Towards robust face recognition from video

Price, Jeffery R.; Gee, Trevor

doi:10.1109/aipr.2001.991209

Cited by 9 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although it is possible to compare top-down feature vectors in the 3193-D space, it is computationally demanding and unnecessary since there are redundant features as well as features that are not helpful with respect to the sidewall estimation problem. Motivated by techniques that have been successfully applied to template-based face recoginition, 5,6 we adopt an LDA approach for dimensionality reduction. Note that discrimination in our system refers to the ability to differentiate between top-downs associated with different sidewall shapes.…”

Section: Dimensionality Reductionmentioning

confidence: 99%

“…One problem often encountered with LDA in practice is that the original feature vectors may be of such high dimensionality ͑3193 in our case͒ that the storage and/or eigenanalysis of S b and S w may be impractical. In such applications, some other form of dimensionality reductionusually principal component analysis ͑PCA͒ in the face recognition case 5,6,10 -performed prior to LDA. PCA, however, does not consider class labels and can decrease discriminative capability.…”

Section: Direct Ldamentioning

confidence: 99%

See 1 more Smart Citation

Semiconductor sidewall shape estimation

Bingham

2004

J. Electron. Imaging

View full text Add to dashboard Cite

For process control, linewidth measurements are commonly performed on semiconductor wafers using top-down images from critical dimension measurement scanning electron microscopes (CD-SEMs). However, a measure of the line sidewall shape will be required as linewidths continue to shrink. Sidewall shape can be measured by physically cleaving the device and performing an SEM scan of the cross section, but this process is time consuming and results in destruction of product wafers. We develop a technique to estimate sidewall shape from top-down SEM images using pattern recognition based on historical cross section/top-down image pairs. Features are computed on subimages extracted from the top-down images. Several combinations of principal component analysis (PCA) and flavors of linear discriminant analysis (LDA) are employed to reduce the dimensionality of the feature vectors and maximize the spread between different sidewall shapes. Direct, weighted LDA (DW-LDA) results in a feature set that provides the best sidewall shape estimation. Experimental testing of the sidewall estimation system shows a root mean square error of approximately 1.8% of the linewidth, showing that this system is a viable method for estimating sidewall shape with little impact on the fabrication process (no new hardware and a minimal increase in process setup).

show abstract

Section: Dimensionality Reductionmentioning

confidence: 99%

Section: Direct Ldamentioning

confidence: 99%

Semiconductor sidewall shape estimation

Bingham

2004

J. Electron. Imaging

View full text Add to dashboard Cite

show abstract

“…Further, a new dataset simulating "On-the-Fly" face detection in video is collected and made available for the public. In [4], multi-classifier based face detection in video is proposed. Here, each classifier is learned on different parts of face like eyes, nose and forehead.…”

Section: Introductionmentioning

confidence: 99%

Robust “On-the-Fly” person identification using Sparse Representation

Ramachandra

Yang

Busch

2013

2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

View full text Add to dashboard Cite

On-the-fly person identification using face has been receiving more and more attention recently as it exhibits additional challenges that include uncontrolled poses, change in illumination and focus as compared to that of conventional face recognition. In this paper, we propose an efficient scheme that can be structured in two steps namely face detection and person identification to accurately address the challenges in "Onthe-Fly" person identification. The proposed face detection scheme is based on the skin color region detection and a novel region based association scheme which is efficient and innovative in locating the evolving face in the video. We then, propose to carry out the person identification by employing LogGabor transform and Sparse Representation Classifier (SRC). Extensive experiments are carried out on the public available video surveillance 'ChokePoint' dataset leading to the highest observed closed-set identification rate of 91% with efficient computational speed of 27 frames/minute on normal desktop.

show abstract