scholarly journals Learning a convolutional neural network for non-uniform motion blur removal

2015 ◽  
Author(s):  
Jian Sun ◽  
Wenfei Cao ◽  
Zongben Xu ◽  
Jean Ponce
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Motion Blur ◽  
Uniform Motion ◽  
Blur Removal

Motion-blur kernel size estimation via learning a convolutional neural network

2019 ◽  
Vol 119 ◽  
pp. 86-93 ◽  
Author(s):  
Lerenhan Li ◽  
Nong Sang ◽  
Luxin Yan ◽  
Changxin Gao
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Motion Blur ◽  
Size Estimation ◽  
Kernel Size ◽  
Blur Kernel

Video super resolution using convolutional neural network and image fusion techniques

2021 ◽  
Vol 24 (4) ◽  
pp. 279-287
Author(s):  
Vikas Kumar ◽  
Tanupriya Choudhury ◽  
Suresh Chandra Satapathy ◽  
Ravi Tomar ◽  
Archit Aggarwal
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Image Fusion ◽  
Reference Model ◽  
Super Resolution ◽  
Motion Blur ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Recently, huge progress has been achieved in the field of single image super resolution which augments the resolution of images. The idea behind super resolution is to convert low-resolution images into high-resolution images. SRCNN (Single Resolution Convolutional Neural Network) was a huge improvement over the existing methods of single-image super resolution. However, video super-resolution, despite being an active field of research, is yet to benefit from deep learning. Using still images and videos downloaded from various sources, we explore the possibility of using SRCNN along with image fusion techniques (minima, maxima, average, PCA, DWT) to improve over existing video super resolution methods. Video Super-Resolution has inherent difficulties such as unexpected motion, blur and noise. We propose Video Super Resolution – Image Fusion (VSR-IF) architecture which utilizes information from multiple frames to produce a single high- resolution frame for a video. We use SRCNN as a reference model to obtain high resolution adjacent frames and use a concatenation layer to group those frames into a single frame. Since, our method is data-driven and requires only minimal initial training, it is faster than other video super resolution methods. After testing our program, we find that our technique shows a significant improvement over SCRNN and other single image and frame super resolution techniques.

scholarly journals Artificial Intelligence and Convolutional Neural Network for Recognition of Human Interaction by Video from Drone

2019 ◽  
Author(s):  
Ghazal Shamsipour ◽  
Saied Pirasteh
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Poor Quality ◽  
Motion Blur ◽  
Human Interaction ◽  
Support Vector ◽  
Central Florida ◽  
The Difference ◽  
High Level ◽  
The University

Recognition of the human interaction on the unconstrained videos taken from cameras and remote sensing platforms like a drone is a challenging problem. This study presents a method to resolve issues of motion blur, poor quality of videos, occlusions, the difference in body structure or size, and high computation or memory requirement. This study contributes to the improvement of recognition of human interaction during disasters such as an earthquake and flood utilizing drone videos for rescue and emergency management. We used Support Vector Machine (SVM) to classify the high-level and stationary features obtained from Convolutional Neural Network (CNN) in key-frames from videos. We extracted conceptual features by employing CNN to recognize objects from first and last images from a video. The proposed method demonstrated the context of a scene, which is significant in determining the behaviour of human in the videos. In this method, we do not require person detection, tracking, and many instances of images. The proposed method was tested for the University of Central Florida (UCF Sports Action), Olympic Sports videos. These videos were taken from the ground platform. Besides, camera drone video was captured from Southwest Jiaotong University (SWJTU) Sports Centre and incorporated to test the developed method in this study. This study accomplished an acceptable performance with an accuracy of 90.42%, which has indicated improvement of more than 4.92% as compared to the existing methods.

Image Forgery Detection Based on Motion Blur Estimated Using Convolutional Neural Network

2019 ◽  
Vol 19 (23) ◽  
pp. 11601-11611 ◽  
Author(s):  
Chunhe Song ◽  
Peng Zeng ◽  
Zhongfeng Wang ◽  
Tong Li ◽  
Lin Qiao ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Motion Blur ◽  
Forgery Detection ◽  
Image Forgery ◽  
Image Forgery Detection

CONVOLUTIONAL NEURAL NETWORK BASED ALGORITHM FOR CECUM ACHIEVEMENT CONFIRMATION

2020 ◽  
Author(s):  
S Kashin ◽  
D Zavyalov ◽  
A Rusakov ◽  
V Khryashchev ◽  
A Lebedev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Sign in / Sign up

Export Citation Format

Share Document