmentation methods.

show abstract

“…Alternative region based descriptors also exist, such as [8]. Shape is put to use in many Computer Vision tasks not limited to matching [32], classification [9,18,35], and retrieval [1,3,6].…”

Section: Introductionmentioning

confidence: 99%

Prime Shapes in Natural Images

Hall

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

This paper provides evidence that about half of all the regions in segmented images can be classified as one a few simple shapes. Using three segmentation algorithms, three different image databases, and two shape descriptors, we empirically show that shapes such as triangles, squares, and circles are observed, up to an affine transform and at a much higher rate than random shapes. This result has potential value in applications such as scene understanding, visual object classification, and matching because qualitative shapes can be used as features. We show an application in scene categorisation based on what might be called 'bag of shapes' .

show abstract

Two perceptually motivated strategies for shape classification

Abstract: In this paper, we propose two new, perceptually motivated

Cited by 46 publications

References 30 publications

Shape and image retrieval by organizing instances using population cues

Shape and image retrieval by organizing instances using population cues

Affinity Learning with Diffusion on Tensor Product Graph

Prime Shapes in Natural Images

Contact Info

Product

Resources

About