Filters








3,482 Hits in 5.3 sec

Joint Training of Cascaded CNN for Face Detection

Hongwei Qin, Junjie Yan, Xiu Li, Xiaolin Hu
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We present how jointly training can be conducted on naive CNN cascade and more sophisticated region proposal network (RPN) and fast R-CNN.  ...  The cascade in detection is popularized by seminal Viola-Jones framework and then widely used in other pipelines, such as DPM and CNN.  ...  Disscussion Except for the use of jointly trained cascaded CNNs for face detection, jointly trained RPN and fast R-CNN is also a promising method for fast and accurate face detection.  ... 
doi:10.1109/cvpr.2016.376 dblp:conf/cvpr/QinYLH16 fatcat:lwlsy4tzavavjbo5jnfz32fqtm

A convolutional neural network cascade for face detection

Haoxiang Li, Zhe Lin, Xiaohui Shen, Jonathan Brandt, Gang Hua
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
The proposed method runs at 14 FPS on a single CPU core for VGA-resolution images and 100 FPS using a GPU, and achieves state-of-the-art detection performance on two public face detection benchmarks.  ...  The proposed CNN cascade operates at multiple resolutions, quickly rejects the background regions in the fast low resolution stages, and carefully evaluates a small number of challenging candidates in  ...  This work is also partly supported by US National Science Foundation Grant IIS 1350763 and GH's start-up funds from Stevens Institute of Technology.  ... 
doi:10.1109/cvpr.2015.7299170 dblp:conf/cvpr/LiLSBH15 fatcat:zkmd3kel5nhhfmkooeosef2l3m

Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks

Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, Yu Qiao
2016 IEEE Signal Processing Letters  
Our method achieves superior accuracy over the state-of-the-art techniques on the challenging FDDB and WIDER FACE benchmark for face detection, and AFLW benchmark for face alignment, while keeps real time  ...  In particular, our framework adopts a cascaded structure with three stages of carefully designed deep convolutional networks that predict face and landmark location in a coarse-to-fine manner.  ...  E-mail: zz013@ie.cuhk.edu.hk We propose a new cascaded CNNs based framework for joint face detection and alignment, and carefully Joint Face Detection and Alignment using Multi-task Cascaded Convolutional  ... 
doi:10.1109/lsp.2016.2603342 fatcat:o73anfq5sngqbgdk3zj5aowuam

Face Detection based on Receptive Field Enhanced Multi-Task Cascaded Convolutional Neural Networks

Xiaochao Li, Zhenjie Yang, Hongwei Wu
2020 IEEE Access  
For real-time detection, cascade CNN based on the lightweight model is still the dominant structure that predicts face in a coarse-to-fine manner with strong generalization ability.  ...  Furthermore, our structure uses 16% fewer parameters. INDEX TERMS Face detection, cascade convolutional neural networks, receptive field.  ...  ., [14] presented a fast CNN's cascade face detector, using a CNN with a novel pyramid architecture, multi-layer merging, knowledge distilling online and offline hard sample mining.  ... 
doi:10.1109/access.2020.3023782 fatcat:pyb3nptd3bemnot3cun53jxfku

CRAFT Objects from Images

Bin Yang, Junjie Yan, Zhen Lei, Stan Z. Li
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Object detection is a fundamental problem in image understanding. One popular solution is the R-CNN framework [15] and its fast versions [14, 27] .  ...  We call the proposed method "CRAFT" (Cascade Regionproposal-network And FasT-rcnn), which tackles each task with a carefully designed network cascade.  ...  KGZD-EW-102-2, and by Au-thenMetric R&D Funds. We thank NVIDIA gratefully for GPU hardware donation and the reviewers for their many constructive comments.  ... 
doi:10.1109/cvpr.2016.650 dblp:conf/cvpr/YangYLL16 fatcat:7kaxpvel75fuvmxuegd5snccoq

CRAFT Objects from Images [article]

Bin Yang, Junjie Yan, Zhen Lei, Stan Z. Li
2016 arXiv   pre-print
Object detection is a fundamental problem in image understanding. One popular solution is the R-CNN framework and its fast versions.  ...  We call the proposed method "CRAFT" (Cascade Region-proposal-network And FasT-rcnn), which tackles each task with a carefully designed network cascade.  ...  KGZD-EW-102-2, and by Au-thenMetric R&D Funds. We thank NVIDIA gratefully for GPU hardware donation and the reviewers for their many constructive comments.  ... 
arXiv:1604.03239v1 fatcat:aic7b3snhjfa7dkdxdozchq3ji

Survey of Face Detection on Low-quality Images [article]

Yuqian Zhou, Ding Liu, Thomas Huang
2018 arXiv   pre-print
It inspires researchers to produce more robust design for face detection in the wild.  ...  Face detection is a well-explored problem. Many challenges on face detectors like extreme pose, illumination, low resolution and small scales are studied in the previous work.  ...  ACKNOWLEDGMENT This research work is supported in part by US Army Research Office grant W911NF-15-1-0317.  ... 
arXiv:1804.07362v1 fatcat:mw2qljjif5drzlplmjvwlfvsyq

Anchor Cascade for Efficient Face Detection

Baosheng Yu, Dacheng Tao
2019 IEEE Transactions on Image Processing  
Experimental results on two widely used face detection benchmarks, FDDB and WIDER FACE, demonstrate the effectiveness of the proposed framework.  ...  Specifically, comparing with a popular CNN-based cascade face detector MTCNN [2], our anchor cascade face detector greatly improves the detection accuracy, e.g., from 0.9435 to 0.9704 at 1k false positives  ...  SPECIFICALLY, WE USE MIN-FACE S min = 18 FOR BOTH APN24(S) AND APN24.anchor cascade, we further bridge the gap between CNN-based cascade face detectors and anchor-based face detectors.  ... 
doi:10.1109/tip.2018.2886790 fatcat:enyuxd4mz5ekxjalerjr4euadm

Detect face in the wild using CNN cascade with feature aggregation at multi-resolution

Jingjing Deng, Xianghua Xie
2017 2017 IEEE International Conference on Image Processing (ICIP)  
with Convolutional Neural Networks Features (R-CNNs) [4] , and Graph CNN [5] .  ...  The most relevant work to ours is [13] , where 3 face-nonface classification CNNs are used for separating face regions from background and 3 calibration CNNs are used to refine the location of detected  ... 
doi:10.1109/icip.2017.8297067 dblp:conf/icip/DengX17 fatcat:ehvuf27puvdlpe3catocmwqviy

Enhancing Detection Performance of Face Recognition Algorithm Using PCA-Faster R-CNN

Hashiru Isiaka Muhammad, Kabir Ibrahim Musa, Mustapha Lawal Abdulrahman, Abdullahi Abubakar, Kabiru Umar, Abdulhakeem Ishola
2021 European Journal of Electrical Engineering and Computer Science  
In particular, we improve the state-of-the-art Faster RCNN framework by using Principal Component Analysis (PCA) technique and Faster R CNN to detect and recognise faces in a face database.  ...  We designed and implemented a face recognition system using Principal Component Analysis (PCA) and Faster R Convolutional Neural Network (Faster R CNN).  ...  However, for object detection, there is high computational complexity in both approaches. Selective search is used by both of the algorithms above i.e. R-CNN and Fast R-CNN.  ... 
doi:10.24018/ejece.2021.5.3.321 fatcat:ryhhyu26nfazdaswi3kvcztfm4

Automated Detection of Greenhouse Structures Using Cascade Mask R-CNN

Haeng Yeol Oh, Muhammad Sarfraz Khan, Seung Bae Jeon, Myeong-Hun Jeong
2022 Applied Sciences  
Similarly, the F1-score of the proposed Cascade Mask R-CNN model was 62.07, which outperformed those of the baseline mask R-CNN and the Mask R-CNN with hyperparameter tuning and transfer learning considered  ...  The experimental results demonstrated that the mAP value of the proposed Cascade Mask R-CNN model was 83.6, which was 12.83 higher than baseline mask R-CNN, and 0.9 higher than Mask R-CNN with hyperparameter  ...  [26] proposed moving the face area of the ground truth to the closest location by adjusting the face candidate area through a CNN of the Cascade structure for accurate face detection.  ... 
doi:10.3390/app12115553 fatcat:yllauvmdqbealf6fodcrjvrppu

Nested Shallow CNN-Cascade for Face Detection in the Wild

Jingjing Deng, Xianghua Xie
2017 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)  
The face detection problem is considered as solving three sub-problems: eliminating easy background with a simple but fast model, then localising the face region with a soft-cascade, followed by precise  ...  In this paper, we propose a nested CNN-cascade learning algorithm that adopts shallow neural network architectures that allow efficient and progressive elimination of negative hypothesis from easy to hard  ...  However, for small objects, R-CNNs have difficulty to detect them in small scale due to low resolution and the lack of visual context.  ... 
doi:10.1109/fg.2017.29 dblp:conf/fgr/DengX17 fatcat:75sdoapswrazvgzxzprmvv2p2a

FaceBoxes: A CPU Real-time Face Detector with High Accuracy [article]

Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li
2018 arXiv   pre-print
for face detection tend to be computationally prohibitive.  ...  As a consequence, the proposed detector runs at 20 FPS on a single CPU core and 125 FPS using a GPU for VGA-resolution images. Moreover, the speed of FaceBoxes is invariant to the number of faces.  ...  , #61572536, #61672521 and AuthenMetric R&D Funds.  ... 
arXiv:1708.05234v4 fatcat:i2iivrsljnbjvgvgbkrxpyyqbi

Real-Time Pre-Identification and Cascaded Detection for Tiny Faces

Yang, Li, Min, Wang
2019 Applied Sciences  
In order to alleviate the problem in existing methods, we propose a pre-identification mechanism and a cascaded detector (PMCD) for tiny-face detection.  ...  The cascade detector is designed with two stages of deep convolutional neural network (CNN) to detect tiny faces in a coarse-to-fine manner, i.e., the face-area candidates are pre-identified as region  ...  Z.Y. and J.L. contributed equally to this paper, conceived the idea of work, implemented algorithms, analyzed the experiment data, and wrote the manuscript.  ... 
doi:10.3390/app9204344 fatcat:jqbx4zt7nbchpp2lxv4gfx3aom

A Lightweight Face Verification Based on Adaptive Cascade Network and Triplet Loss Function

Jianhong Lin, Zhaoyang Ye, Weinan Liu, Siqi Ren, Ye Wang, Wenrui Ma, Bin Xu, Yifan Ding, Liqin Shi
2022 Wireless Communications and Mobile Computing  
One of the most important and useful applications of artificial intelligence is face detection. The outbreak of COVID-19 has promoted the development of the noncontact identity authentication system.  ...  Using dynamic semihard triplet strategy for training, our network achieves a classification accuracy of 99.2% on the dataset of Labeled Faces in the Wild.  ...  Conclusions This paper proposes a framework based on adaptive cascade CNN network and triplet loss for face detection and verification with fast speed and high accuracy.  ... 
doi:10.1155/2022/3017149 fatcat:6ocf3jzvjfdp3jn4qnuifwgori
« Previous Showing results 1 — 15 out of 3,482 results