An Affine Invariant Salient Region Detector

By Timor Kadir, Andrew Zisserman, M. Brady. European Conference on Computer Vision, 2004

565 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5a3ad8b87e865665d6879a63578990af1bde8055

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

Measuring the Objectness of Image Windows (2011, background): “Interest point detectors (IPs) [29], [41] respond to local textured image neighborhoods and are widely used for finding image correspondences [41] and recognizing specific objects [37].”
Center-surround divergence of feature statistics for salient object detection (2011, background): “These approaches range from the computation of entropy [13, 10], over determining features that best discriminate between a target and a null hypothesis [8], to learning the optimal feature combination with machine learning techniques [15, 3].”
Bag-of-visual-words and spatial extensions for land-use classification (2010, methodology): “While there are other detectors, such as the HarrisLaplace/Affine [19], Hessian-Laplace/Affine [19], Kadir and Brady’s Saliency Detector [10]; other descriptors, such as shape context [4], steerable filters [5], PCA-SIFT [11], spin images [12], moment invariants [6], and cross-correlation; and other”
Geographic Image Retrieval Using Local Invariant Features (2013, methodology): “We adopt a standard approach, termed BOVW [55], to summarize the descriptors without regard to where they appear in an image.”
MILES: Multiple-Instance Learning via Embedded Instance Selection (2006, background): “[27], interest point detectors [38], and edge-based detectors [52].”
Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking (2011, methodology): “In recent years, detectors have been proposed that are invariant to affine changes (Mikolajczyk and Schmid 2002; Schaffalitzky and Zisserman 2002; Tuytelaars and van Gool 2000; Matas et al. 2002; Kadir et al. 2004).”
Frequency-tuned salient region detection (2009, background): “Saliency has also been referred to as visual attention [27, 22], unpredictability, rarity, or surprise [17, 14].”
ASIFT: A New Framework for Fully Affine Invariant Image Comparison (2009, methodology): “Some moment-based region detectors [24, 3] including the Harris-Affine and Hessian-Affine region detectors [35, 37], an edge-based region detector [58, 57], an intensity-based region detector [56, 57], an entropy-based region detector [18], and two level line-based region detectors MSER (“maximally ”
Semi-Local Affine Parts for Object Recognition (2004, background): “While a few other affine- and scale-invariant detectors are available in the literature [9, 15, 16, 19], we chose the Laplacian because it finds perceptually salient blob-like regions that tend to be centered away from object boundaries.”
Linear Time Maximally Stable Extremal Regions (2008, background): “Extraction of invariant regions has recently been the focus of intense study [1,2,3,4,5,6,7,8,9,10,11,12], supporting a wide variety of applications such as recognition, image retrieval, mosaicing, 3D reconstruction, tracking, robot navigation and more.”
What is an object? (2010, background): “Interest point detectors (IPs) [20, 27] respond to local textured image neighborhoods and are widely used for finding image correspondences [27] and recognizing specific objects [24].”
Feature representation for statistical-learning-based object detection: A review (2015, methodology): “The saliency feature [61][62] computes the local entropy to determine the key regions of objects.”
A comprehensive review of current local features for computer vision (2008, methodology): “The last but not the least afﬁne invariant detector is the salient region detector [33], which locates regions based on an entropy function.”
A Comparison of Affine Region Detectors (2005, unknown): “Examples of the overlap errors are displayed in ﬁgure 12.”
Object Recognition in the Geometric Era: A Retrospective (2006, methodology): “The successful application of this idea by Cordelia Schmid and Roger Mohr [72] inspired an intensive search for other intensity and aﬃne projection invariant features [46, 70, 79, 38, 50].”
Harvesting Image Databases from the Web (2007, methodology): “Regions are detected using: difference of Gaussians, Multiscale-Harris [18], Kadir’s saliency operator [14], and points sampled from Canny edge points.”
Saliency detection using maximum symmetric surround (2010, background): “Saliency has been referred to as visual attention [5, 1], unpredictability, rarity, or surprise [6].”