Review of shape representation and description techniques

By Dengsheng Zhang, Guojun Lu. Pattern Recognition, 2004

2,078 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/eece0c3c49f3e898a752c6ea9d9bd5f55bdb0ae4

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

A Novel Method to Construct Taxonomy Electrical Appliances Based on Load Signaturesof (2007, methodology): “As introduced in [15]-[16], there are different methods for shape characterization and classification.”
A Review on Image Feature Extraction and Representation Techniques (2013, methodology): “For more details of image shape feature extraction and representation, please refer to the literature [20].”
Motion history image: its variants and applications (2012, background): “Figure 9 shows various other options for shape representation based on [68,80,81,168].”
On the spatial distribution of buildings for map generalization (2018, background): “Shape, for example, can be measured based either on boundary information or on boundary plus interior content, including shape signatures, histograms, invariants, moments, curvature, context, matrices, and spectral features (Peura & Iivarinen, 1997; Zhang & Lu, 2004).”
A Survey of Shape Feature Extraction Techniques (2008, background): “Chain code describes an object by a sequence of unit-size line segments with a given orientation [7].”
A review on automatic image annotation techniques (2012, background): “Zhang and Lu [104] broadly classify shape extraction techniques into two major groups: contour based and region based methods.”
Is Rotation a Nuisance in Shape Recognition? (2014, methodology): “Our approach used the curvature scale space and outperformed the state of the art.”
Computing (2021, background): “This case study takes aim at identifying what drives our reactions to the built environment so that we can teach machines to understand the mechanisms of human–environment engagement.”
Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool (2015, background): “Because noise and outliers are common in medical segmentations, it is not recommended to use the HD directly [8, 40].”
Shape retrieval using triangle-area representation and dynamic space warping (2007, background): “The ever growing number of images generated everyday has motivated researchers to develop, evaluate and implement sophisticated algorithms for the retrieval of images from large databases based on their content rather than their textual annotations alone.”
Personal recognition using hand shape and texture (2006, neutral): “content [14], [15].”
Outlier Analysis (2013, methodology): “The most crucial part of the feature extraction is to convert [504] the shape into a time-series using the methods discussed in section 5 of Chapter 10.”
Medical image registration: a review (2014, background): “Reviewsonimagesegmentationtechniquescanbefound in Gonzalez and Woods (2008), Ma, Zhen et al. (2010), Monteiro (2007), Zhang and Lu (2004), Zhang (2001).”
SalientShape: group saliency in image collections (2013, methodology): “– circularity: Perimeter2/Area [49], – solidity: RegionArea/ConvexHullArea [26], – Fourier Descriptor [50], and – Shape Context [2].”
Plant Species Identification Using Computer Vision Techniques: A Systematic Literature Review (2017, background): “It piles up curvature measures at each point of the contour over successive smoothing scales, summing up the information into a map where concavities and convexities clearly appear, as well as the relative scale up to which they persist [151].”