Local Binary Pattern Networks

Lin, Jeng-Hau; Lazarow, Justin; Yang, Yuexiang; Hong, Dezhi; Gupta, Rajesh K.; Tu, Zhuowen

doi:10.1109/wacv45572.2020.9093550

Cited by 7 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome the limitation that traditional LBP can lose the neighboring pixels related to different scales that can affect the texture of facial images, Yasmin et al [ 30 ] proposed a new extended LBP method based on the bitwise “AND” operation of two rotational kernels to extract facial features. In view of satisfactory performance of the LBP operator, the CNNs that integrate advantages of the LBP have been developed [ 41 , 55 , 56 ]. Lyons et al [ 27 ] used a multiscale, multiorientation set of Gabor filters to code facial expression images through comparing the similarity space derived from semantic ratings of the images by human observers with the one derived from Gabor representation; authors believed that the latter shows a significant degree of psychological plausibility.…”

Section: Related Workmentioning

confidence: 99%

Patch Attention Layer of Embedding Handcrafted Features in CNN for Facial Expression Recognition

Liang

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

Recognizing facial expression has attracted much more attention due to its broad range of applications in human–computer interaction systems. Although facial representation is crucial to final recognition accuracy, traditional handcrafted representations only reflect shallow characteristics and it is uncertain whether the convolutional layer can extract better ones. In addition, the policy that weights are shared across a whole image is improper for structured face images. To overcome such limitations, a novel method based on patches of interest, the Patch Attention Layer (PAL) of embedding handcrafted features, is proposed to learn the local shallow facial features of each patch on face images. Firstly, a handcrafted feature, Gabor surface feature (GSF), is extracted by convolving the input face image with a set of predefined Gabor filters. Secondly, the generated feature is segmented as nonoverlapped patches that can capture local shallow features by the strategy of using different local patches with different filters. Then, the weighted shallow features are fed into the remaining convolutional layers to capture high-level features. Our method can be carried out directly on a static image without facial landmark information, and the preprocessing step is very simple. Experiments on four databases show that our method achieved very competitive performance (Extended Cohn–Kanade database (CK+): 98.93%; Oulu-CASIA: 97.57%; Japanese Female Facial Expressions database (JAFFE): 93.38%; and RAF-DB: 86.8%) compared to other state-of-the-art methods.

show abstract