DLBP: A novel descriptor for depth image based face recognition

Abstract

International audienceAbstract:This paper presents a novel descriptor for face depth images, generalizing the well-known Local Binary Pattern (LBP), in order to enhance its discriminative power for smooth depth images. The proposed descriptor is based on detecting shape patterns from face surfaces and enables accurate and fast description of shape variation in depth images. It is in the same form as conventional LBP, so patterns can be readily combined to form joint histograms to represent depth faces. The descriptor is computationally very simple, rapid and it is totally training-free. When we associate our descriptor in a face recognition scheme based on nearest neighbor classifier, it shows its discriminative power in depth based face recognition comparing to the conventional LBP and other extensions proposed for 3D face recognition. Many experiments are conducted on different databases in order to evaluate our method

Introducing FoxFaces: A 3-in-1 Head Dataset

“…The bimodal framework considered here is strongly inspired by LBP applied on both depth and color channels. A variation of LBP characterizing depth images (called DLBP) was proposed in (Aissaoui et al, 2014). We use this descriptor for constructing a depth-related feature vector.…”

“…Depth images presenting lot of missing data are dropped at this stage. Denoising of depth images is also performed as described in (Aissaoui et al, 2014). We notice that head pose variation is not considered in these experiments.…”

“…In order to quantify the challenges brought by the new dataset, we compare in Fig 4, the face recognition rates obtained by applying some descriptors (LBP, DLBP and 3DLBP (Huang et al, 2006)) on 3D data from our dataset to those obtained on other wellknown 3D datasets (FRGC, TEXAS and Bosphorus) (Aissaoui et al, 2014). Descriptor's parameters given the best rates are chosen.…”

Intelligent Hotel Guidance System via Face Recognition Technology

“…The LBP operator makes use of the relationship between the center point and the surrounding point to quantify it, which can more effectively eliminate the influence of light. The LBP operator can also be combined with Principal Component Analysis, Support Vector Machine and Deep Learning for recognition, which can further improve the recognition efficiency and effectiveness [30][31][32][33]. The path performance between network terminals and the central node is very important.…”

Robust Face Recognition with Deeply Normalized Depth Images

“…Methods in the second category directly work on depth images, and focus on devising effective feature descriptors and classifiers. A variety of hand-crafted descriptors have been introduced for depth-image-based face recognition, such as local binary patterns [11], local quantized patterns [12], and bag of dense derivative depth patterns [13]. After feature descriptors are extracted from depth images, different classifiers like support vector machines [14] and nearest neighbor classifiers [15] are applied to recognize the faces in the depth images.…”