Multi-source deep transfer learning for cross-sensor biometrics

Kandaswamy, Chetak; Monteiro, João C.; Silva, Luís M.; Cardoso, Jaime S.

doi:10.1007/s00521-016-2325-5

Cited by 24 publications

(5 citation statements)

References 27 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, apart from the deep learning methods, we also show the comparison with handcrafted features such as Histogram of Oriented Gradients (HOG) [6] and Daisy features (similar to SIFT) [33]. The 1 Kandaswamy et al [12] has reported results on this database, but the protocol used in their work is transfer learning based. Santos et al [27] had performed cross-sensor experiments, but evaluated their algorithm on the entire dataset.…”

Section: Resultsmentioning

confidence: 99%

Heterogeneity Aware Deep Embedding for Mobile Periocular Recognition

Rishabh

Baweja

Ghosh

et al. 2018

2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

Mobile biometric approaches provide the convenience of secure authentication with an omnipresent technology. However, this brings an additional challenge of recognizing biometric patterns in an unconstrained environment including variations in mobile camera sensors, illumination conditions, and capture distance. To address the heterogeneous challenge, this research presents a novel heterogeneity aware loss function within a deep learning framework. The effectiveness of the proposed loss function is evaluated for periocular biometrics using the CSIP, IMP and VISOB mobile periocular databases. The results show that the proposed algorithm yields state-of-the-art results in a heterogeneous environment and improves generalizability for crossdatabase experiments.

show abstract

Section: Resultsmentioning

confidence: 99%

Heterogeneity Aware Deep Embedding for Mobile Periocular Recognition

Rishabh

Baweja

Ghosh

et al. 2018

2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

show abstract

“…A possible alternative is to use deep transfer learning (DTL) which offers more flexibility when extracting high-level features [41]. DTL can perform layer-by-layer feature transference to solve a target problem in either a supervised or unsupervised setting [80]. -In a CNN, the features detected by earlier layers include low-level image details such as edges and colors.…”

Section: Discussionmentioning

confidence: 99%

Human Pose and Path Estimation from Aerial Video Using Dynamic Classifier Selection

2018

View full text Add to dashboard Cite

Background / introduction-We consider the problem of estimating human pose and trajectory by an aerial robot with a monocular camera in near real time. We present a preliminary solution whose distinguishing feature is a dynamic classifier selection architecture.Methods-In our solution, each video frame is corrected for perspective using projective transformation. Then, two alternative feature sets are used: (i) Histogram of Oriented Gradients (HOG) of the silhouette, (ii) Convolutional Neural Network (CNN) features of the RGB image. The features (HOG or CNN) are classified using a dynamic classifier. A class is defined as a pose-viewpoint pair, and a total of 64 classes are defined to represent a forward walking and turning gait sequence.Results-Our solution provides three main advantages: (i) Classification is efficient due to dynamic selection (4-class vs. 64-class classification). (ii) Classification errors are confined to neighbors of the true viewpoints. (iii) The robust temporal relationship between poses is used to resolve the left-right ambiguities of human silhouettes.Conclusions-Experiments conducted on both frontoparallel videos and aerial videos confirm our solution can achieve accurate pose and trajectory estimation for both scenarios. We found using HOG features provides higher accuracy than using CNN features. For example, applying the HOG-based variant of our scheme to the "walking on a figure 8-shaped path" dataset (1652 frames) achieved estimation accuracies of 99.6% for viewpoints and 96.2% for number of poses.

show abstract

“…In this section, some related works are briefly introduced. Examples of applications in different research areas, such as image classification [ 48 , 49 ], text classification [ 50 ], and biometrics [ 51 ], can be found in the literature. In Reference [ 52 ], a new multi-source deep transfer neural network algorithm, based on a convolutional neural network (CNN) and a multi-source TL technique, is proposed and evaluated on several classification benchmarks.…”

Section: Related Workmentioning

confidence: 99%

RNN- and LSTM-Based Soft Sensors Transferability for an Industrial Process

Curreri

Patané

Xibilia

2021

Sensors

View full text Add to dashboard Cite

The design and application of Soft Sensors (SSs) in the process industry is a growing research field, which needs to mediate problems of model accuracy with data availability and computational complexity. Black-box machine learning (ML) methods are often used as an efficient tool to implement SSs. Many efforts are, however, required to properly select input variables, model class, model order and the needed hyperparameters. The aim of this work was to investigate the possibility to transfer the knowledge acquired in the design of a SS for a given process to a similar one. This has been approached as a transfer learning problem from a source to a target domain. The implementation of a transfer learning procedure allows to considerably reduce the computational time dedicated to the SS design procedure, leaving out many of the required phases. Two transfer learning methods have been proposed, evaluating their suitability to design SSs based on nonlinear dynamical models. Recurrent neural structures have been used to implement the SSs. In detail, recurrent neural networks and long short-term memory architectures have been compared in regard to their transferability. An industrial case of study has been considered, to evaluate the performance of the proposed procedures and the best compromise between SS performance and computational effort in transferring the model. The problem of labeled data scarcity in the target domain has been also discussed. The obtained results demonstrate the suitability of the proposed transfer learning methods in the design of nonlinear dynamical models for industrial systems.

show abstract

Multi-source deep transfer learning for cross-sensor biometrics

Cited by 24 publications

References 27 publications

Heterogeneity Aware Deep Embedding for Mobile Periocular Recognition

Heterogeneity Aware Deep Embedding for Mobile Periocular Recognition

Human Pose and Path Estimation from Aerial Video Using Dynamic Classifier Selection

RNN- and LSTM-Based Soft Sensors Transferability for an Industrial Process

Contact Info

Product

Resources

About