SVD Face: Illumination-Invariant Face Representation

Kim, Wonjun; Suh, Sungjoo; Hwang, Wonjun; Han, Jae-Joon

doi:10.1109/lsp.2014.2334656

Cited by 48 publications

(27 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is not straightforward to determine how many components should be removed. Another solution is to learn an illumination invariant representation [14,15,16,17]. For example, O. Arandjelović et al [14] combines a weak photometric model with a statistical model to achieve invariance to illumination, pose and user motion pattern variation.…”

Section: Albedo Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Recovering variations in facial albedo from low resolution images

Chen

Wang

Hu³

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

Recovering facial albedo from low quality face images is a challenging task which arises when face recognition is attempted in the wild. Low quality of facial images is usually caused by extrinsic factors such as low resolution and noises, and intrinsic ones such as expressions. Existing research recovers facial albedo by dealing with the extrinsic and intrinsic factors separately. However, it is more natural and potentially more useful to approach albedo recovery by removing the two effects simultaneously.In this paper, we present a novel framework which can recover facial albedo by jointly solving these for both the extrinsic and intrinsic sources of uncertainty. This framework models albedo recovery problem by a joint optimization process which alternatively

show abstract

Section: Albedo Estimationmentioning

confidence: 99%

“…Related works such as [20,14,15,16,17] only deal with single sources of facial image variation (e.g., illumination variation), or perform super resolution independently [8,21,9,10,11,22,23]. Thus, there are no peer methods for direct comparison.…”

Section: Performancementioning

confidence: 99%

Recovering variations in facial albedo from low resolution images

Chen

Wang

Hu³

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Some other feature vectors applied by different researchers for improving the recognition accuracy in case of multiple feature difference parameters includes DCT, Nearest Neighbor Discriminant Analysis [10], LBP [12], Gabor Filter [13], textural feature [18] etc. These features are used individually or collectively for improving the recognition accuracy in case of head movement [14], pose variation [15], illumination [16][17] variant, age variation etc. In this paper, a aspect variant analysis is presented by using the static and dynamic equalization along with multiple featured analysis.…”

Section: Related Workmentioning

confidence: 99%

Multi Featured Fuzzy based Block Weight Assignment and Block Frequency Map Model for Transformation Invariant Facial Recognition

Juneja¹,

Rana²

2018

IJIGSP

View full text Add to dashboard Cite

Abstract-Misalignment of the camera, some jerk during capture is natural that results some tilt or geometric transformed photo. The accurate recognition on these misaligned facial images is one of the biggest challenges in real time systems. In this paper, a fuzzy enabled multiparameter based model is presented, which is applied to individual blocks to assign block weights. At first, the model has divided the image into square segments of fixed size. Each segmented division is analyzed under directional, structural and texture features. Fuzzy rule is applied on the obtained quantized values for each segment and to assign weights to each segment. While performing the recognition process, each weighted block is compared with all weighted-feature blocks of training set. A weight-ratio to exactly map and one-to-all map methods are assigned to identify overall matching accuracy. The work is applied on FERET and LFW datasets with rotational, translational and skewed transformation. The comparative observations are taken against KPCA and ICA methods. The proportionate transformation specific observations show that the model has improved the accuracy up to 30% for rotational and skewed transformation and in case of translation the improvement is up to 11%.

show abstract

“…The natural face image is taken in diverse environment condition which cause sundry illumination [1,2] problem. Illumination affects the image entirely or moderately.…”

Section: Introductionmentioning

confidence: 99%

MFAST Processing Model for Occlusion and Illumination Invariant Facial Recognition

Juneja¹

2016

Advanced Computing and Communication Technologies

View full text Add to dashboard Cite

Illumination Variation and wearable objects loses the partial facial information that it degrades the accuracy of recognition process. In this paper, a high performance driven accurate method is provided for facial recognition. The proposed MFAST (Multi-Featured Analog Signal Transformed) Model genuinely transmute the substantial facial information in analog featured conformation. This analog featured structured is formed using segmented featured elicitation. These features include center difference evaluation as moment, the asymmetric structure analysis as Skewness and Outlier Prone Measure as Kurtosis. These analogous features are shaped to justified form and generate a compound signal form. Mapping of these distillates signal points over facial dataset with specification of threshold window. The decomposed form recognition method enhanced the accuracy and performance. The experimentation on FERET, LFW and Indian Databases signify that the model outperformed than existing algorithms.

show abstract

SVD Face: Illumination-Invariant Face Representation

Cited by 48 publications

References 13 publications

Recovering variations in facial albedo from low resolution images

Recovering variations in facial albedo from low resolution images

Multi Featured Fuzzy based Block Weight Assignment and Block Frequency Map Model for Transformation Invariant Facial Recognition

MFAST Processing Model for Occlusion and Illumination Invariant Facial Recognition

Contact Info

Product

Resources

About