Shape and texture combined face recognition for detection of forged ID documents

Saez-Trigueros, Daniel; Hertlein, Heinz; Li, Meng; Hartnett, Margaret

doi:10.1109/mipro.2016.7522348

Cited by 5 publications

(5 citation statements)

References 26 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MFDA technique uses random subspace sampling [93] to construct multiple lower-dimensional feature subspaces, and bagging [94] to select subsets of training samples for LDA that contain inter-class pairs near the classification boundary to increase the discriminative ability of the representation. Dense SIFT descriptors were also used in [95] as texture features, and combined with shape features in the form of relative distances between pairs of facial landmarks. This combination of shape and texture features was further processed using multiple PCA+LDA transformations.…”

Section: Hybrid Methodsmentioning

confidence: 99%

Face Recognition: From Traditional to Deep Learning Methods

Trigueros,

Meng,

Hartnett

2018

Preprint

Self Cite

View full text Add to dashboard Cite

Starting in the seventies, face recognition has become one of the most researched topics in computer vision and biometrics. Traditional methods based on hand-crafted features and traditional machine learning techniques have recently been superseded by deep neural networks trained with very large datasets. In this paper we provide a comprehensive and upto-date literature review of popular face recognition methods including both traditional (geometry-based, holistic, featurebased and hybrid methods) and deep learning methods.

show abstract

Section: Hybrid Methodsmentioning

confidence: 99%

Face Recognition: From Traditional to Deep Learning Methods

Trigueros,

Meng,

Hartnett

2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Representative methods such as principal component analysis and support vector machines (SVM) also emerged during this period. The existing methods can be roughly divided into several factions: based on geometric features, based on correlation matching, based on subspace learning, based on statistical methods and based on neural network [2]. At present, the mainstream face recognition models are mainly trained based on deep learning methods.…”

Section: Figure 2 the Face Recognition Flow Chartmentioning

confidence: 99%

Adversarial attacks against face recognition: a study

Cheng

Liu

2023

Conference on Infrared, Millimeter, Terahertz Waves and Applications (IMT2022)

View full text Add to dashboard Cite

With the continuous development of artificial intelligence, face recognition is widely used in identity authentication, facial recognition payment, intelligent security and other fields. However, the existence of adversarial samples has great security risks to face recognition. In the face recognition system, the attacker can make the system mistake the identity by adding tiny changes to the face image, thus causing a series of security threats such as system intrusion, illegal access to authority, stolen property, and evasion of legal responsibility. In this paper, we first introduce the basic concept of adversarial attacks, and briefly analyze the typical adversarial sample generation methods in recent years. Then, the adversarial attack security problem of face recognition is discussed. Finally, the research status of face recognition adversarial attacks is analyzed.

show abstract

“…With a variety of facial traits, traditional approaches frequently struggle (Trigueros et al, 2018), with findings that are erroneous due to lighting and image variations (Xin & Wang, 2019). By focusing on image histograms as a complementary feature alongside CNN-based models, it will aim to mitigate these challenges and improve the overall performance of gender classification systems.…”

Section: Introductionmentioning

confidence: 99%

Investigating Image Histograms using CNN and Tensor Flow-Based Gender Classification

Tiani Ayu Lestari,

Muhamad Fatchan,

Wahyu Hadikristanto

2024

IJSAS

View full text Add to dashboard Cite

This study investigates the integration of image histograms with Convolutional Neural Networks (CNNs) using TensorFlow for gender classification. The research focuses on preprocessing techniques that significantly reduce the dimensionality of image data, enhancing computational efficiency model performance. Data augmentation methods, including rotation, shifting, and flipping, were applied to diversify the training dataset. The CNN model achieved high accuracy and validation accuracy, demonstrating its robustness. The findings reveal that the preprocessing steps effectively condensed the pixel to be 151,321 while retaining critical features for classification. The study underscores the potential applications of this methodology in security, marketing, and healthcare, where accurate gender classification is essential. Future research should explore more diverse datasets, advanced model architectures, and enhanced feature extraction methods to further improve performance. This research contributes to the field by offering a comprehensive approach to efficient and accurate gender classification, supported by robust data augmentation and preprocessing techniques.

show abstract

Shape and texture combined face recognition for detection of forged ID documents

Cited by 5 publications

References 26 publications

Face Recognition: From Traditional to Deep Learning Methods

Face Recognition: From Traditional to Deep Learning Methods

Adversarial attacks against face recognition: a study

Investigating Image Histograms using CNN and Tensor Flow-Based Gender Classification

Contact Info

Product

Resources

About