ABSTRACT
Blind image deblurring is a challenging problem in computer vision, aiming to restore the sharp image from blurred observation. Due to the incompatibility between the complex unknown degradation and the simple synthetic model, directly training a deep convolutional neural network (CNN) usually cannot sufficiently handle real-world blurry images. An existed generative adversarial network (GAN) can generate more detailed and realistic images, but the game between generator and discriminator is unbalancing, which leads to the training parameters not being able to converge to the ideal Nash equilibrium points. In this paper, we propose a GAN with a dual-branch discriminator using multiple sparse priors for image deblurring (DBSGAN) to overcome this limitation. By adding the multiple sparse priors into the other branch of the discriminator, the task of the discriminator is more complex. It can balance the game between the generator and the discriminator. Extensive experimental results on both synthetic and real-world blurry image datasets demonstrate the superior performance of our method over the state of the art in terms of quantitative metrics and visual quality. Especially for the GOPRO dataset, the averaged PSNR improves 1.7% over others.
Subject(s)
Image Processing, Computer-Assisted , Neural Networks, Computer , Image Processing, Computer-Assisted/methodsABSTRACT
OBJECTIVE: To compare the effects of manipulation treatment and transcutaneous electrical nerve stimulation (TENS) on patients with cervicogenic headache. METHODS: Seventy patients with cervicogenic headache were randomly allocated to receive manipulation treatment and TENS treatment, which were given every other day respectively for total 40 days. The headache degree (numeric rating scale, NRS), frequency, lasting time and the range of motion (ROM) of the cervical spine 2 weeks before treatment and 4 weeks after treatment, were compared. RESULTS: Before treatment, there were no significant differences in the headache NRS scores , frequency, lasting time and the ROM scores between the two groups (P>0.05). After treatment, the headache NRS score, frequency, lasting time in the manipulation group decreased significantly (P<0.01), while in the TENS group just the headache NRS score decreased significantly (P<0.05). The ROM scores in both groups showed no significant changes (P>0.05). The response rate of manipulation treatment is 94.5%, significantly higher than 64.5% of TENS treatment (P<0.05). CONCLUSION: The manipulation treatment is an effective method for patients with cervicogenic headache.
