Open Access
FDDB: A benchmark for face detection in unconstrained settings
Vidit Jain,Erik Learned-Miller +1 more
Reads0
Chats0
TLDR
A new data set of face images with more faces and more accurate annotations for face regions than in previous data sets is presented and two rigorous and precise methods for evaluating the performance of face detection algorithms are proposed.Abstract:
Despite the maturity of face detection research, it remains difficult to compare different algorithms for face detection. This is partly due to the lack of common evaluation schemes. Also, existing data sets for evaluating face detection algorithms do not capture some aspects of face appearances that are manifested in real-world scenarios. In this work, we address both of these issues. We present a new data set of face images with more faces and more accurate annotations for face regions than in previous data sets. We also propose two rigorous and precise methods for evaluating the performance of face detection algorithms. We report results of several standard algorithms on the new benchmark.read more
Citations
More filters
Journal ArticleDOI
Convolutional herbal prescription building method from multi-scale facial features
TL;DR: In this paper, a multi-scale convolutional neural network based on three-grained face was proposed to mine features from different granularities of faces, which mined the patient's face information from the organs, local regions, and the entire face.
Dissertation
Efficient object detection via structured learning and local classifiers
TL;DR: This thesis presents an automatic efficient object detection framework to detect object instances in images using bounding boxes, which can be trained and tested easily on current personal computers and can perform reasonably well with acceptable detection accuracy and good computational efficiency.
Proceedings Article
Unsupervised Learning of Object Landmarks via Self-Training Correspondence
TL;DR: The approach can learn landmarks that are more flexible in terms of capturing large changes in viewpoint and shows the favourable properties of the method on a variety of difficult datasets including LS3D, BBCPose and Human3.6M.
Book ChapterDOI
Continuous Trade-off Optimization Between Fast and Accurate Deep Face Detectors
Petru Soviany,Radu Tudor Ionescu +1 more
TL;DR: In this article, five straightforward approaches to achieve an optimal trade-off between accuracy and speed in face detection were proposed, based on separating the test images in two batches, an easy batch that was fed to a faster face detector and a difficult batch that is fed to an accurate yet slower detector.
Proceedings ArticleDOI
VikingDet: A Real-time Person and Face Detector for Surveillance Cameras
TL;DR: A novel one-stage detector that can simultaneously detect both pedestrians and their faces, named as VikingDet, which achieves satisfactory performances in several relative benchmarks with a speed at more than 60 FPS on NVIDIA TITAN X GPU, and can be further deployed on an embedded device with a real-time speed of over 28 FPS.
References
More filters
Journal ArticleDOI
Robust Real-Time Face Detection
Paul A. Viola,Michael Jones +1 more
TL;DR: In this paper, a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates is described. But the detection performance is limited to 15 frames per second.
Journal ArticleDOI
The Hungarian method for the assignment problem
TL;DR: This paper has always been one of my favorite children, combining as it does elements of the duality of linear programming and combinatorial tools from graph theory, and it may be of some interest to tell the story of its origin this article.
Proceedings Article
On Spectral Clustering: Analysis and an algorithm
TL;DR: A simple spectral clustering algorithm that can be implemented using a few lines of Matlab is presented, and tools from matrix perturbation theory are used to analyze the algorithm, and give conditions under which it can be expected to do well.
Journal ArticleDOI
Neural network-based face detection
TL;DR: A neural network-based upright frontal face detection system that arbitrates between multiple networks to improve performance over a single network, and a straightforward procedure for aligning positive face examples for training.
Journal ArticleDOI
Detecting faces in images: a survey
TL;DR: In this article, the authors categorize and evaluate face detection algorithms and discuss relevant issues such as data collection, evaluation metrics and benchmarking, and conclude with several promising directions for future research.