Deep 3D-LBP: CNN-based fusion of shape modeling and texture descriptors for accurate face recognition

Bahroun, Sahbi; Abed, Rahma; Zagrouba, Ezzeddine

doi:10.1007/s00371-021-02324-x

Cited by 12 publications

(6 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature extraction algorithms for facial recognition systems focus on permanent facial features such as eyebrows, eyes, nose, mouth, skin color and face texture shape. Some of these most representative descriptors are LBP for color and texture face images [9,10] and Mesh LBP [11,12,13,14] for face texture and shape. In the second phase, a deep classifier is used to differentiate among several individuals.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Combining Color Texture and Shape Features In a Multi-Input Convolutional Neural Network for Efficient Face Recognition In Unconstrained Environments

Bahroun

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Developing an effective feature representation for face recognition in an un-constrained environment is still a challenging research field. However, in that environment, face images suffer from several issues that could affect the achieved results such as facial expression, occlusion, low resolution, noise, illumination and pose variation. In this paper, an end-to-end multi-input deep convolu-tional neural network architecture was designed for face recognition. The newly designed CNN structure can take full advantage of multi-modal 2D/3D features extracted from face such as: 3DMM-Mesh LBP image, LBPC image, and the face image itself. Through experiments conducted on the LFW, YTF, Multi-PIE, and Bosphorus databases, the obtained results showed a significant improvement compared to traditional state-of-the-art methods which demonstrated the strength of introducing a multi-input convolutional neural network for face recognition in uncontrolled environments.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The newly designed 1D-CNN structure took advantage of multi-modal physiological signals and automatically complete the process from feature extraction to emotion classification simultaneously. Bahroun et.al [13] propose a Deep 3D-LBP network.…”

Section: Related Workmentioning

confidence: 99%

Combining Color Texture and Shape Features In a Multi-Input Convolutional Neural Network for Efficient Face Recognition In Unconstrained Environments

Bahroun

2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Bahroun et al 26 demonstrated a local binary pattern-based approach to 3D facial recognition (3D-LBP). The CNN is used in the deep learning approach used in the proposed method to provide an accurate face recognition process for various fields.…”

Section: Related Workmentioning

confidence: 99%

“…Bahroun et al 26 . demonstrated a local binary pattern-based approach to 3D facial recognition (3D-LBP).…”

Section: Related Workmentioning

confidence: 99%

Framework for facial recognition and reconstruction for enhanced security and surveillance monitoring using 3D computer vision

Wang

Zhang

2023

J. Electron. Imag.

View full text Add to dashboard Cite

Workflows can be optimized with the use of three-dimensional (3D) computer vision (CV) by monitoring processes from many angles. The potential for increased efficiency and cost savings is clear here. Input scenarios are always being monitored by security and surveillance systems to recognize and classify items, human faces, and moving things. The input reconstruction in these surveillance systems is problematic because of the mapping from three dimensions to two dimensions in the form of pixels. We present a new 3D CV paradigm-based framework for facial recognition and reconstruction. In this setup, deep neural networks are used to distinguish between mapped and unmapped pixels during a 2D to 3D or 3D to 2D transformation. To use correlation analysis to recognize human faces, it is necessary to first examine the input image for textural properties. The mapping procedure continues with the extraction of textural elements using dimensional contours. Then, continuous contours are used to do the 3D mapping and reduce the number of false positives. Instead, this framework isolates individual contours of moving objects or faces to increase the number of training iterations. Finally, missing pixels in the dimension conversion are filled to rebuild the human face utilizing discrete and continuous outlines. Hence, the suggested framework minimizes the false rate (10%), increases the false positive rate as (13.93%), and minimizes the error by (9.89%) while maximizing the recognition accuracy for (13.93%) and the precision is (13.21%).

show abstract

“…As a fundamental topic in computer vision and graphics, 3D face reconstruction can be used for face recognition [1][2][3][4], face alignment [5][6][7][8], emotion analysis [9], and face animation [10]. Over the years, many novel approaches to 3D face reconstruction from a single image have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Fast 3D face reconstruction from a single image combining attention mechanism and graph convolutional network

et al. 2022

View full text Add to dashboard Cite

In recent years, researchers have made significant contributions to 3D face reconstruction with the rapid development of deep learning. However, learning-based methods often suffer from time and memory consumption. Simply removing network layers hardly solves the problem. In this study, we propose a solution that achieves fast and robust 3D face reconstruction from a single image without the need for accurate 3D data for training. In terms of increasing speed, we use a lightweight network as a facial feature extractor. As a result, our method reduces the reliance on graphics processing units, allowing fast inference on central processing units alone. To maintain robustness, we combine an attention mechanism and a graph convolutional network in parameter regression to concentrate on facial details. We experiment with different combinations of three loss functions to obtain the best results. In comparative experiments, we evaluate the performance of the proposed method and state-of-the-art methods on 3D face reconstruction and sparse face alignment, respectively. Experiments on a variety of datasets validate the effectiveness of our method.

show abstract

Deep 3D-LBP: CNN-based fusion of shape modeling and texture descriptors for accurate face recognition

Cited by 12 publications

References 97 publications

Combining Color Texture and Shape Features In a Multi-Input Convolutional Neural Network for Efficient Face Recognition In Unconstrained Environments

Combining Color Texture and Shape Features In a Multi-Input Convolutional Neural Network for Efficient Face Recognition In Unconstrained Environments

Framework for facial recognition and reconstruction for enhanced security and surveillance monitoring using 3D computer vision

Fast 3D face reconstruction from a single image combining attention mechanism and graph convolutional network

Contact Info

Product

Resources

About