Shape Classification Using the Inner-Distance

By Haibin Ling, David W. Jacobs. 2007

1,173 citations recorded by the source corpus.

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

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (2016, background): “Point features often encode certain statistical properties of points and are designed to be invariant to certain transformations, which are typically classified as intrinsic [2, 21, 3] or extrinsic [18, 17, 13, 10, 5].”
Dynamic Graph CNN for Learning on Point Clouds (2018, methodology): “e shape in 3D space and includes classical methods like shape context [Belongie et al. 2001], spin images [Johnson and Hebert 1999], integral features [Manay et al. 2006], distance-based descriptors [Ling and Jacobs 2007], point feature histograms [Rusu et al .2009, 2008a], and normal histograms [To”
LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis (2018, background): “Handcrafted local features, such as the histogram feature [14], the inner-distance-based descriptor [8] and the heat kernel signatures [21], are widely used for point cloudbased recognition tasks, but they are usually designed for specific applications and have a poor generalization ability.”
Robust Part-Based Hand Gesture Recognition Using Kinect Sensor (2013, background): “as shape contexts [13] and inner-distance [14], they are not”
Learning Weight Uncertainty with Stochastic Gradient MCMC for Shape Classification (2016, background): “%) pSGLD 84.80± 0.35 RMSprop 84.30± 0.55 BCF + SVM [77] 83.40±1.30 ICS [4] 78.4 Distinctive Parts [46] 80.7 Bag of SIFT [47] 80.4 IDSC [49] 73.6 Class segment set [68] 69.7 Table 3.”
Plant species identification using digital morphometrics: A review (2012, methodology): “A related method is the inner-distance measure, a metric based on the lengths of the shortest routes between outline points without passing outside of the shape, which was used by Ling and Jacobs (2007).”
Event Detection in Crowded Videos (2007, background): “Similarly, the extensive research on generalizing shape matching [11, 17] requires reliable figure/ground separation, which is infeasible in crowded scenes using current segmentation techniques.”
Shape-Texture Debiased Neural Network Training (2020, background): “…decade ago, computer vision researchers had explicitly designed a variety of hand-crafted features, either based on shape ( e.g ., shape context (Belongie et al., 2002) and inner distance shape context (Ling & Jacobs, 2007)) or texture ( e.g ., textons (Malik et al., 2001)), for object recognition.”
Leafsnap: A Computer Vision System for Automatic Plant Species Identification (2012, methodology): “Our approach is very different from the IDSC-based [7] recognition described in [5].”
Learning Context-Sensitive Shape Similarity by Graph Transduction (2010, methodology): “[27] 99 99 99 98 99 98 98 95 96 94 IDSC [3] + our method 99 99 99 99 99 99 99 99 97 99”
Incorporating visual adjectives for image classification (2016, background): “…Color-SIFT [25] and Local Color Statistics (LCS) [18] for color description, Shape Context (SC) [27] and Inner-Distance Shape Context (IDSC) [28] for shape formulation, etc. Based on the various kinds of visual features, there are several research efforts aimed at combining multiple…”
The wave kernel signature: A quantum mechanical approach to shape analysis (2011, methodology): “Examples include [15, 11, 8], who used ideas similar to the Shape Context in a geodesic distance framework.”
Attentional ShapeContextNet for Point Cloud Recognition (2018, methodology): “Before the deep learning era [19], carefully designed features like shape context [3] and inner distances [21] were successfully applied to the problem of shape matching and recognition.”
GIFT: A Real-Time and Scalable 3D Shape Search Engine (2016, background): “However, efﬁciency issue has been more or less ignored by previous works, though enormous efforts have been devoted to retrieval effectiveness , that is to say, to de-sign informative and discriminative features [12, 2, 17, 6, 41, 15, 18] to boost the retrieval accuracy.”
Path Similarity Skeleton Graph Matching (2008, methodology): “IDSC + DP [ 47 ] 99 99 99 98 98 97 97 98 94 79”