Open AccessDense small face detection based on regional cascade multi‐scale method
Author(s) -
Ke Xiao,
Li Jianping,
Guo Wenzhong
Publication year - 2019
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2018.6571
Subject(s) - detector , computer science , artificial intelligence , object detection , cascade , convolutional neural network , face (sociological concept) , scale (ratio) , computer vision , scalability , pattern recognition (psychology) , face detection , feature (linguistics) , set (abstract data type) , pyramid (geometry) , object class detection , facial recognition system , optics , telecommunications , physics , engineering , social science , sociology , linguistics , philosophy , quantum mechanics , database , chemical engineering , programming language
In the field of object detection, the research on the problem of detecting small face is the most extensive, but when there are objects with obvious scale differences in the image, the detection performance is not obvious, which is due to the scale invariance properties of the deep convolutional neural networks. Although in recent years, there have been some methods proposed to solve this problem such as FPN and SNIP, which is based on feature pyramid. However, they have not fundamentally solved the problem. A regional cascade multi‐scale detection method has been proposed. First, a global detector and several local detectors have been trained, respectively. The global detector is trained by the original training set, while the local detector is trained by the sub‐training set generated by the original training set. Second, the global detector can detect object roughly and the local detectors can produce more detailed results that improve the performance of global detector. Finally, to integrate the detection results of global detector and local detectors as the output, non‐maximum suppression methods are used. The method can be carried in any depth model of object detection, has good scalability, and is more suitable for dense face detection.