Integrated Deep Model for Face Detection and Landmark Localization From “In The Wild” Images

Storey, Gary, Bouridane, Ahmed and Jiang, Richard (2018) Integrated Deep Model for Face Detection and Landmark Localization From “In The Wild” Images. IEEE Access, 6. pp. 74442-74452. ISSN 2169-3536

08540344.pdf - Published Version

Download (2MB) | Preview
Text (Full text)
Storey et al - Integrated Deep Model for Face Detection and Landmark Localisation from 'in the wild' Images AAM.pdf - Accepted Version

Download (24MB) | Preview
Official URL:


The tasks of face detection and landmark localisation are a key foundation for many facial analysis applications, while great advancements have been achieved in recent years especially there are still challenges to increase the precision of face detection. Within this paper we presents our novel method the Integrated Deep Model fusing two state-of-the-art deep learning architectures namely Faster R-CNN and a stacked hourglass glass for improved face detection precision and accurate landmark localisation. Integration is achieved through the application of a novel optimisation function and is shown in experimental evaluation to increase accuracy of face detection specifically precision by reducing false positive detection’s considerably. Our proposed Integrated Deep Model method is evaluated on the Annotated Faces In-The- Wild, Annotated Facial Landmarks in the Wild and the Face Detection Dataset and Benchmark face detection test sets and show a high level of recall and precision when compared with previously proposed methods. Landmark localisation is evaluated on the Annotated Faces In-The-Wild and 300-W test sets, this specifically focuses on localisation accuracy from detected face bounding boxes when compared with baseline evaluations using ground truth bounding boxes, our findings highlight only a very small increase in error which is more profound for the subset of facial landmarks which border the face.

Item Type: Article
Uncontrolled Keywords: Computer vision, face detection, machine learning
Subjects: G400 Computer Science
G700 Artificial Intelligence
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 19 Oct 2018 08:50
Last Modified: 01 Aug 2021 12:02

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics