A Study on Optimal Face Ratio for Recognition Using Part-Based Feature Extractor

Neo, Han Foon; Teo, Chuan Chin; Teoh, Andrew Beng Jin

doi:10.1109/sitis.2007.52

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the results indicate that the eye region exhibit the highest discriminative value. Other works presenting results for particular regions of the face can be found in (Savvides et al 2004a(Savvides et al , b, 2006Neo et al 2007Neo et al , 2010Teo et al 2007;Wright et al 2009;Woodard et al 2010;Park et al 2011).…”

Section: Introductionmentioning

confidence: 99%

A study in facial regions saliency: a fuzzy measure approach

et al. 2013

View full text Add to dashboard Cite

People recognize familiar faces in a similar way by using interior facial features (facial regions) such as eyes, nose, mouth, etc. However, the importance of these regions in the realization of face identification and a quantification of the impact of such regions on the recognition process could vary from one region to another. An intuitively appealing observation is that of monotonicity: the more regions are taken into account in the recognition process, the better. From a formal point of view, the relevance of the facial regions and an aggregation of these pieces of experimental evidence can be described in the formal setting of fuzzy measures. Fuzzy measures are of particular interest with this regard given their monotonicity property (which stands in a clear contrast with the more restrictive additivity property inherent to probability-like measures). In this study, we concentrate on the construction of fuzzy measures (more specifically, k-fuzzy measure) and characterize their performance in the problem of face recognition using a collection of experimental data.

show abstract

Section: Introductionmentioning

confidence: 99%

A study in facial regions saliency: a fuzzy measure approach

et al. 2013

View full text Add to dashboard Cite

show abstract

“…10 Face images of size 1806200 are normalised to 73661, and cropped to several sizes (25, 50 and 75% of the face). This face verification technique is conducted by using different part-based linear subspace feature extractors to estimate the optimal face ratio, such as non-negative matrix factorisation, local non-negative matrix factorisation and spatially confined nonnegative matrix factorisation.…”

Section: Introductionmentioning

confidence: 99%

Lower‐quarter‐based face verification using correlation filter

Sleit

Abu‐Hurra

Almobaideen

2011

The Imaging Science Journal

View full text Add to dashboard Cite

Correlation filters have been applied successfully in pattern matching needed in face verification. In this paper, we propose a face verification technique based on half the lower face using the minimum average correlation energy (MACE) filter which has the ability to satisfy the correlation peak at the origin, and minimise the average correlation energy. Our experiments show that the application of the MACE filter for face verification using the lower-left or -right parts of the face generates authentication with at least 80% accuracy. Authentication accuracy using the MACE filter based on the whole face increases to at least 88%, but requires approximately twice as much response time.

show abstract