Joint learning of visual and spatial features for edit propagation from a single image

Gui, Yan; Zeng, Guang

doi:10.1007/s00371-019-01633-6

Cited by 58 publications

(41 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is done to reduce the number of incorrect detection made by the proposed scheme as the weight assigned to different input sources of detection will be eliminating the outliers. This phase considered two cases: (1) video (human pose analysis [24], person and visual identification [25][26][27], action recognition [28]) and (2) audio data collected from sensors (linguistic analysis [29,30]). The output of this phase is obtained on the basis of the following function:…”

Section: Phase 2: Ensemble Approach For Abnormality Trackingmentioning

confidence: 99%

DeTrAs: deep learning-based healthcare framework for IoT-based assistance of Alzheimer patients

Sharma

Dudeja

Aujla

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

Healthcare 4.0 paradigm aims at realization of data-driven and patient-centric health systems wherein advanced sensors can be deployed to provide personalized assistance. Hence, extreme mentally affected patients from diseases like Alzheimer can be assisted using sophisticated algorithms and enabling technologies. Motivated from this fact, in this paper, DeTrAs: Deep Learning-based Internet of Health Framework for the Assistance of Alzheimer Patients is proposed. DeTrAs works in three phases: (1) A recurrent neural network-based Alzheimer prediction scheme is proposed which uses sensory movement data, (2) an ensemble approach for abnormality tracking for Alzheimer patients is designed which comprises two parts: (a) convolutional neural network-based emotion detection scheme and (b) timestamp window-based natural language processing scheme, and (3) an IoT-based assistance mechanism for the Alzheimer patients is also presented. The evaluation of DeTrAs depicts almost 10–20% improvement in terms of accuracy in contrast to the different existing machine learning algorithms.

show abstract

Section: Phase 2: Ensemble Approach For Abnormality Trackingmentioning

confidence: 99%

DeTrAs: deep learning-based healthcare framework for IoT-based assistance of Alzheimer patients

Sharma

Dudeja

Aujla

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…c) Compute the magnitude and three phases of each element of the quaternion array using Eq. (4), (6), (7) and (8). One magnitude array and three phase arrays can be obtained.…”

Section: The Proposed Quaternion Markovmentioning

confidence: 99%

“…With the development of image processing technology, the cost of image forensics software is decreasing which destroys the trustworthiness of digital images [1]. Some image forensics issues have been proposed [2]- [7]. Besides, machine learning is used to solve forensics issues [8]- [10].…”

Section: Introductionmentioning

confidence: 99%

Quaternion Markov Splicing Detection for Color Images Based on Quaternion Discrete Cosine Transform

Wang¹,

Liu²,

Wang³

et al. 2020

KSII TIIS

View full text Add to dashboard Cite

With the increasing amount of splicing images, many detection schemes of splicing images are proposed. In this paper, a splicing detection scheme for color image based on the quaternion discrete cosine transform (QDCT) is proposed. Firstly, the proposed quaternion Markov features are extracted in QDCT domain. Secondly, the proposed quaternion Markov features consist of global and local quaternion Markov, which utilize both magnitude and three phases to extract Markov features by using two different ways. In total, 2916-D features are extracted. Finally, the support vector machine (SVM) is used to detect the splicing images. In our experiments, the accuracy of the proposed scheme reaches 99.16% and 97.52% in CASIA TIDE v1.0 and CASIA TIDE v2.0, respectively, which exceeds that of the existing schemes.

show abstract

“…People could just use shallow neural network instead of DNN due to the lack of computing ability. The shallow neural network was not good enough compared with Support Vector Machines (SVM) [4][5][6], so the neural network algorithm was not popular at that time. In recent years, neural network has received more and more attention with the rapid increase of computer's computing power, especially convolutional neural network (CNN) [7][8].…”

Section: Introductionmentioning

confidence: 99%

Comparison of Different CNN Models in Tuberculosis Detecting

2020

KSII TIIS

View full text Add to dashboard Cite

Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

show abstract

Joint learning of visual and spatial features for edit propagation from a single image

Cited by 58 publications

References 31 publications

DeTrAs: deep learning-based healthcare framework for IoT-based assistance of Alzheimer patients

DeTrAs: deep learning-based healthcare framework for IoT-based assistance of Alzheimer patients

Quaternion Markov Splicing Detection for Color Images Based on Quaternion Discrete Cosine Transform

Comparison of Different CNN Models in Tuberculosis Detecting

Contact Info

Product

Resources

About