Face Alignment by Local Deep Descriptor Regression
This addresses face alignment for computer vision applications, offering a potential replacement for traditional descriptors like SIFT and HOG, but it is incremental as it builds on existing deep CNN methods.
The paper tackles face alignment by proposing Local Deep Descriptor Regression (LDDR), which uses deep convolutional neural networks to compute local descriptors for key-points, achieving high accuracy on unconstrained datasets with varying sizes, poses, and occlusions.
We present an algorithm for extracting key-point descriptors using deep convolutional neural networks (CNN). Unlike many existing deep CNNs, our model computes local features around a given point in an image. We also present a face alignment algorithm based on regression using these local descriptors. The proposed method called Local Deep Descriptor Regression (LDDR) is able to localize face landmarks of varying sizes, poses and occlusions with high accuracy. Deep Descriptors presented in this paper are able to uniquely and efficiently describe every pixel in the image and therefore can potentially replace traditional descriptors such as SIFT and HOG. Extensive evaluations on five publicly available unconstrained face alignment datasets show that our deep descriptor network is able to capture strong local features around a given landmark and performs significantly better than many competitive and state-of-the-art face alignment algorithms.