Quantitative Analysis of Facial Paralysis Using Local Binary Patterns in Biomedical Videos

Abstract

Facial paralysis is the loss of voluntary muscle movement of one side of the face. A quantitative, objective, and reliable assessment system would be an invaluable tool for clinicians treating patients with this condition. This paper presents a novel framework for objective measurement of facial paralysis. The motion information in the horizontal and vertical directions and the appearance features on the apex frames are extracted based on the local binary patterns (LBPs) on the temporal-spatial domain in each facial region. These features are temporally and spatially enhanced by the application of novel block processing schemes. A multiresolution extension of uniform LBP is proposed to efficiently combine the micropatterns and large-scale patterns into a feature vector. The symmetry of facial movements is measured by the resistor-average distance (RAD) between LBP features extracted from the two sides of the face. Support vector machine is applied to provide quantitative evaluation of facial paralysis based on the House-Brackmann (H-B) scale. The proposed method is validated by experiments with 197 subject videos, which demonstrates its accuracy and efficiency.

Evaluation of Facial Paralysis Based on Spatial Features of Filtered Images

“…Table 2 presents the recognition rates of using of LBP images filtered by Gabor filters (GBLBP), LBP images decomposed by wavelet transform (WLLBP). Our results are also compared with other conventional methods such as method using intensity of pixel (IP) [1], [3], LBP images (LBP) [2], [3], [7], intensity image filtered by Gabor filters (GBIP) [3] and wavelet decomposition of intensity images (WLIP) [4]. From the result table, we can see that the average recognition rates of GBLBP and WLLPB are better than the conventional methods.…”

“…Some typical methods include the methods of Watchman et al [1] and He et al [2]. The main principle is based on the measurement of asymmetry between two sides of the face.…”

Quantitative Assessment of Facial Paralysis Based on Spatiotemporal Features

“…Finally, we compare our recognition results with that of the other conventional methods. The conventional methods include the intensity of pixel based (IP-B) [3], [6], the LBP based (LPB-B) [4], [6], the Gabor image of intensity of pixel based (GBIP-B) [6] and the Gabor image of LBP based (GBLBP-B) [6] method. For our method, because we extract the spatiotemporal features based on the tracking of landmarks, we denote the "Tracking" as the name of our method for shortness in result tables.…”

“…Some typical methods include the methods of Watchman et al [3] and He et al [4]. The main principle is based on the measurement of the asymmetric features between the two sides of the face.…”

Realce E Reconhecimento De Voz Contínua Em Ambientes Adversos

“…Esta nova abordagem, chamada Ideal Neighborhood Mask (INM), usa a técnica Local Binary pattern (LBP) [198] [199], que é frequentemente usada no processamento de imagens em 2-D para a descrição da textura. Os LBPs tornaram-se como uns dos melhores descritores de textura, em termos de desempenho e habilidades altamente discriminativas e computacionalmente simples e eficientes [200] [201].…”