Approaching human level facial landmark localization by deep learning

Fan, Haoqiang; Zhou, Erjin

doi:10.1016/j.imavis.2015.11.004

Cited by 108 publications

(64 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, to wit, the performance of the work in [26] is not due to the suitability of the proposed model to the task of facial landmark detection so much as it is due to complex engineering of the used algorithm which could also be used in our formulation, but this falls beyond the scope of this paper. On the other hand, the work in [27] outperforms our method in the case of very small errors. However, the opposite is the case for any error larger than 0.02.…”

Section: F Comparison With the State-of-the-artmentioning

confidence: 83%

See 1 more Smart Citation

Fast and Exact Newton and Bidirectional Fitting of Active Appearance Models

Kossaifi

Tzimiropoulos

Pantić

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Active Appearance Models (AAMs) are generative models of shape and appearance that have proven very attractive for their ability to handle wide changes in illumination, pose and occlusion when trained in the wild, while not requiring large training dataset like regression-based or deep learning methods. The problem of fitting an AAM is usually formulated as a non-linear least squares one and the main way of solving it is a standard Gauss-Newton algorithm. In this paper we extend Active Appearance Models in two ways: we first extend the Gauss-Newton framework by formulating a bidirectional fitting method that deforms both the image and the template to fit a new instance. We then formulate a second order method by deriving an efficient Newton method for AAMs fitting. We derive both methods in a unified framework for two types of Active Appearance Models, holistic and part-based, and additionally show how to exploit the structure in the problem to derive fast yet exact solutions. We perform a thorough evaluation of all algorithms on three challenging and recently annotated inthe-wild datasets, and investigate fitting accuracy, convergence properties and the influence of noise in the initialisation. We compare our proposed methods to other algorithms and show that they yield state-of-the-art results, out-performing other methods while having superior convergence properties.Index Terms-Active Appearance Models, Newton method, bidirectional image alignment, inverse compositional, forward additive.

show abstract

Section: F Comparison With the State-of-the-artmentioning

confidence: 83%

“…However, the opposite is the case for any error larger than 0.02. This is to be expected as the work in [27] is a submission from industry (Megvii company) using cascaded Deep Convolutional Neural Networks trained on undisclosed Fig. 10.…”

Section: F Comparison With the State-of-the-artmentioning

confidence: 90%

Fast and Exact Newton and Bidirectional Fitting of Active Appearance Models

Kossaifi

Tzimiropoulos

Pantić

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Robustness is a major requirement for facial algorithms to produce the correct output. Even if a landmark point is not visible, it is typical for a facial landmark detection algorithms to guess a position for the point [1]. This is important if we want to detect the rotation of the face.…”

Section: Some Advantages Of Anns Includementioning

confidence: 99%

“…There has been a significant body of prior work exploring deep learning approaches for face detection [15] using SVMs [24,25], Regression Trees [26], and Deep Convolutional Neural Networks (CNNs) [1,2,10,15], to mention a few. Given the large visual variations of faces, including occlusions, large pose variations and extreme lighting conditions, accurate face recognition includes a number of challenges [10].…”

Section: Related Workmentioning

confidence: 99%