Maximally Stable Colour Regions for Recognition and Matching

By Per-Erik Forssén. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

308 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/1903231edcf47533e9d9fc21119f6cd3fa3f136b

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

In Media Technology

Citations in the corpus

Evaluating Color Descriptors for Object and Scene Recognition (2010, background): “Other region detectors [10], such as the dense sampling detector, Maximally Stable Extremal Regions [27], and Maximally Stable Color Regions [28], can be plugged in.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “2007; Ferraz and Binefa 2012) or considered color information for a higher discrimination (Forssén 2007).”
Intelligent multi-camera video surveillance: A review (2013, background): “Many filters, such as Gabor filter (Daugman et al., 1985) and other linear filter-banks (Winn et al., 2005; Varma and Zisserman, 2005; Leung and Malik, 1999), and local descriptors, such as SIFT (Lowe, 2004), color SIFT (Abdel-Hakim and Farag, 2006), Local Binary Patterns (LBP) (Ojala et al., 2002),”
Custom Pictorial Structures for Re-identification (2011, methodology): “The first aspect is captured by HSV histograms, while the second aspect is codified by Maximally Stable Color Regions (MSCR) [11], previously adopted for re-id in [8].”
Image webs: Computing and exploiting connectivity in image collections (2010, background): “Next, tentative correspondences between local features are generated by matching each feature in one image to its approximate nearest neighbor in the other (in descriptor space).”
A review of multimodal image matching: Methods and applications (2021, background): “[130] extended MSER to exploit shape structure cues, and many other improvements are introduced for higher discrimination, such as using curvature images [164,165], color information [166], or other segmentation basis [167].”
A survey of approaches and trends in person re-identification (2014, unknown): “Each part is then described using 3 features, weighted HSV histogram, maximally stable color regions (MSCR) [51] and recurrent highly textured local”
Dissimilarity-based people re-identification and search for intelligent video surveillance (2013, methodology): “Maximally Stable Colour Regions (MSCR) [51] are used in [28, 45, 88].”
Linear Time Maximally Stable Extremal Regions (2008, methodology): “They have also been used in recognition [16] as well as tracking [11] and have been extended to color [17] and volumetric images [18].”