Multi-view Face Detection Using Deep Convolutional Neural Networks

By Sachin Sudhakar Farfade, Mohammad Javad Saberian, Li-Jia Li. International Conference on Multimedia Retrieval, 2015

593 citations recorded by the source corpus.

In this paper we consider the problem of multi-view face detection. While there has been significant research on this problem, current state-of-the-art approaches for this task require annotation of facial landmarks, e.g. TSM [25], or annotation of face poses [28, 22]. They also require training dozens of models to fully capture faces in all orientations, e.g. 22 models in HeadHunter method [22]. In this paper we propose Deep Dense Face Detector (DDFD), a method that does not require pose/landmark annotation and is able to detect faces in a wide range of orientations using a single model based on deep convolutional neural networks. The proposed method has minimal complexity; unlike other recent deep learning object detection methods [9], it does not require additional components such as segmentation, bounding-box regression, or SVM classifiers. Furthermore, we analyzed scores of the proposed face detector for faces in different orientations and found that 1) the proposed method is able to detect faces from different angles and can handle occlusion to some extent, 2) there seems to be a correlation between distribution of positive examples in the training set and scores of the proposed face detector. The latter suggests that the proposed method's performance can be further improved by using better sampling strategies and more sophisticated data augmentation techniques. Evaluations on popular face detection benchmark datasets show that our single-model face detector algorithm has similar or better performance compared to the previous methods, which are more complex and require annotations of either different poses or facial landmarks.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/174930cac7174257515a189cd3ecfdd80ee7dd54

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition (2019, methodology): “5 [39], CascadeCNN [33], Structured Models [58], DDFD [12], NPDFace [36], PEP-Adapt [32], TSM [70], as well as three commercial systems Face++, Picasa and Face.”
DenseBox: Unifying Landmark Localization with End to End Object Detection (2015, methodology): “It is pointed out by [10] that R-CNN with general proposal methods designed for general object detection could results in inferior performance in detection task such as face detection, due to loss recall for small-sized faces and faces in complex appearance variations.”
Detecting Masked Faces in the Wild with LLE-CNNs (2017, methodology): “Different from the boostingbased and DPM-based approaches, CNN-based face detectors directly learn face representations from data [34, 5] and adopt deep learning paradigm [9, 8, 26] to detect the presence of a face in a scanning window.”
Face detection techniques: a review (2018, unknown): “Farfadeetal.”
Object Detection With Deep Learning: A Review (2018, methodology): “The evaluated models cover DDFD [168], Cascade-CNN [180], aggregate channel features (ACF)-multiscale [181], Pico [182], Head-Hunter [183], Joint Cascade [31], SURF-multiview [184], Viola–Jones [166], NPDFace [185], Faceness [169], convolutional channel features (CCF) [186], MTCNN [176], Conv3-D [17”
From Facial Parts Responses to Face Detection: A Deep Learning Approach (2015, methodology): “A recent study [6] shows that face detection can be further improved by using deep learning, leveraging the high capacity of deep convolutional networks.”
Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound (2016, background): “Several authors [1], [23], [24] have reported that these features (sometimes also called descriptors) can be used for tasks such as image retrieval by mapping images to the feature space and identifying their neighbours.”
Deep multi-view learning methods: A review (2021, background): “Facial Detection and Recognition Facial detection from multi-view source data is a valuable research topic and challenging task since the there exists large viewpoint changes in poses and illumination [170, 171, 173, 174, 176, 177].”
FlexFlow: A Flexible Dataflow Accelerator Architecture for Convolutional Neural Networks (2017, background): “Recent years, more and more applications based on CNN models are spotlighted, such as handwriting recognition [18], face detection [9], [12], video surveillance [27], nature language analysis [10], [11], [24], and intelligent transportation [14], [28], [30].”
Machine learning strategies for systems with invariance properties (2016, unknown): “such as deep convolutional neural networks [34] or weight-sharing neural networks [35] for image recognition systems with”
Using Deep Learning to Challenge Safety Standard for Highly Autonomous Machines in Agriculture (2016, methodology): “Deep learning is utilized for barrel detection using a sliding window approach similar to [6].”
Convolutional Channel Features (2015, methodology): “What should be noted is that CCF considerably outperforms another CNN based method DDFD [19] which fine-tunes the CNN model to face detection, showing the effectiveness of boosting forest as a way to ap-”
Scale-Aware Face Detection (2017, methodology): “[8] shows that simple ﬁne-tuning the CNN model from ImageNet classiﬁcation task for face/background clas-siﬁcation leads to good performance.”
Multi-focus image fusion with a deep convolutional neural network (2017, methodology): “Another approach is to input the source images into the network as a whole without dividing them into patches, as was applied in [39,43,45] , aiming to directly generate a dense prediction map.”
Face Detection with the Faster R-CNN (2016, background): “[7] propose a fully convolutional neural network to detect faces at different resolutions.”
A survey of the recent architectures of deep convolutional neural networks (2019, background): “(2015) proposed deep CNN for detecting faces from different poses as well as from occluded faces (Farfade et al. 2015).”
WIDER FACE: A Face Detection Benchmark (2015, unknown): “Modern face detection algorithms can be categorized into four categories: cascade based methods [2, 10, 15, 16, 21], part based methods [19, 23, 30], channel feature based methods [25, 24], and neural network based methods [6, 14, 25, 28].”