Constrained Variable Impedance Control using Quadratic Programming

Jin, Zhehao; Qin, Dongdong; Liu, Andong; Zhang, Wen‐An

doi:10.1109/icra46639.2022.9812210

Cited by 4 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The core idea of the overall design is: on the one hand, using the classifier of shallow network to quickly remove most of the background, on the other hand, let the deep network focus on the remaining area for face detection and recognition, which can not only guarantee the running speed, but also improve the algorithm recall rate. [9] First of all, the first level network belongs to shallow full convolution neural network, and is seen as a box when the generation of the network, the concrete structure are shown in figure 3 below, the whole contains three convolution layer and a maximum pool, after the input image of face box after the proposal of using human face classification to determine whether the topic area contains face, At the same time, the regression of the face boundary frame and the location of the key points of the face are carried out. This process can effectively exclude non-face regions in the image, and generate more candidate regions that may have faces.…”

Section: Face Detection and Recognition Technology Analysis Based On ...mentioning

confidence: 99%

Face detection and recognition technology based on EfficientNet and BNNeck

2023

International Conference on Mathematics, Modeling, and Computer Science (MMCS2022)

View full text Add to dashboard Cite

Face detection is the premise of face attribute recognition, and face attribute recognition is the deep understanding of the computer to face image features. In the construction and development of modern society, with the continuous development of computer vision technology, identity recognition technology with biometric recognition as the core has been paid attention to, and began to be widely used in face verification, interpersonal interaction, precision delivery and other fields. Therefore, on the basis of understanding the current research status of artificial intelligence technology theory and EfficientNet, BNNeck algorithm design, the paper deeply discusses the neural network as the core of the cascade face detection and recognition technology in the new era. The final results show that the improved cascaded face recognition method proposed in this paper has research value.

show abstract

Section: Face Detection and Recognition Technology Analysis Based On ...mentioning

confidence: 99%