Empirical analysis of cascade deformable models for multi-view face detection

Orozco, Javier; Martínez, Brais; Pantić, Maja

doi:10.1016/j.imavis.2015.07.002

Cited by 28 publications

(24 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We acquired the groundtruth annotations of 68 points from the 300 Faces In-The-Wild Challenge [20,21]. The fitting process is initialized by computing the face's bounding box using the Cascade Deformable Part Models face detector [22] and then estimating the appropriate global similarity transform that fits the mean shape within the bounding box bounds. Note that this initial similarity transform only involves a translation and scaling component and not any in-plane rotation.…”

Section: Resultsmentioning

confidence: 99%

HOG active appearance models

Antonakos

Alabort-i-Medina

Tzimiropoulos

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

We propose the combination of dense Histogram of Oriented Gradients (HOG) features with Active Appearance Models (AAMs). We employ the efficient Inverse Compositional optimization technique and show results for the task of face fitting. By taking advantage of the descriptive characteristics of HOG features, we build robust and accurate AAMs that generalize well to unseen faces with illumination, identity, pose and occlusion variations. Our experiments on challenging in-the-wild databases show that HOG AAMs significantly outperfrom current state-of-the-art results of discriminative methods trained on larger databases.

show abstract

Section: Resultsmentioning

confidence: 99%

HOG active appearance models

Antonakos

Alabort-i-Medina

Tzimiropoulos

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Besides, the annotations that are needed to train such a detector can be acquired very quickly, since only a bounding box containing the image's face is required. Other detectors that can be used are efficient subwindow search [26] and deformable part-based models [27,28,24]. The statistical shape model of facial landmark points can be built easily using a small number of facial shapes.…”

Section: Introductionmentioning

confidence: 99%

Joint Unsupervised Face Alignment and Behaviour Analysis

Zafeiriou

Antonakos

Zafeiriou

et al. 2014

Computer Vision – ECCV 2014

Self Cite

View full text Add to dashboard Cite

Abstract. The predominant strategy for facial expressions analysis and temporal analysis of facial events is the following: a generic facial landmarks tracker, usually trained on thousands of carefully annotated examples, is applied to track the landmark points, and then analysis is performed using mostly the shape and more rarely the facial texture. This paper challenges the above framework by showing that it is feasible to perform joint landmarks localization (i.e. spatial alignment) and temporal analysis of behavioural sequence with the use of a simple face detector and a simple shape model. To do so, we propose a new component analysis technique, which we call Autoregressive Component Analysis (ARCA), and we show how the parameters of a motion model can be jointly retrieved. The method does not require the use of any sophisticated landmark tracking methodology and simply employs pixel intensities for the texture representation.

show abstract

“…proposed by Falzenswalb et al [6] can be considered the baseline framework for many of the recent face detectors using discriminatively trained maximum margin classifiers [7], [8], [9].…”

Section: Categorization Of Existing Face Detectorsmentioning

confidence: 99%

“…Zhu et al [7] However in [8], Orozco et al argued that these models presented in [7] were aimed to landmark localization and pose estimation but they are suboptimal when only face detection is required because it requires full landmark labelling which reduces the amount of data that can be used in training and it is slow for practical face detection applications.…”

Section: Part Based Face Detectorsmentioning

confidence: 99%

“…where is the model parameters defined as: 8) and is the concatenated feature vector that represents each training sample by combining the appearance and deformation features extracted from it which can be defined as: The target of the training process is to obtain the optimum value of the vector that would lead to a scoring function capable of discriminating between the positive and the negative training samples with a maximum margin. This problem is solved using the support vector machines that was explained in details in Chapter 2.…”

Section: Automatic Part Annotationmentioning

confidence: 99%

See 1 more Smart Citation

Mathematical modeling for partial object detection.

El-Barkouky¹

View full text Add to dashboard Cite

From a computer vision point of view, the image is a scene consisting of objects of interest and a background represented by everything else in the image. The relations and interactions among these objects are the key factors for scene understanding. In this dissertation, a mathematical model is designed for the detection of partially occluded faces captured in unconstrained real life conditions. The proposed model novelty comes from explicitly considering certain objects that are common to occlude faces and embedding them in the face model. This enables the detection of faces in difficult settings and provides more information to subsequent analysis in addition to the bounding box of the face.In the proposed Selective Part Models (SPM), the face is modelled as a collection of parts that can be selected from the visible regular facial parts and some of the occluding objects which commonly interact with faces such as sunglasses, caps, hands, shoulders, and other faces. With the face detection being the first step in the face recognition pipeline, the proposed model does not only detect partially occluded faces efficiently but it also suggests the occluded parts to be excluded from the subsequent recognition step. The model was tested on several recent face detection databases and benchmarks and achieved state of the art performance. In addition, detailed analysis for the performance with respect vi to different types of occlusion were provided. Moreover, a new database was collected for evaluating face detectors focusing on the partial occlusion problem.This dissertation highlights the importance of explicitly handling the partial occlusion problem in face detection and shows its efficiency in enhancing both the face detection performance and the subsequent recognition performance of partially occluded faces. The broader impact of the proposed detector exceeds the common security applications by using it for human robot interaction. The humanoid robot Nao is used to help in teaching children with autism and the proposed detector is used to achieve natural interaction between the robot and the children by detecting their faces which can be used for recognition or more interestingly for adaptive interaction by analyzing their expressions. vii

show abstract

Empirical analysis of cascade deformable models for multi-view face detection

Cited by 28 publications

References 17 publications

HOG active appearance models

HOG active appearance models

Joint Unsupervised Face Alignment and Behaviour Analysis

Mathematical modeling for partial object detection.

Contact Info

Product

Resources

About