Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying

By Chad Carson, Serge J. Belongie, Hayit Greenspan, Jitendra Malik. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002

1,653 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fedf7729b620ec2cf4e79705d2898f82e9a2ba66

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Building the gist of a scene: the role of global image features in recognition. (2006, background): “Colored surfaces, in addition to providing useful segmentation cues for parsing the image (Carson et al., 2002), also informs about semantic properties of a place, such as its probable temperature (Greene and Oliva, 2005).”
Content-based Image Retrieval in Medical Applications (2004, methodology): “It is built from ellipsoids (“blobs”) representing local image regions of uniform color or texture on an abstract level of interpretation [3].”
Methods for Nuclei Detection, Segmentation, and Classification in Digital Histopathology: A Review—Current Status and Future Potential (2014, background): “Loy and Zelinsky [93] proposed fast gradient-based interest operator for detection of seed points having high radial symmetry.”
Geometric Applications of the Split Bregman Method: Segmentation and Surface Reconstruction (2010, neutral): “T. Goldstein () · X. Bresson · S. Osher Department of Mathematics, UCLA, Box 951555, Los Angeles, CA 90095-1555, USA e-mail: tomgold2@gmail.com J Sci Comput (2010) 45: 272–293 273 into this framework, see [ 13 , 24, 44].”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition (neutral): “Email: {torralba,fergus,billf}@csail.mit.edu on really large datasets means that the chosen image representation is often relatively simple, e.g. color [17], wavelets [42] or crude segmentations [9].”
Features for image retrieval: an experimental comparison (2008, methodology): “Another well known system is Blobworld [20], developed at UC Berkeley.”
A review on automatic image annotation techniques (2012, methodology): “Segmentation algorithms based on statistical models have also been proposed [71] [72] [73].”
Performance evaluation of local colour invariants (2009, neutral): “In this paper, we consider the extension to colour-based descriptors. colour has high discriminative power; in many cases, objects can well be recognized merely by their colour characteristics [15] [16] [17] [18] [19] [20].”
CLUE: cluster-based retrieval of images by unsupervised learning (2005, methodology): “This work was supported in part by the National Science Foundation under Grant IIS-0219272 and CNS-0202007, The Pennsylvania State University, the PNC Foundation, SUN Microsystems under Grant EDUD-7824-010456-US, the University of New Orleans, The Research Institute for Children, NASA/EPSCoR DART…”
An efficient image similarity measure based on approximations of KL-divergence between two gaussian mixtures (2003, methodology): “An alternative image representation is a continuous probabilistic framework based on a Mixture of Gaussians model (MoG) [1] [3].”
A survey of content-based image retrieval with high-level semantics (2007, background): “Interesting insights can also be gained from the outcomes of the ImageCLEF image retrieval evaluations (Clough et al. 2004; Clough et al. 2006) in which different systems are compared on the same task.”