Generalizing the Hough transform to detect arbitrary shapes

By Dana H. Ballard. 1981

Subfields: Computer Vision and Pattern Recognition

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

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (2020, methodology): “BBFNet [8] obtains instance segmentation results by Watershed transform [84,4] and Hough-voting [5,51].”
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers (2020, methodology): “Then, instance segments are obtained by grouping ‘thing’ pixels with various methods, such as instance center regression [44, 86, 70, 100, 20], Watershed transform [88, 3, 8], Hough-voting [4, 53, 8], or pixel affinity [45, 66, 81, 30, 8].”
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (2019, methodology): “Class-agnostic instance segmentation: Motivated by Hough Voting [1, 5], we represent each object instance by its center of mass, encoded by a 2-D Gaussian with standard deviation of 8 pixels.”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, methodology): “We use a probabilistic Hough transorm [2] to match those candidate regions across images, and assign them confidence scores reflecting both appearance and spatial consistency.”
Unsupervised Image Matching and Object Discovery as Optimization (2019, methodology): “Intuitively, s ij scales the appearance-only score a ij by a geometric-consistency term akin to a generalized Hough transform [5], see [12] for details.”
Segmentation of confocal microscope images of cell nuclei in thick tissue sections (1999, methodology): “The first step used a Hough transform-based method to shrink nuclei (Ballard, 1981) and the second method used an automatic focusing”
Automatic Model-Based Segmentation of the Heart in CT Images (2008, methodology): “To achieve fully automatic segmentation, the GHT is used to localize the heart in the 3-”
Outlier Analysis (2013, methodology): “A variety of shape learning methods [54, 92, 316, 504] are available”
Fast PRISM: Branch and Bound Hough Transform for Object Class Detection (2011, methodology): “Despite the close relation, there is a subtle difference due to the dependency on fs or λs , which suggests the preferable usage: predicting objects λ ∼ If (f ) + f given a feature f or sampling features f ∼ Iλ(λ) + λ to verify an object hypothesis λ.6 The former approach is taken by the Generalised”
Object detection using a max-margin Hough transform (2009, background): “The Hough transform [6] provides yet another way of dealing with the complexity issue of searching over pose and has been used for various pose estimation problems including shape detection [2].”
Actionness Ranking with Lattice Conditional Ordinal Random Fields (2014, methodology): “Since the underlying appearance of actionness will greatly vary, we also incorporate the non-parametric generalized Hough transform [2, 36].”
Coloring Local Feature Extraction (2006, unknown): “Ballard and Swain [6] described objects by their color histograms.”
ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes (2020, methodology): “Inspired by the seminal work on the generalized Hough transform [3], VOTENET proposes an adaptation of the voting mechanism for object detection to a deep learning framework that is fully differentiable.”
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects (2013, methodology): “As in the Generalised Hough Transform [2], in Drost et al .’s method an object is detected and simultaneously localised via the accumulation of votes in a parameter space.”
Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review (2016, background): “The search space can be narrowed down by introducing the gradient direction into the voting procedure [96].”
Improved Automatic Detection and Segmentation of Cell Nuclei in Histopathology Images (2010, methodology): “The Hough transform [21] has also been used”
Object Recognition in the Geometric Era: A Retrospective (2006, background): “The most consistent pose is found by voting into a space of affine transformations, similar to the generalized Hough transform [5,75].”