Face image super-resolution with pose via nuclear norm regularized structural orthogonal Procrustes regression

Gao, Guangwei; Zhu, Dong; Yang, Meng; Lu, Huimin; Wu, Yang; Gao, Hao

doi:10.1007/s00521-018-3826-1

Cited by 10 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of images per batch was set to 64, and the network was trained 1000 times. The testing dataset comprised the internationally common datasets "Set5" [40,41] and "Set14" [42,43]. The GPU was NVIDIA GeForce 1080 T i , the experimental environment was Keras, and Python 3.5 and OpenCV 3.0 were applied to carry out the simulation experiments.…”

Section: Parameter Settingsmentioning

confidence: 99%

RETRACTED: Image Super-Resolution Algorithm Based on Dual-Channel Convolutional Neural Networks

et al. 2019

View full text Add to dashboard Cite

For the image super-resolution method from a single channel, it is difficult to achieve both fast convergence and high-quality texture restoration. By mitigating the weaknesses of existing methods, the present paper proposes an image super-resolution algorithm based on dual-channel convolutional neural networks (DCCNN). The novel structure of the network model was divided into a deep channel and a shallow channel. The deep channel was used to extract the detailed texture information from the original image, while the shallow channel was mainly used to recover the overall outline of the original image. Firstly, the residual block was adjusted in the feature extraction stage, and the nonlinear mapping ability of the network was enhanced. The feature mapping dimension was reduced, and the effective features of the image were obtained. In the up-sampling stage, the parameters of the deconvolutional kernel were adjusted, and high-frequency signal loss was decreased. The high-resolution feature space could be rebuilt recursively using long-term and short-term memory blocks during the reconstruction stage, further enhancing the recovery of texture information. Secondly, the convolutional kernel was adjusted in the shallow channel to reduce the parameters, ensuring that the overall outline of the image was restored and that the network converged rapidly. Finally, the dual-channel loss function was jointly optimized to enhance the feature-fitting ability in order to obtain the final high-resolution image output. Using the improved algorithm, the network converged more rapidly, the image edge and texture reconstruction effect were obviously improved, and the Peak Signal-to-Noise Ratio (PSNR) and structural similarity were also superior to those of other solutions.

show abstract

Section: Parameter Settingsmentioning

confidence: 99%

RETRACTED: Image Super-Resolution Algorithm Based on Dual-Channel Convolutional Neural Networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The generative model is a model that can learn the potential distribution of data and generate new sensor samples. Traditional generative models include the Gaussian model (GM), Bayesian network (BN) [3], S-type reliability network (SRN) [4], Gaussian mixture model (GMM) [5], multinomial mixture model (MMM) [6], hidden Markov model (HMM) [7] and hidden Markov random field (HMRF) [8]. Goodfellow et al [9] proposed generative adversarial networks (GAN) by summarizing the advantages and disadvantages of traditional generative networks.…”

Section: Introductionmentioning

confidence: 99%

RETRACTED: The Novel Sensor Network Structure for Classification Processing Based on the Machine Learning Method of the ACGAN

Chen

Tao

Wang

et al. 2019

Sensors

View full text Add to dashboard Cite

To address the problem of unstable training and poor accuracy in image classification algorithms based on generative adversarial networks (GAN), a novel sensor network structure for classification processing using auxiliary classifier generative adversarial networks (ACGAN) is proposed in this paper. Firstly, the real/fake discrimination of sensor samples in the network has been canceled at the output layer of the discriminative network and only the posterior probability estimation of the sample tag is outputted. Secondly, by regarding the real sensor samples as supervised data and the generative sensor samples as labeled fake data, we have reconstructed the loss function of the generator and discriminator by using the real/fake attributes of sensor samples and the cross-entropy loss function of the label. Thirdly, the pooling and caching method has been introduced into the discriminator to enable more effective extraction of the classification features. Finally, feature matching has been added to the discriminative network to ensure the diversity of the generative sensor samples. Experimental results have shown that the proposed algorithm (CP-ACGAN) achieves better classification accuracy on the MNIST dataset, CIFAR10 dataset and CIFAR100 dataset than other solutions. Moreover, when compared with the ACGAN and CNN classification algorithms, which have the same deep network structure as CP-ACGAN, the proposed method continues to achieve better classification effects and stability than other main existing sensor solutions.

show abstract

“…22 These sequences were selected to verify the proposed algorithm. The proposed algorithm is used to analyze the evaluation standard of the accuracy rate (Precision Plot, PT) [38][39][40][41][42][43] and the success rate (Success Plot, SP) 38,[44][45][46][47][48] curve map. At the same time, the CLE, 38 DP, 38 and weight are also used.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Retracted: Multiscale fast correlation filtering tracking algorithm based on a feature fusion model

Chen

Wang

Liu

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary In scenes high in visual complexity, the identification of a moving object can be affected by changes in scale and occlusion factors during the tracking process, resulting in reduced tracking accuracy. Accordingly, to address the problem of low accuracy, a multiscale fast correlation filtering tracking algorithm based on a feature fusion model is proposed in the present work with the aim of reducing the poor tracking effects caused by occlusion discrimination and scale changes in complex scenes. The object's grayscale (GRAY) feature, histogram of oriented gradient (HOG) feature, and color name (CN) feature are reduced to dimensions and fused to form a feature matrix. Moreover, a hierarchical principal component analysis (HPCA) algorithm is used to extract visually salient features and reconstruct the feature matrix under real‐time conditions, the correlation filtering position is trained, the number of dimensions is effectively reduced, and the feature fusion matrix is used to train the multiscale fast correlation filtering, with the result that the object's position and scale can be accurately predicted. The proposed algorithm is then compared with five popular correlation filtering tracking algorithms. Experimental results demonstrate that its average tracking speed reaches a reasonable frames/second velocity; moreover, it can also achieve promising object tracking results on the OTB benchmark data sets. The tracking accuracy is superior to that of the other five correlation filtering tracking algorithms when applied to scenes featuring object occlusion and changes in scale. The proposed algorithm also exhibits better robustness and improved performance under real‐time conditions in sophisticated scenarios, including scale variation, deformation, fast motion, occlusion, and so on.

show abstract

Face image super-resolution with pose via nuclear norm regularized structural orthogonal Procrustes regression

Cited by 10 publications

References 48 publications

RETRACTED: Image Super-Resolution Algorithm Based on Dual-Channel Convolutional Neural Networks

RETRACTED: Image Super-Resolution Algorithm Based on Dual-Channel Convolutional Neural Networks

RETRACTED: The Novel Sensor Network Structure for Classification Processing Based on the Machine Learning Method of the ACGAN

Retracted: Multiscale fast correlation filtering tracking algorithm based on a feature fusion model

Contact Info

Product

Resources

About