Hierarchical image segmentation by polygon grouping

Prasad, Lakshman; Swaminarayan, Sriram

doi:10.1109/cvprw.2008.4562980

Cited by 8 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the neighborhood information can be integrated into the affinity learning procedure. As proven by many other papers [22], [23], [24], [25], [26], this information complements purely local information to a great advantage. We use the finest level of hierarchical image segmentation as the basic unit instead of pixels.…”

Section: Related Workmentioning

confidence: 83%

See 1 more Smart Citation

Affinity Learning with Diffusion on Tensor Product Graph

Yang

Prasad

Latecki

2013

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

140

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

Section: Related Workmentioning

confidence: 83%

“…We generate L hierarchical oversegmentation results by varying the segmentation parameters of method [26], which are the input parameters to a Canny edge detector. V h l represents the regions at level h of the lth oversegmentation.…”

Section: Hierarchical Graph Constructionmentioning

confidence: 99%

Affinity Learning with Diffusion on Tensor Product Graph

Yang

Prasad

Latecki

2013

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

140

127

View full text Add to dashboard Cite

show abstract

“…Accordingly, several Multiscale and hierarchical segmentation methods have been proposed 10,11,12,13 . In the past we have developed 13,14,15 an efficient hierarchical segmentation scheme that leverages edge and region interactions synergistically to obtain polygonal segmentations of images at multiple scales and represents the segmentation as a pyramid of richly attributed planar graphs. In this paper we employ this scheme to construct a graphical model that enables semantic search of images.…”

Section: Hierarchical Image Segmentationmentioning

confidence: 99%

Semantic segmentation of multispectral overhead imagery

2016

Self Cite

View full text Add to dashboard Cite

Land cover classification uses multispectral pixel information to separate image regions into categories. Image segmentation seeks to separate image regions into objects and features based on spectral and spatial image properties. However, making sense of complex imagery typically requires identifying image regions that are often a heterogeneous mixture of categories and features that constitute functional semantic units such as industrial, residential, or commercial areas. This requires leveraging both spectral classification and spatial feature extraction synergistically to synthesize such complex but meaningful image units. We present an efficient graphical model for extracting such semantically cohesive regions. We employ an initial hierarchical segmentation of images into features represented as nodes of an attributed graph that represents feature properties as well as their adjacency relations with other features. This provides a framework to group spectrally and structurally diverse features, which are nevertheless semantically cohesive, based on user-driven identifications of features and their contextual relationships in the graph. We propose an efficient method to construct, store, and search an augmented graph that captures nonadjacent vicinity relationships of features. This graph can be used to query for semantic notional units consisting of ontologically diverse features by constraining it to specific query node types and their indicated/desired spatial interaction characteristics. User interaction with, and labeling of, initially segmented and categorized image feature graph can then be used to learn feature (node) and regional (subgraph) ontologies as constraints, and to identify other similar semantic units as connected components of the constraint-pruned augmented graph of a query image.

show abstract

“…In the final year of the project, we used a new algorithm for finding buildings, an adapted version of LANL's patented RADIUS algorithm [38]. We ran a variety of tests to demonstrate using the various types of annotation to test the new building finder algorithm.…”

Section: Demonstration Of Testing An Algorithm With Benchmark Immentioning

confidence: 99%

“…The BldgFinder algorithm was developed based on LANL's RADIUS image segmentation technology [38] and a pre-defined "buildingness" metric. The algorithm is a binary classifier; therefore, its performance was evaluated in terms of detecting the object of interest (i.e., "building") as well as objects which were not of interest, (i.e., "non-building"), and its ability to avoid confusion between these two classes [39].…”

Section: Obtain Algorithm To Testmentioning

confidence: 99%