Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks

Zhang, Kaipeng; Zhang, Zhanpeng; Li, Zhifeng; Qiao, Yu

doi:10.1109/lsp.2016.2603342

Cited by 4,865 publications

(2,522 citation statements)

References 26 publications

Supporting

Mentioning

2,274

Contrasting

Unclassified

Order By: Relevance

“…We also conduct face detection experiments using two recently published algorithms [7,8]. The method in [7] is based on a Multi-task Cascaded Convolutional Network (MTCNN) with three stages of deep convolutional networks (CNN) which predict face and landmark location in a coarseto-fine manner.…”

Section: Baseline Face Detection Methodsmentioning

confidence: 99%

“…quick rejection of background regions) has been applied to features learned by Convolutional Neural Networks (CNN) [18], and the amount of research works on face detection making use of CNNs is exploding, e.g. [7,19,20,21], inspired by the remarkable recent success of CNNs in many computer vision tasks. A drawback of these approaches, and of many approaches for unconstrained face detection, is that they usually need a considerable amount of annotated training data, apart from being computationally expensive [7].…”

Section: Face Detectionmentioning

confidence: 99%

“…[7,19,20,21], inspired by the remarkable recent success of CNNs in many computer vision tasks. A drawback of these approaches, and of many approaches for unconstrained face detection, is that they usually need a considerable amount of annotated training data, apart from being computationally expensive [7]. Unconstrained face detection has gained attention recently also due to benchmarks for the development of unconstrained face detection algorithms, such as the Face Detection Data Set and Benchmark (FDDB) [22], or the Annotated Facial Landmarks in the Wild (AFLW) [23].…”

Section: Face Detectionmentioning

confidence: 99%

“…The developed method utilizes a modified version of the well-known Viola-Jones algorithm for face detection, which is complemented with the addition of tracking capabilities via optical flow computation. We also include two recently published algorithms based on Multi-task Cascaded Convolutional Networks [7] and Deformable Part Models [8,9] to our comparison framework.…”

Section: Contributionsmentioning

confidence: 99%

See 3 more Smart Citations

Real‐time AdaBoost cascade face tracker based on likelihood map and optical flow

et al. 2017

View full text Add to dashboard Cite

The authors present a novel face tracking approach where optical flow information is incorporated into a modified version of the Viola-Jones detection algorithm. In the original algorithm, detection is static, as information from previous frames is not considered; in addition, candidate windows have to pass all stages of the classification cascade, otherwise they are discarded as containing no face. In contrast, the proposed tracker preserves information about the number of classification stages passed by each window. Such information is used to build a likelihood map, which represents the probability of having a face located at that position. Tracking capabilities are provided by extrapolating the position of the likelihood map to the next frame by optical flow computation. The proposed algorithm works in real time on a standard laptop. The system is verified on the Boston Head Tracking Database, showing that the proposed algorithm outperforms the standard Viola-Jones detector in terms of detection rate and stability of the output bounding box, as well as including the capability to deal with occlusions. The authors also evaluate two recently published face detectors based on convolutional networks and deformable part models with their algorithm showing a comparable accuracy at a fraction of the computation time.

show abstract

Section: Baseline Face Detection Methodsmentioning

confidence: 99%

Section: Face Detectionmentioning

confidence: 99%

Section: Face Detectionmentioning

confidence: 99%

Section: Contributionsmentioning

confidence: 99%

See 2 more Smart Citations

Real‐time AdaBoost cascade face tracker based on likelihood map and optical flow

et al. 2017

View full text Add to dashboard Cite

show abstract

“…One is the PolyU NIR-face database for fine-tuning the VGG model to obtain FRM, and it consists of 335 samples imaged under near-infrared condition. Before feeding the face images into DCNN, a robust joint face detection and alignment model [10] based on multitask cascaded CNNs is adopted for region of interest (ROI) cropping followed by normalizing the ROI as 224*224. Another one is the lab-made hand-dorsa vein database containing 98 females and 102 males whose ages vary from 19 to 62.…”

Section: Datasets and Experimental Setupmentioning

confidence: 99%