Hybrid Pyramid Convolutional Network for Multiscale Face Detection

Autor: Dongdong Fang, Guangqiang Yin, Shaoqi Hou, Yixi Pan, Ye Li
Rok vydání: 2021
Předmět:
Rotation
Article Subject
General Computer Science
Computer science
General Mathematics
Computer applications to medicine. Medical informatics
R858-859.7
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Neurosciences. Biological psychiatry. Neuropsychiatry
Context (language use)
02 engineering and technology
Convolutional neural network
Convolution
Robustness (computer science)
0202 electrical engineering
electronic engineering
information engineering
Pyramid (image processing)
Face detection
business.industry
General Neuroscience
020206 networking & telecommunications
Pattern recognition
General Medicine
Semantics
Feature (computer vision)
Face (geometry)
020201 artificial intelligence & image processing
Neural Networks
Computer
Artificial intelligence
business
Algorithms
RC321-571
Research Article
Zdroj: Computational Intelligence and Neuroscience
Computational Intelligence and Neuroscience, Vol 2021 (2021)
ISSN: 1687-5273
1687-5265
DOI: 10.1155/2021/9963322
Popis: Face detection remains a challenging problem due to the high variability of scale and occlusion despite the strong representational power of deep convolutional neural networks and their implicit robustness. To handle hard face detection under extreme circumstances especially tiny faces detection, in this paper, we proposed a multiscale Hybrid Pyramid Convolutional Network (HPCNet), which is a one-stage fully convolutional network. Our HPCNet consists of three newly presented modules: firstly, we designed the Hybrid Dilated Convolution (HDC) module to replace the fully connected layers in VGG16, which enlarges receptive field and reduces its loss of local information; secondly, we constructed the Hybrid Feature Pyramid (HFP) to combine semantic information from higher layers together with details from lower layers; and thirdly, to deal with the problem of occlusion and blurring effectively, we introduced Context Information Extractor (CIE) in HPCNet. In addition, we presented an improved Online Hard Example Mining (OHEM) strategy, which can enhance the average precision of face detection by balancing the number of positive and negative samples. Our method has achieved an accuracy of 0.933, 0.924, and 0.848 on the Easy, Medium, and Hard subset of WIDER FACE, respectively, which surpasses most of the advanced algorithms.
Databáze: OpenAIRE
Externí odkaz: