A new ranking method for principal components analysis and its application to face image analysis

Thomaz, Carlos Eduardo; Giraldi, Gilson A.

doi:10.1016/j.imavis.2009.11.005

Cited by 503 publications

(222 citation statements)

References 18 publications

Supporting

Mentioning

211

Contrasting

Unclassified

Order By: Relevance

“…Faces were frontal facing and prealigned images from a face database maintained by the Department of Electrical Engineering of FEI, São Paolo, Brazil (Thomaz & Giraldi, 2010). The set of faces contained an equal number of male and female pictures.…”

Section: Methodsmentioning

confidence: 99%

The differential effects of emotional salience on direct associative and relational memory during a nap

Alger

Payne

2016

Cogn Affect Behav Neurosci

View full text Add to dashboard Cite

Relational memories are formed from shared components between directly learned memory associations, flexibly linking learned information to better inform future judgments. Sleep has been found to facilitate both direct associative and relational memories. However, the impact of incorporating emotionally salient information into learned material and the interaction of emotional salience and sleep in facilitating both types of memory is unknown. Participants encoded two sets of picture pairs, with either emotionally negative or neutral objects paired with neutral faces. The same objects were present in both sets, paired with two different faces across the sets. Baseline memory for these directly paired associates was tested immediately after encoding, followed by either a 90-min nap opportunity or wakefulness. Five hours after learning, a surprise test assessed relational memory, the indirect association between two faces paired with the same object during encoding, followed by a retest of direct associative memory. Overall, negative information was remembered better than neutral for directly learned pairs. A nap facilitated both preservation of direct associative memories and formation of relational memories, compared to remaining awake. Interestingly, however, this sleep benefit was observed specifically for neutral directly paired associates, while both neutral and negative relational associations benefitted from a nap. Finally, REM sleep played opposing roles in neutral direct and relational associative memory formation, with more REM sleep leading to forgetting of direct associations but promoting relational associations, suggesting that, while not benefitting memory consolidation for directly learned details, REM sleep may foster the memory reorganization needed for relational memory.Keywords Emotion . Associative memory . Naps . Sleep . Inference . Relational memory In our encounters with the everyday stream of information, we do not encode and store all individual experiences in a veridical fashion. Rather, new information is integrated with old, and overlapping details are consolidated into schemata, or networks linked by common features of related memories, to flexibly form novel relationships (Eichenbaum, 2004;Eichenbaum & Cohen, 2001). We use these new representations derived from related memories to adaptively make inferential judgments about future experiences. However, our everyday experiences are not devoid of emotion. Emotional salience, defined by the valence (negative to positive) and arousal (calming to arousing) of an experience, is a biologically adaptive cue that can influence how an event is remembered and possibly how it is integrated in memory. In addition to the influence of emotion, sleep during the consolidation and integration period of a new memory may impact its fate. This experiment investigates the separate and interacting contributions of emotional salience and sleep to the consolidation of direct associative and relational memories, the indirect associations between two...

show abstract

Section: Methodsmentioning

confidence: 99%

The differential effects of emotional salience on direct associative and relational memory during a nap

Alger

Payne

2016

Cogn Affect Behav Neurosci

View full text Add to dashboard Cite

show abstract

“…We used the Extended Cohn-Kanade (CK+) [20], Georgia Tech [21], FEI [22], Extended YALE B [23] and FRGC v1 [24] face databases. All the images are copped except the Extended Cohn-Kanade (CK+) database and resized to 27×32.…”

Section: Resultsmentioning

confidence: 99%

“…The algorithm used for the FR by SN is based on the dyadic sampling necessary for building the shearlet candidates library to use in the network and the frames theory for the weights calculations [17]. By sampling the continuous shearlet transform ( , , ) SH a s t  on an appropriate discretization lattice for the scaling, shear, and translation parameters ( , , ) a s t , one obtains a discrete transform which is associated to a Parseval (tight) frame for 22 () L . Indeed, we obtain a discrete system of shearlets…”

Section: Approximation By Shearlet Network (Sn)mentioning

confidence: 99%

Shearlet Network-based Sparse Coding Augmented by Facial Texture Features for Face Recognition

Borgi

Labate

El'arbi

et al. 2013

Image Analysis and Processing – ICIAP 2013

View full text Add to dashboard Cite

Abstract. One open challenge in face recognition (FR) is the single training sample per subject. This paper addresses this problem through a novel approach called Shearlet Network (SN) which takes advantage of the sparse representation (SR) properties of shearlets in biometric applications, specifically, for face coding and recognition. Shearlets are derived from wavelets with composite dilations, a method extending the traditional wavelet approach by allowing for the construction of waveforms defined not only at various scales and locations but also at various orientations. The contributions of this paper are the combination of the power of multi-scale representation with a unique ability to capture geometric information to derive a very efficient representation of facial templates, and the use of a PCA-based approach to design a fusion step by a refined model of belief function based on the Dempster-Shafer rule in the context of confusion matrices. This last step is helpful to improve the processing of facial texture features. We compared our new algorithm (SNPCA) against SN, a wavelet network (WN) implementation and other standard algorithms. Our tests, run on several face databases including FRGC, Extended Yale B database and others, show that this approach yields a very competitive performance as compared to wavelet networks (WN), standard shearlet and PCA-based methods.

show abstract

“…In this section we describe the experiments conducted on the FERET [15] and FEI dataset [16]. All the face images are manually aligned.…”

Section: Methodsmentioning

confidence: 99%

Face Hallucination by Learning Local Distance Metric

Zou

Zhou

Liao

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this letter, we propose a novel method for face hallucination by learning a new distance metric in the low-resolution (LR) patch space (source space). Local patch-based face hallucination methods usually assume that the two manifolds formed by LR and high-resolution (HR) image patches have similar local geometry. However, this assumption does not hold well in practice. Motivated by metric learning in machine learning, we propose to learn a new distance metric in the source space, under the supervision of the true local geometry in the target space (HR patch space). The learned new metric gives more freedom to the presentation of local geometry in the source space, and thus the local geometries of source and target space turn to be more consistent. Experiments conducted on two datasets demonstrate that the proposed method is superior to the state-ofthe-art face hallucination and image super-resolution (SR) methods.

show abstract

A new ranking method for principal components analysis and its application to face image analysis

Cited by 503 publications

References 18 publications

The differential effects of emotional salience on direct associative and relational memory during a nap

The differential effects of emotional salience on direct associative and relational memory during a nap

Shearlet Network-based Sparse Coding Augmented by Facial Texture Features for Face Recognition

Face Hallucination by Learning Local Distance Metric

Contact Info

Product

Resources

About