Facial-expression recognition based on a low-dimensional temporal feature space

Abdallah, Taoufik Ben; Guermazi, Radhouane; Hammami, Mohamed

doi:10.1007/s11042-017-5354-x

Cited by 10 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The findings in [1] show that temporal features contain meaningful information that could be further utilized in facilitating the emotion recognition tasks. The PTLBP u2 has three different levels with each level consisting of different sizes and number of sub-regions.…”

Section: Existing Video-based Face/expression Recognitionmentioning

confidence: 97%

“…In [1], Abdallah et al exploited the temporal features which extracts the XT and YT orthogonal planes from the LBP-TOP for the purpose of emotion recognition. They proposed the Pyramid of Uniform Temporal Local Binary Pattern Representation (PTLBP u2 ) which divides the video sequences into different number of sub-regions.…”

Section: Existing Video-based Face/expression Recognitionmentioning

confidence: 99%

“…For instance, witnesses under protection program may become Fig. 1 Sub-regions selected for PTLBP 2u with the combination of level 2 and level 3 [1] victims of the automatic facial recognition system as the system makes it easier to expose the protected witness's identity.…”

Section: Security Issues Against Face Recognitionmentioning

confidence: 99%

“…Besides, the existing research on video-based temporal facial features recognition systems tend to focus more on recognizing the emotions instead of the identity [4]. The research conducted in [1] which uses temporal features for emotion recognition shows that temporal features hold important and useful information regarding facial movements, which relate to facial expressions corresponding to underlying emotions. This furthermore forms an additional motivation in support of our aim of investigating the effects of temporal features on video-based face recognition of identity.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Faceless identification based on temporal strips

Leong

Phan

Baskaran

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

This paper first presents a novel approach for modelling facial features, Local Directional Texture (LDT), which exploits the unique directional information in image textures for the problem of face recognition. A variant of LDT with privacy-preserving temporal strips (TS) is then considered to achieve faceless recognition with a higher degree of privacy while maintaining high accuracy. The TS uses two strips of pixel blocks from the temporal planes, XT and YT, for face recognition. By removing the reliance on spatial context (i.e., XY plane) for this task, the proposed method withholds facial appearance information from public view, where only one-dimensional temporal information that varies across time are extracted for recognition. Thus, privacy is assured, yet without impeding the facial recognition task which is vital for many security applications such as street surveillance and perimeter access control. To validate the reliability of the proposed method, experiments were carried out using the Honda/UCSD, CK+, CAS(ME) 2 and CASME II databases. The proposed method achieved a recognition rate of 98.26% in the standard video-based face recognition database, Honda/UCSD. It also offers a 81.92% reduction in the dimension length required for storing the extracted features, in contrast to the conventional LBP-TOP.

show abstract

Section: Existing Video-based Face/expression Recognitionmentioning

confidence: 97%

Section: Existing Video-based Face/expression Recognitionmentioning

confidence: 99%

Section: Security Issues Against Face Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations