Heterogeneous Face Recognition Using Domain Specific Units

Pereira, Tiago de Freitas; Anjos, André; Marcel, Sébastien

doi:10.1109/tifs.2018.2885284

Cited by 59 publications

(49 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main idea used from [50] is the adaptation of lower layers of CNN, instead of adapting the whole network when limited amount of target data is available. The network in [50] only has one forward path, whereas in MC-CNN the network architecture itself is extended to accommodate multi-channel data. The main advantage of the proposed framework is the adaptation of a minimal amount of network weights when the training data is limited, which is usually the case with available PAD datasets.…”

Section: B Network Architecturementioning

confidence: 99%

Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network

George

Mostaani

Geissenbuhler

et al. 2020

IEEE Trans.Inform.Forensic Secur.

Self Cite

188

186

View full text Add to dashboard Cite

Face recognition is a mainstream biometric authentication method. However, vulnerability to presentation attacks (a.k.a spoofing) limits its usability in unsupervised applications. Even though there are many methods available for tackling presentation attacks (PA), most of them fail to detect sophisticated attacks such as silicone masks. As the quality of presentation attack instruments improves over time, achieving reliable PA detection with visual spectra alone remains very challenging. We argue that analysis in multiple channels might help to address this issue. In this context, we propose a multi-channel Convolutional Neural Network based approach for presentation attack detection (PAD). We also introduce the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks. Data from different channels such as color, depth, near-infrared and thermal are available to advance the research in face PAD. The proposed method was compared with feature-based approaches and found to outperform the baselines achieving an ACER of 0.3% on the introduced dataset. The database and the software to reproduce the results are made available publicly.

show abstract

Section: B Network Architecturementioning

confidence: 99%

Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network

George

Mostaani

Geissenbuhler

et al. 2020

IEEE Trans.Inform.Forensic Secur.

Self Cite

188

186

View full text Add to dashboard Cite

show abstract

“…Each block consists of two values (colors), which are the average and standard deviation of the RGB colors, respectively. The calculation method of the average value as shown in (1). After calculating the average value of each of the red, green, and blue in the square, a new color is formed.…”

Section: Image Preprocessing and Feature Extractionmentioning

confidence: 99%

“…It requires a more advanced image processing engine to enhance processing performance. T. de Freitas Pereira et al [1] suggested that the high-level features are potentially domain independent in visual spectra images of Deep Convolutional Neural Networks trained. The shallow CNN stacked with LSTM and deep CNN were applied in a proposed method that is by G. Batchuluun et al [6].…”

Section: Introductionmentioning

confidence: 99%

A Novel Facial Thermal Feature Extraction Method for Non-Contact Healthcare System

et al. 2020

View full text Add to dashboard Cite

The non-contact healthcare system is a system that can avoid germ infection, and can also provide comfortable and convenient health care services for the caregivers. In the current thermal imaging research, local or small area images are used to represent the overall temperature information of the participants, but the temperature feature of the face should not only be used in a small part and ignore other parts. The facial thermal image can show clear temperature feature but is not conducive to meaningful feature extraction. Therefore, this research proposed a novel facial thermal image feature extraction method, which is used facial landmarks to detect and cut 12 blocks to establish a new feature matrix based on color mean values and standard deviation values. It can establish clear features on facial thermal images. The core part of the proposed healthcare system is the use of a deep learning framework, which is based on CAFFE under the DIGITS platform. The CAFFE runs the classic CNN, GoogLeNet. Based on the acquired images and new feature types, four models were trained, which were used for the raw RGB image, raw thermal image, RGB feature image, and thermal feature image. In the experiment, 800 images were used for training and validation, and 200 images were used for testing. An additional 40 images were used for random testing. The experimental results show that RGB images cannot be effectively used, thermal images can effectively predict the health status, and thermal feature images have the highest prediction accuracy. INDEX TERMS Non-contact healthcare system, thermal feature extraction, deep learning, GoogLeNet.

show abstract

“…Given the heterogeneous nature of photographs and its abstract faces (i.e., sketches/cartoons/caricatures) stemming from different generation mechanisms (i.e., intensity by digital sensor vs. drawing by hand) [10,38,56,56], there can be large geometric deformations and texture differences between a face photograph and its associated abstract faces [19,41,57]. These factors make abstract face recognition a challenging heterogeneous face recognition problem [8]. In this paper, we focus on the recognition of jointly sketch, cartoon, and caricature face, as shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Learning from the Past: Meta-Continual Learning with Knowledge Embedding for Jointly Sketch, Cartoon, and Caricature Face Recognition

Zheng

Lan

Wang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

This paper deals with a challenging task of learning from different modalities by tackling the difficulty problem of jointly face recognition between abstract-like sketches, cartoons, caricatures and real-life photographs. Due to the significant variations in the abstract faces, building vision models for recognizing data from these modalities is an extremely challenging. We propose a novel framework termed as Meta-Continual Learning with Knowledge Embedding to address the task of jointly sketch, cartoon, and caricature face recognition. In particular, we firstly present a deep relational network to capture and memorize the relation among different samples. Secondly, we present the construction of our knowledge graph that relates image with the label as the guidance of our meta-learner. We then design a knowledge embedding mechanism to incorporate the knowledge representation into our network. Thirdly, to mitigate catastrophic forgetting, we use a meta-continual model that updates our ensemble model and improves its prediction accuracy. With this meta-continual model, our network can learn from its past. The final classification is derived from our network by learning to compare the features of samples.

show abstract

Heterogeneous Face Recognition Using Domain Specific Units

Cited by 59 publications

References 42 publications

Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network

Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network

A Novel Facial Thermal Feature Extraction Method for Non-Contact Healthcare System

Learning from the Past: Meta-Continual Learning with Knowledge Embedding for Jointly Sketch, Cartoon, and Caricature Face Recognition

Contact Info

Product

Resources

About