Sensor Level Fusion for Multi-modal Biometric Identification using Deep Learning

2021 ◽  
Author(s):  
Boucetta Aldjia ◽  
Boussaad Leila
Keyword(s):  
Deep Learning ◽  
Biometric Identification ◽  
Level Fusion

scholarly journals Palmprint And Dorsal Hand Vein Multi-Modal Biometric Fusion Using Deep Learning

2020 ◽  
Vol 10 (2) ◽  
pp. 18-42
Author(s):  
Norah Abdullah Al-johani ◽  
Lamiaa A. Elrefaei
Keyword(s):  
Deep Learning ◽  
Support Vector ◽  
Biometric System ◽  
Score Level Fusion ◽  
Dorsal Hand ◽  
Hand Vein ◽  
Recognition Systems ◽  
Dorsal Hand Vein ◽  
Level Fusion ◽  
Very High

Advancements in biometrics have attained relatively high recognition rates. However, the need for a biometric system that is reliable, robust, and convenient remains. Systems that use palmprints (PP) for verification have a number of benefits including stable line features, reduced distortion and simple self-positioning. Dorsal hand veins (DHVs) are distinctive for every person, such that even identical twins have different DHVs. DHVs appear to maintain stability over time. In the past, different features algorithms were used to implement palmprint (PP) and dorsal hand vein (DHV) systems. Previous systems relied on handcrafted algorithms. The advancements of deep learning (DL) in the features learned by the convolutional neural network (CNN) has led to its application in PP and DHV recognition systems. In this article, a multimodal biometric system based on PP and DHV using (VGG16, VGG19 and AlexNet) CNN models is proposed. The proposed system is uses two approaches: feature level fusion (FLF) and Score level fusion (SLF). In the first approach, the features from PP and DHV are extracted with CNN models. These extracted features are then fused using serial or parallel fusion and used to train error-correcting output codes (ECOC) with a support vector machine (SVM) for classification. In the second approach, the fusion at score level is done with sum, max, and product methods by applying two strategies: Transfer learning that uses CNN models for features extraction and classification for PP and DHV, then score level fusion. For the second strategy, features are extracted with CNN models for PP and DHV and used to train ECOC with SVM for classification, then score level fusion. The system was tested using two DHV databases and one PP database. The multimodal system is tested two times by repeating PP database for each DHV database. The system achieved very high accuracy rate.

scholarly journals Deep Learning Approach for Multimodal Biometric Recognition System Based on Fusion of Iris, Face, and Finger Vein Traits

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5523 ◽  
Author(s):  
Nada Alay ◽  
Heyam H. Al-Baity
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Recognition Performance ◽  
Identification System ◽  
Biometric Recognition ◽  
Multimodal Biometrics ◽  
Score Level Fusion ◽  
Softmax Classifier ◽  
Finger Vein ◽  
Level Fusion

With the increasing demand for information security and security regulations all over the world, biometric recognition technology has been widely used in our everyday life. In this regard, multimodal biometrics technology has gained interest and became popular due to its ability to overcome a number of significant limitations of unimodal biometric systems. In this paper, a new multimodal biometric human identification system is proposed, which is based on a deep learning algorithm for recognizing humans using biometric modalities of iris, face, and finger vein. The structure of the system is based on convolutional neural networks (CNNs) which extract features and classify images by softmax classifier. To develop the system, three CNN models were combined; one for iris, one for face, and one for finger vein. In order to build the CNN model, the famous pertained model VGG-16 was used, the Adam optimization method was applied and categorical cross-entropy was used as a loss function. Some techniques to avoid overfitting were applied, such as image augmentation and dropout techniques. For fusing the CNN models, different fusion approaches were employed to explore the influence of fusion approaches on recognition performance, therefore, feature and score level fusion approaches were applied. The performance of the proposed system was empirically evaluated by conducting several experiments on the SDUMLA-HMT dataset, which is a multimodal biometrics dataset. The obtained results demonstrated that using three biometric traits in biometric identification systems obtained better results than using two or one biometric traits. The results also showed that our approach comfortably outperformed other state-of-the-art methods by achieving an accuracy of 99.39%, with a feature level fusion approach and an accuracy of 100% with different methods of score level fusion.

CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment

2019 ◽  
Vol 13 (2) ◽  
pp. 282-291 ◽  
Author(s):  
Dwaipayan Biswas ◽  
Luke Everson ◽  
Muqing Liu ◽  
Madhuri Panwar ◽  
Bram-Ernst Verhoef ◽  
...  
Keyword(s):  
Heart Rate ◽  
Deep Learning ◽  
Biometric Identification ◽  
Rate Estimation ◽  
Learning Framework ◽  
Heart Rate Estimation

scholarly journals Crop Type Mapping from Optical and Radar Time Series Using Attention-Based Deep Learning

2021 ◽  
Vol 13 (22) ◽  
pp. 4668
Author(s):  
Stella Ofori-Ampofo ◽  
Charlotte Pelletier ◽  
Stefan Lang
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Decision Level ◽  
Type Mapping ◽  
Learning Techniques ◽  
Crop Type ◽  
Single Sensor ◽  
Decision Level Fusion ◽  
Level Fusion ◽  
Sentinel 2

Crop maps are key inputs for crop inventory production and yield estimation and can inform the implementation of effective farm management practices. Producing these maps at detailed scales requires exhaustive field surveys that can be laborious, time-consuming, and expensive to replicate. With a growing archive of remote sensing data, there are enormous opportunities to exploit dense satellite image time series (SITS), temporal sequences of images over the same area. Generally, crop type mapping relies on single-sensor inputs and is solved with the help of traditional learning algorithms such as random forests or support vector machines. Nowadays, deep learning techniques have brought significant improvements by leveraging information in both spatial and temporal dimensions, which are relevant in crop studies. The concurrent availability of Sentinel-1 (synthetic aperture radar) and Sentinel-2 (optical) data offers a great opportunity to utilize them jointly; however, optimizing their synergy has been understudied with deep learning techniques. In this work, we analyze and compare three fusion strategies (input, layer, and decision levels) to identify the best strategy that optimizes optical-radar classification performance. They are applied to a recent architecture, notably, the pixel-set encoder–temporal attention encoder (PSE-TAE) developed specifically for object-based classification of SITS and based on self-attention mechanisms. Experiments are carried out in Brittany, in the northwest of France, with Sentinel-1 and Sentinel-2 time series. Input and layer-level fusion competitively achieved the best overall F-score surpassing decision-level fusion by 2%. On a per-class basis, decision-level fusion increased the accuracy of dominant classes, whereas layer-level fusion improves up to 13% for minority classes. Against single-sensor baseline, multi-sensor fusion strategies identified crop types more accurately: for example, input-level outperformed Sentinel-2 and Sentinel-1 by 3% and 9% in F-score, respectively. We have also conducted experiments that showed the importance of fusion for early time series classification and under high cloud cover condition.

Sign in / Sign up

Export Citation Format

Share Document