Local Directional Number Pattern for Face Analysis: Face and Expression Recognition

By Adín Ramírez Rivera, Jorge A. Rojas Castillo, Oksam Chae. IEEE Transactions on Image Processing, 2013

517 citations recorded by the source corpus.

This paper proposes a novel local feature descriptor, local directional number pattern (LDN), for face analysis, i.e., face and expression recognition. LDN encodes the directional information of the face's textures (i.e., the texture's structure) in a compact way, producing a more discriminative code than current methods. We compute the structure of each micro-pattern with the aid of a compass mask that extracts directional information, and we encode such information using the prominent direction indices (directional numbers) and sign-which allows us to distinguish among similar structural patterns that have different intensity transitions. We divide the face into several regions, and extract the distribution of the LDN features from them. Then, we concatenate these features into a feature vector, and we use it as a face descriptor. We perform several experiments in which our descriptor performs consistently under illumination, noise, expression, and time lapse variations. Moreover, we test our descriptor with different masks to analyze its performance in different face analysis tasks.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/783ec77b0004eaf88810a97e389b766cf1ca01c3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Thiago Oliveira-Santos
2. A. D. Souza
3. Edilson de Aguiar
4. Andre Teixeira Lopes
5. Sze‐Teng Liong

Citations in the corpus

• OFF-ApexNet on Micro-expression Recognition System (2018, background): “To date, plenty of the recognition systems developed achieved more than 95% of expression classification accuracy [3, 4] and some of them even reached almost 100% perfect recognition performance [5–7].”
• COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios (2020, unknown): “More details about this descriptor can be find in [46].”
• Facial expression recognition with Convolutional Neural Networks: Coping with few data and the training sample order (2017, methodology): “recent methods [16, 7, 44, 43, 67, 8], in our experiments the contempt expression images were not used.”