Learning Statistical Structure for Object Detection

Schneiderman, Henry

doi:10.1007/978-3-540-45179-2_54

Cited by 19 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…non-face). Bayesian classifiers are a compact way of capturing shared dependencies between feature values, and can also be used in a generative framework to learning the Bayesian network 10 . GOTS implements a semi naive Bayes classifier, which assumes the general form of:…”

Section: Learning a Restricted Bayesian Network For Object Detectionmentioning

confidence: 99%

Toward automated face detection in thermal and polarimetric thermal imagery

Gordon

Acosta

Short

et al. 2016

Signal Processing, Sensor/Information Fusion, and Target Recognition XXV

View full text Add to dashboard Cite

Visible spectrum face detection algorithms perform pretty reliably under controlled lighting conditions. However, variations in illumination and application of cosmetics can distort the features used by common face detectors, thereby degrade their detection performance. Thermal and polarimetric thermal facial imaging are relatively invariant to illumination and robust to the application of makeup, due to their measurement of emitted radiation instead of reflected light signals. The objective of this work is to evaluate a government off-the-shelf wavelet based naïve-Bayes face detection algorithm and a commercial off-the-shelf Viola-Jones cascade face detection algorithm on face imagery acquired in different spectral bands. New classifiers were trained using the Viola-Jones cascade object detection framework with preprocessed facial imagery. Preprocessing using Difference of Gaussians (DoG) filtering reduces the modality gap between facial signatures across the different spectral bands, thus enabling more correlated histogram of oriented gradients (HOG) features to be extracted from the preprocessed thermal and visible face images. Since the availability of training data is much more limited in the thermal spectrum than in the visible spectrum, it is not feasible to train a robust multi-modal face detector using thermal imagery alone. A large training dataset was constituted with DoG filtered visible and thermal imagery, which was subsequently used to generate a custom trained Viola-Jones detector. A 40% increase in face detection rate was achieved on a testing dataset, as compared to the performance of a pre-trained/baseline face detector. Insights gained in this research are valuable in the development of more robust multimodal face detectors.

show abstract

Section: Learning a Restricted Bayesian Network For Object Detectionmentioning

confidence: 99%

Toward automated face detection in thermal and polarimetric thermal imagery

Gordon

Acosta

Short

et al. 2016

Signal Processing, Sensor/Information Fusion, and Target Recognition XXV

View full text Add to dashboard Cite

show abstract

“…Alternatively, one can compute the mutual information (or other scores) between the labels and single variables [21] or subsets of the variables [17]. These methods and other variable selection methods benefit from having a set of informative features.…”

Section: Introductionmentioning

confidence: 99%

Combining Variable Selection with Dimensionality Reduction

Wolf¹,

Bileschi²

2005

View full text Add to dashboard Cite

Report Documentation Page AbstractThis paper bridges the gap between variable selection methods (e.g., Pearson coefficients, KS test) and dimensionality reduction algorithms (e.g., PCA, LDA). Variable selection algorithms encounter difficulties dealing with highly correlated data, since many features are similar in quality. Dimensionality reduction algorithms tend to combine all variables and cannot select a subset of significant variables. Our approach combines both methodologies by applying variable selection followed by dimensionality reduction. This combination makes sense only when using the same utility function in both stages, which we do. The resulting algorithm benefits from complex features as variable selection algorithms do, and at the same time enjoys the benefits of dimensionality reduction.

show abstract

“…There appears to be no global acceptance of this fact or any body of work that lays down the foundations for systematic application of these approaches. There are arguably as many methodologies as there are distinct learning approaches [198,202,203].…”

Section: Face Detection and Localizationmentioning

confidence: 99%