A novel synthetic dataset for research in overlapped fingerprint separation

People spend more than 80% of their time in indoor spaces, such as shopping malls and office buildings. Indoor trajectories collected by indoor positioning devices, such as WiFi and Bluetooth devices, can reflect human movement behaviors in indoor spaces. Insightful indoor movement patterns can be discovered from indoor trajectories using various clustering methods. These methods are based on a measure that reflects the degree of similarity between indoor trajectories. Researchers have proposed many trajectory similarity measures. However, existing trajectory similarity measures ignore the indoor movement constraints imposed by the indoor space and the characteristics of indoor positioning sensors, which leads to an inaccurate measure of indoor trajectory similarity. Additionally, most of these works focus on the spatial and temporal dimensions of trajectories and pay less attention to indoor semantic information. Integrating indoor semantic information such as the indoor point of interest into the indoor trajectory similarity measurement is beneficial to discovering pedestrians having similar intentions. In this paper, we propose an accurate and reasonable indoor trajectory similarity measure called the indoor semantic trajectory similarity measure (ISTSM), which considers the features of indoor trajectories and indoor semantic information simultaneously. The ISTSM is modified from the edit distance that is a measure of the distance between string sequences. The key component of the ISTSM is an indoor navigation graph that is transformed from an indoor floor plan representing the indoor space for computing accurate indoor walking distances. The indoor walking distances and indoor semantic information are fused into the edit distance seamlessly. The ISTSM is evaluated using a synthetic dataset and real dataset for a shopping mall. The experiment with the synthetic dataset reveals that the ISTSM is more accurate and reasonable than three other popular trajectory similarities, namely the longest common subsequence (LCSS), edit distance on real sequence (EDR), and the multidimensional similarity measure (MSM). The case study of a shopping mall shows that the ISTSM effectively reveals customer movement patterns of indoor customers.

Download Full-text

Posture similarity index: a method to compare hand postures in synergy space

PeerJ ◽

10.7717/peerj.6078 ◽

2018 ◽

Vol 6 ◽

pp. e6078 ◽

Cited By ~ 1

Author(s):

Nayan Bhatt ◽

Varadhan SKM

Keyword(s):

Experimental Data ◽

Tracking System ◽

Synthetic Data ◽

Similarity Index ◽

Principal Component ◽

Synthetic Dataset ◽

Human Hand ◽

Task Requirements ◽

Kinematic Synergies ◽

The Central Nervous System

Background The human hand can perform a range of manipulation tasks, from holding a pen to holding a hammer. The central nervous system (CNS) uses different strategies in different manipulation tasks based on task requirements. Attempts to compare postures of the hand have been made for use in robotics and animation industries. In this study, we developed an index called the posture similarity index to quantify the similarity between two human hand postures. Methods Twelve right-handed volunteers performed 70 postures, and lifted and held 30 objects (total of 100 different postures, each performed five times). A 16-sensor electromagnetic tracking system captured the kinematics of individual finger phalanges (segments). We modeled the hand as a 21-DoF system and computed the corresponding joint angles. We used principal component analysis to extract kinematic synergies from this 21-DoF data. We developed a posture similarity index (PSI), that represents the similarity between posture in the synergy (Principal component) space. First, we tested the performance of this index using a synthetic dataset. After confirming that it performs well with the synthetic dataset, we used it to analyze the experimental data. Further, we used PSI to identify postures that are “representative” in the sense that they have a greater overlap (in synergy space) with a large number of postures. Results Our results confirmed that PSI is a relatively accurate index of similarity in synergy space both with synthetic data and real experimental data. Also, more special postures than common postures were found among “representative” postures. Conclusion We developed an index for comparing posture similarity in synergy space and demonstrated its utility by using synthetic dataset and experimental dataset. Besides, we found that “special” postures are actually “special” in the sense that there are more of them in the “representative” postures as identified by our posture similarity index.

Download Full-text

Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images

Frontiers in Neurorobotics ◽

10.3389/fnbot.2021.751037 ◽

2021 ◽

Vol 15 ◽

Author(s):

Xin Li ◽

Yonggang Li ◽

Renchao Wu ◽

Can Zhou ◽

Hongqiu Zhu

Keyword(s):

Detection System ◽

Short Circuit ◽

Infrared Image ◽

Parameter Tuning ◽

Recall Rate ◽

Synthetic Methods ◽

Synthetic Dataset ◽

Small Scale ◽

Infrared Images ◽

Key Variables

This paper is concerned with the problem of short circuit detection in infrared image for metal electrorefining with an improved Faster Region-based Convolutional Neural Network (Faster R-CNN). To address the problem of insufficient label data, a framework for automatically generating labeled infrared images is proposed. After discussing factors that affect sample diversity, background, object shape, and gray scale distribution are established as three key variables for synthesis. Raw infrared images without fault are used as backgrounds. By simulating the other two key variables on the background, different classes of objects are synthesized. To improve the detection rate of small scale targets, an attention module is introduced in the network to fuse the semantic segment results of U-Net and the synthetic dataset. In this way, the Faster R-CNN can obtain rich representation ability about small scale object on the infrared images. Strategies of parameter tuning and transfer learning are also applied to improve the detection precision. The detection system trains on only synthetic dataset and tests on actual images. Extensive experiments on different infrared datasets demonstrate the effectiveness of the synthetic methods. The synthetically trained network obtains a mAP of 0.826, and the recall rate of small latent short circuit is superior to that of Faster R-CNN and U-Net, effectively avoiding short-circuit missed detection.

Download Full-text

Latent overlapped fingerprint separation: a review

Multimedia Tools and Applications ◽

10.1007/s11042-016-3908-y ◽

2016 ◽

Vol 76 (15) ◽

pp. 16263-16290 ◽

Cited By ~ 11

Author(s):

Branka Stojanović ◽

Oge Marques ◽

Aleksandar Nešković

Keyword(s):

Fingerprint Separation

Download Full-text

Solving the Adaptive Curriculum Sequencing Problem with Prey-Predator Algorithm

International Journal of Distance Education Technologies ◽

10.4018/ijdet.2019100105 ◽

2019 ◽

Vol 17 (4) ◽

pp. 71-93 ◽

Cited By ~ 2

Author(s):

Marcelo de Oliveira Costa Machado ◽

Eduardo Barrére ◽

Jairo Souza

Keyword(s):

Adaptive Learning ◽

Synthetic Dataset ◽

Learning Material ◽

Hard Problem ◽

Np Hard ◽

Sequencing Problem ◽

Np Hard Problem ◽

Curriculum Sequencing

Adaptive curriculum sequencing (ACS) is still a challenge in the adaptive learning field. ACS is a NP-hard problem especially considering the several constraints of the student and the learning material when selecting a sequence from repositories where several sequences could be chosen. Therefore, this has stimulated several researchers to use evolutionary approaches in the search for satisfactory solutions. This work explores the use of an adaptation of the prey-predator algorithm for the ACS problem. Pedagogical experiments with a real student dataset and convergence experiments with a synthetic dataset have shown that the proposed solution is suitable for the problem, although it is a solution not yet explored in the adaptive learning literature.

Download Full-text

Synthetic dataset generation for text recognition with generative adversarial networks

Twelfth International Conference on Machine Vision (ICMV 2019) ◽

10.1117/12.2558271 ◽

2020 ◽

Author(s):

Valeria Efimova ◽

Viacheslav Shalamov ◽

Andrey Filchenkov

Keyword(s):

Synthetic Dataset ◽

Text Recognition ◽

Generative Adversarial Networks ◽

Adversarial Networks

Download Full-text

Virtual to Real Adaptation of Pedestrian Detectors

Sensors ◽

10.3390/s20185250 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5250

Author(s):

Luca Ciampi ◽

Nicola Messina ◽

Fabrizio Falchi ◽

Claudio Gennaro ◽

Giuseppe Amato

Keyword(s):

Video Game ◽

Real World ◽

Domain Adaptation ◽

Pedestrian Detection ◽

Synthetic Dataset ◽

Real World Data ◽

Human Effort ◽

General Object ◽

Different Characteristics ◽

A Performance

Pedestrian detection through Computer Vision is a building block for a multitude of applications. Recently, there has been an increasing interest in convolutional neural network-based architectures to execute such a task. One of these supervised networks’ critical goals is to generalize the knowledge learned during the training phase to new scenarios with different characteristics. A suitably labeled dataset is essential to achieve this purpose. The main problem is that manually annotating a dataset usually requires a lot of human effort, and it is costly. To this end, we introduce ViPeD (Virtual Pedestrian Dataset), a new synthetically generated set of images collected with the highly photo-realistic graphical engine of the video game GTA V (Grand Theft Auto V), where annotations are automatically acquired. However, when training solely on the synthetic dataset, the model experiences a Synthetic2Real domain shift leading to a performance drop when applied to real-world images. To mitigate this gap, we propose two different domain adaptation techniques suitable for the pedestrian detection task, but possibly applicable to general object detection. Experiments show that the network trained with ViPeD can generalize over unseen real-world scenarios better than the detector trained over real-world data, exploiting the variety of our synthetic dataset. Furthermore, we demonstrate that with our domain adaptation techniques, we can reduce the Synthetic2Real domain shift, making the two domains closer and obtaining a performance improvement when testing the network over the real-world images.

Download Full-text

Intelligent Clustering and Dynamic Incremental Learning to Generate Multi-Codebook Fuzzy Neural Network for Multi-Modal Data Classification

Symmetry ◽

10.3390/sym12040679 ◽

2020 ◽

Vol 12 (4) ◽

pp. 679

Author(s):

Muhammad Anwar Ma’sum

Keyword(s):

Neural Networks ◽

Incremental Learning ◽

Data Classification ◽

Fuzzy Neural Networks ◽

Benchmark Dataset ◽

Synthetic Dataset ◽

Special Treatment ◽

Modal Data ◽

Fuzzy Neural ◽

Benchmark Datasets

Classification in multi-modal data is one of the challenges in the machine learning field. The multi-modal data need special treatment as its features are distributed in several areas. This study proposes multi-codebook fuzzy neural networks by using intelligent clustering and dynamic incremental learning for multi-modal data classification. In this study, we utilized intelligent K-means clustering based on anomalous patterns and intelligent K-means clustering based on histogram information. In this study, clustering is used to generate codebook candidates before the training process, while incremental learning is utilized when the condition to generate a new codebook is sufficient. The condition to generate a new codebook in incremental learning is based on the similarity of the winner class and other classes. The proposed method was evaluated in synthetic and benchmark datasets. The experiment results showed that the proposed multi-codebook fuzzy neural networks that use dynamic incremental learning have significant improvements compared to the original fuzzy neural networks. The improvements were 15.65%, 5.31% and 11.42% on the synthetic dataset, the benchmark dataset, and the average of all datasets, respectively, for incremental version 1. The incremental learning version 2 improved by 21.08% 4.63%, and 14.35% on the synthetic dataset, the benchmark dataset, and the average of all datasets, respectively. The multi-codebook fuzzy neural networks that use intelligent clustering also had significant improvements compared to the original fuzzy neural networks, achieving 23.90%, 2.10%, and 15.02% improvements on the synthetic dataset, the benchmark dataset, and the average of all datasets, respectively.

Download Full-text

Robust nonlinear canonical correlation analysis: application to seasonal climate forecasting

Nonlinear Processes in Geophysics ◽

10.5194/npg-15-221-2008 ◽

2008 ◽

Vol 15 (1) ◽

pp. 221-232 ◽

Cited By ~ 22

Author(s):

A. J. Cannon ◽

W. W. Hsieh

Keyword(s):

Correlation Analysis ◽

Canonical Correlation Analysis ◽

Canonical Correlation ◽

Mean Squared Error ◽

Synthetic Dataset ◽

Model Parameters ◽

Inverse Mapping ◽

Seasonal Climate ◽

The Mean ◽

Improved Performance

Abstract. Robust variants of nonlinear canonical correlation analysis (NLCCA) are introduced to improve performance on datasets with low signal-to-noise ratios, for example those encountered when making seasonal climate forecasts. The neural network model architecture of standard NLCCA is kept intact, but the cost functions used to set the model parameters are replaced with more robust variants. The Pearson product-moment correlation in the double-barreled network is replaced by the biweight midcorrelation, and the mean squared error (mse) in the inverse mapping networks can be replaced by the mean absolute error (mae). Robust variants of NLCCA are demonstrated on a synthetic dataset and are used to forecast sea surface temperatures in the tropical Pacific Ocean based on the sea level pressure field. Results suggest that adoption of the biweight midcorrelation can lead to improved performance, especially when a strong, common event exists in both predictor/predictand datasets. Replacing the mse by the mae leads to improved performance on the synthetic dataset, but not on the climate dataset except at the longest lead time, which suggests that the appropriate cost function for the inverse mapping networks is more problem dependent.

Download Full-text