A Survey of Face Hallucination

Liang, Yan; Lai, Jianhuang; Zheng, Wei‐Shi; Cai, Zemin

doi:10.1007/978-3-642-35136-5_11

Cited by 14 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As it can be seen from the result of Bicubic interpolation on 8 × 8, the LR image is slightly rotated which could be seen as misaligned. Misalignment can cause a severe degradation on the hallucination result as reported by [8], however, the proposed method still maintains reasonable quality. These results show that the proposed method is robust on hallucinating VLR images for face recognition despite the simplicity of the algorithm.…”

Section: Visual Quality and Recognition Ratementioning

confidence: 64%

Hallucination space relationship learning to improve very low resolution face recognition

Ahn

Kim

Ch’ng

2015

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)

View full text Add to dashboard Cite

It is known that face recognition rate is affected by the resolution of probe image. Therefore it is natural to expect improving the resolution via face hallucination would increase the recognition rate. However, it was concluded in the previous works that improvement in the visual quality does not necessarily lead to a better recognition rate, and performance of face hallucination for recognition is especially poor when very low resolution (VLR) images are used. Experiment results in this paper will show that there is a correlation between visual quality and recognition rate. And hallucination space relationship learning algorithm is proposed which is robust on hallucinating VLR images to improve the performance in terms of both visual quality and recognition rate.

show abstract

Section: Visual Quality and Recognition Ratementioning

confidence: 64%

Hallucination space relationship learning to improve very low resolution face recognition

Ahn

Kim

Ch’ng

2015

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)

View full text Add to dashboard Cite

show abstract

“…The face hallucination method is one of learning-based SR methods, which is proposed for resolution enhancement of facial images [ 6 – 12 ]. In this section, we briefly introduce the basic concept of face hallucination, which is shown in Figure 1 .…”

Section: Face Hallucinationmentioning

confidence: 99%

“…Face hallucination is one of learning-based SR techniques proposed by Baker and Kanade [ 1 , 6 ], which is focused on resolution enhancement of facial images. To date, a lot of algorithms of face hallucination methods have been proposed [ 7 – 12 ]. Though face hallucination is a powerful and useful technique, some detailed high-frequency components cannot be recovered.…”

Section: Introductionmentioning

confidence: 99%

Alignment-Free and High-Frequency Compensation in Face Hallucination

Chen

Han

2014

The Scientific World Journal

View full text Add to dashboard Cite

Face hallucination is one of learning-based super resolution techniques, which is focused on resolution enhancement of facial images. Though face hallucination is a powerful and useful technique, some detailed high-frequency components cannot be recovered. It also needs accurate alignment between training samples. In this paper, we propose a high-frequency compensation framework based on residual images for face hallucination method in order to improve the reconstruction performance. The basic idea of proposed framework is to reconstruct or estimate a residual image, which can be used to compensate the high-frequency components of the reconstructed high-resolution image. Three approaches based on our proposed framework are proposed. We also propose a patch-based alignment-free face hallucination. In the patch-based face hallucination, we first segment facial images into overlapping patches and construct training patch pairs. For an input low-resolution (LR) image, the overlapping patches are also used to obtain the corresponding high-resolution (HR) patches by face hallucination. The whole HR image can then be reconstructed by combining all of the HR patches. Experimental results show that the high-resolution images obtained using our proposed approaches can improve the quality of those obtained by conventional face hallucination method even if the training data set is unaligned.

show abstract

“…Essa [9] proposed dynamic expression description method FACS+ based on video. It solved the problem that there was no time description information in FACS.…”

Section: Introductionmentioning

confidence: 99%

Feature Fusion Algorithm for Multimodal Emotion Recognition from Speech and Facial Expression Signal

Zhao

Wang

2016

MATEC Web of Conferences

View full text Add to dashboard Cite

Abstract. In order to overcome the limitation of single mode emotion recognition. This paper describes a novel multimodal emotion recognition algorithm, and takes speech signal and facial expression signal as the research subjects. First, fuse the speech signal feature and facial expression signal feature, get sample sets by putting back sampling, and then get classifiers by BP neural network (BPNN). Second, measure the difference between two classifiers by double error difference selection strategy. Finally, get the final recognition result by the majority voting rule. Experiments show the method improves the accuracy of emotion recognition by giving full play to the advantages of decision level fusion and feature level fusion, and makes the whole fusion process close to human emotion recognition more, with a recognition rate 90.4%.

show abstract

A Survey of Face Hallucination

Cited by 14 publications

References 17 publications

Hallucination space relationship learning to improve very low resolution face recognition

Hallucination space relationship learning to improve very low resolution face recognition

Alignment-Free and High-Frequency Compensation in Face Hallucination

Feature Fusion Algorithm for Multimodal Emotion Recognition from Speech and Facial Expression Signal

Contact Info

Product

Resources

About