Shape feature extraction and description based on tensor scale

Andaló, Fernanda A.; Miranda, Paulo A. V.; Torres, Ricardo da S.; Falcão, Alexandre X.

doi:10.1016/j.patcog.2009.06.012

Cited by 55 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The top ten retrieved images from the whole MPEG-7 dataset are illustrated in Fig. 16 with three methods: first row, shape representation using tensor scale descriptor with influence zones TSDIZ [21], followed by shape representation with beam angle statistic BAS [22] and at last, our method for global matching. The irrelevant responses are highlighted with a red rectangle, thus, our method outperforms the BAS [22] and is very close to TSDIZ [21].…”

Section: Global Shape Matchingmentioning

confidence: 99%

Discriminative outlines parts for shape retrieval

Bouagar

Larabi

2015

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Section: Global Shape Matchingmentioning

confidence: 99%

Discriminative outlines parts for shape retrieval

Bouagar

Larabi

2015

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

“…The shape features include two parts: one is the size of the region; and the other is the shape feature based on tensor scale, a morphometric histogram presented by [6]. The shape feature unifies the representation of local structure thickness, orientation and anisotropy.…”

Section: A Unary Featuresmentioning

confidence: 99%

Segment-Forest for Segmentation

Fan¹,

Li²

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

In this paper, we present a novel generalized Segment-Forest Model (SFM) to segment an object as well as label all the object's semantic parts simultaneously. Segment-Forest is composed by various generated segment trees that act directly on superpixels. Unlike recent works, SFM does not need the prior information like skeleton to capture the core structure of an object, but actively learns the structure from semantic parts during the learning stage. The prediction is an Inference-On-Tree-VotingOn-Forest process, which precludes the expensive computation of the multi-objective optimization. Both training and inference in SFM are extremely efficient, especially compared with traditional multi-objective optimization approaches using in segmentation. We demonstrate superior performance particularly in object articulation, non-rigid deformation on two standard datasets over current state-of-the-art methods. Through further occlusion experiments, we show that SFM can work robustly in the real world.

show abstract

“…3) Tensor Scale Descriptor (TSD) [21]. TSD is a shape descriptor based on the tensor scale concept morphometric parameter yielding a unified representation of local structure thickness, orientation, and anisotropy [22]. That is, at any image point, its tensor scale is represented by the largest ellipse (2D) centered at that point and within the same homogeneous region.…”

Section: B Feature Descriptionmentioning

confidence: 99%

How Far You Can Get Using Machine Learning Black-Boxes

Rocha

Papa

Meira

2010

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images

View full text Add to dashboard Cite

Abstract-Supervised Learning (SL) is a machine learning research area which aims at developing techniques able to take advantage from labeled training samples to make decisions over unseen examples. Recently, a lot of tools have been presented in order to perform machine learning in a more straightforward and transparent manner. However, one problem that is increasingly present in most of the SL problems being solved is that, sometimes, researchers do not completely understand what supervised learning is and, more often than not, publish results using machine learning black-boxes. In this paper, we shed light over the use of machine learning black-boxes and show researchers how far they can get using these out-of-thebox solutions instead of going deeper into the machinery of the classifiers. Here, we focus on one aspect of classifiers namely the way they compare examples in the feature space and show how a simple knowledge about the classifier's machinery can lift the results way beyond out-of-the-box machine learning solutions.

show abstract

Shape feature extraction and description based on tensor scale

Cited by 55 publications

References 16 publications

Discriminative outlines parts for shape retrieval

Discriminative outlines parts for shape retrieval

Segment-Forest for Segmentation

How Far You Can Get Using Machine Learning Black-Boxes

Contact Info

Product

Resources

About