The optimal distance measure for object detection

Mahamud, S.; Hebert, Martial

doi:10.1109/cvpr.2003.1211361

Cited by 38 publications

(46 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section summarizes the performance comparison conducted by Rothganger et al ((2006), which include the algorithms given by Ferrari et al (2004), Lowe (2004), Mahamud & Hebert (2003), and Moreels et al (2004). The method by Lowe (2004) has been presented in Section 3, and the rest are addressed below.…”

Section: Performance Comparison In a Case Studymentioning

confidence: 99%

“…The method by Lowe (2004) has been presented in Section 3, and the rest are addressed below. Mahamud & Hebert (2003) develop a multi-class object detection framework with a nearest neighbor (NN) classifier as its core. They derive the optimal distance measure that minimizes a nearest neighbor mis-classification risk, and present a simple linear logistic model which measures the optimal distance in terms of simple features like histograms of color, shape and texture.…”

Section: Performance Comparison In a Case Studymentioning

confidence: 99%

See 1 more Smart Citation

Stereo Correspondence with Local Descriptors for Object Recognition

Hsu¹

2011

Advances in Theory and Applications of Stereo Vision

View full text Add to dashboard Cite

Section: Performance Comparison In a Case Studymentioning

confidence: 99%

Section: Performance Comparison In a Case Studymentioning

confidence: 99%

Stereo Correspondence with Local Descriptors for Object Recognition

Hsu¹

2011

Advances in Theory and Applications of Stereo Vision

View full text Add to dashboard Cite

“…Distance function learning is done through the optimization of a parameterized function, so that the WC distances are minimized and BC distances are maximized. Examples of the employed distance functions are L 2 distance [21], Chi-squared [22], weighted similarity [23], and probability of belongingness to different classes [24]. However, most employed distance functions take the following form:…”

Section: Related Workmentioning

confidence: 99%

Learning Global-Local Distance Metrics for Signature-Based Biometric Cryptosystems

2017

View full text Add to dashboard Cite

Biometric traits, such as fingerprints, faces and signatures have been employed in bio-cryptosystems to secure cryptographic keys within digital security schemes. Reliable implementations of these systems employ error correction codes formulated as simple distance thresholds, although they may not effectively model the complex variability of behavioral biometrics like signatures. In this paper, a Global-Local Distance Metric (GLDM) framework is proposed to learn cost-effective distance metrics, which reduce within-class variability and augment between-class variability, so that simple error correction thresholds of bio-cryptosystems provide high classification accuracy. First, a large number of samples from a development dataset are used to train a global distance metric that differentiates within-class from between-class samples of the population. Then, once user-specific samples are available for enrollment, the global metric is tuned to a local user-specific one. Proof-of-concept experiments on two reference offline signature databases confirm the viability of the proposed approach. Distance metrics are produced based on concise signature representations consisting of about 20 features and a single prototype. A signature-based bio-cryptosystem is designed using the produced metrics and has shown average classification error rates of about 7% and 17% for the PUCPR and the GPDS-300 databases, respectively. This level of performance is comparable to that obtained with complex state-of-the-art classifiers.

show abstract

“…Our dataset is publicly available at http://www-cvr.ai.uiuc.edu/ponce grp/data, and several other research groups graciously provided test results on it using their systems. The specific algorithms tested were the ones proposed by Ferrari, Tuytelaars & Van Gool [7], Lowe [20], Mahamud & Hebert [21], and Moreels, Maire & Perona [25]. In addition, we performed a test using our wide-baseline matching procedure between a database of training images and the test set, without using 3D models.…”

Section: D Object Recognitionmentioning

confidence: 99%

3D Object Modeling and Recognition from Photographs and Image Sequences

Rothganger

Lazebnik

Schmid

et al. 2006

Toward Category-Level Object Recognition

View full text Add to dashboard Cite

Abstract. This chapter proposes a representation of rigid three-dimensional (3D) objects in terms of local affine-invariant descriptors of their images and the spatial relationships between the corresponding surface patches. Geometric constraints associated with different views of the same patches under affine projection are combined with a normalized representation of their appearance to guide the matching process involved in object modeling and recognition tasks. The proposed approach is applied in two domains: (1) Photographs -models of rigid objects are constructed from small sets of images and recognized in highly cluttered shots taken from arbitrary viewpoints. (2) Video -dynamic scenes containing multiple moving objects are segmented into rigid components, and the resulting 3D models are directly matched to each other, giving a novel approach to video indexing and retrieval.

show abstract

The optimal distance measure for object detection

Abstract: We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes.

Cited by 38 publications

References 13 publications

Stereo Correspondence with Local Descriptors for Object Recognition

Stereo Correspondence with Local Descriptors for Object Recognition

Learning Global-Local Distance Metrics for Signature-Based Biometric Cryptosystems

3D Object Modeling and Recognition from Photographs and Image Sequences

Contact Info

Product

Resources

About