Fusion network for blur discrimination

Abstract. Blurry image discrimination is a challenging and critical problem in computer vision. It is useful for image restoration, object recognition, and other image applications. In previous studies, researchers proposed a discrimination method based on hand-extracted features or deep learning. However, these methods are either pure data driven by deep learning or over-simplified assumptions on prior knowledge. As a result, a discrimination method is proposed for distinguishing sharp images and blurry images based on a fusion network. The proposed method can automatically discriminate and detect blur without performing image restoration or blur kernel function estimation. Actually, the blur and the noise are extracted by the improved VGG16 network and texture noise extraction algorithm, respectively. Then the fusion network integrates the advantages of deep learning and hand-extracted features, and achieves ultimate high-accuracy discrimination results. Rigorous experiments performed on own dataset and other popular datasets with a number of blurry images and sharp images, including RealBlur dataset, BSD-B dataset, and GoPro dataset. The results show that the proposed method outperforms with an accuracy of 98% on our own dataset and 94.8% on the other dataset, which satisfies the requirements of the image applications. Similarly, we have compared our method with state-of-the-art methods to show its robustness and generalization ability.

[1]  K. M. Bhurchandi,et al.  No reference noise estimation in digital images using random conditional selection and sampling theory , 2017, The Visual Computer.

[2]  Muhammad Ammar Khan,et al.  Detection of Blur and Non-Blur Regions using Frequency-based Multi-level Fusion Transformation and Classification via KNN Matting , 2019, 2019 13th International Conference on Mathematics, Actuarial Science, Computer Science and Statistics (MACS).

[3]  Michal Irani,et al.  Blind Deblurring Using Internal Patch Recurrence , 2014, ECCV.

[4]  Maarten Jansen,et al.  Noise Reduction by Wavelet Thresholding , 2001 .

[5]  Hubert Konik,et al.  Blur identification in image processing , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[6]  Cheol-Su Kim,et al.  Novel input and output mapping-sensitive error back propagation learning algorithm for detecting small input feature variations , 2011, Neural Computing and Applications.

[7]  Deqing Sun,et al.  Blind Image Deblurring Using Dark Channel Prior , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Kai Zeng,et al.  A Local Metric for Defocus Blur Detection Based on CNN Feature Learning , 2019, IEEE Transactions on Image Processing.

[9]  Gabor C. Temes,et al.  Simple and efficient noise estimation algorithm , 2004 .

[10]  Li Xu,et al.  Unnatural L0 Sparse Representation for Natural Image Deblurring , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Tomasz Szandala.  Convolutional Neural Network for Blur Images Detection as an Alternative for Laplacian Method , 2020, 2020 IEEE Symposium Series on Computational Intelligence (SSCI).

[12]  Xi Chen,et al.  The improved image inpainting algorithm via encoder and similarity constraint , 2020, The Visual Computer.

[13]  Tae Hyun Kim,et al.  Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Sunghyun Cho,et al.  Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms , 2020, ECCV.

[15]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[16]  Huchuan Lu,et al.  Defocus Blur Detection via Multi-stream Bottom-Top-Bottom Fully Convolutional Network , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[17]  Qian Zhang,et al.  Research of improving semantic image segmentation based on a feature fusion model , 2020, Journal of Ambient Intelligence and Humanized Computing.

[18]  Yun Du,et al.  The infrared moving target extraction and fast video reconstruction algorithm , 2019, Infrared Physics & Technology.

[19]  Li Xu,et al.  Discriminative Blur Detection Features , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Bittu Kumar.  Mean-Median based Noise Estimation Method using Spectral Subtraction for Speech Enhancement Technique , 2016 .

[21]  Yi-fei Pu,et al.  Fractional-order global optimal backpropagation machine trained by an improved fractional-order steepest descent method , 2020, Frontiers of Information Technology & Electronic Engineering.

[22]  Jizhou Sun,et al.  Multiscale blur detection by learning discriminative deep features , 2018, Neurocomputing.

[23]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[24]  Wen Gao,et al.  Single-Image Blind Deblurring Using Multi-Scale Latent Structure Prior , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[25]  Tao Zhang,et al.  Fraction-Order Total Variation Image Blind Restoration Based on Self-Similarity Features , 2020, IEEE Access.

[26]  Jiantao Zhou,et al.  Image Restoration via Simultaneous Nonlocal Self-Similarity Priors , 2020, IEEE Transactions on Image Processing.

[27]  Jiaya Jia,et al.  Image partial blur detection and classification , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Georgy Sofronov,et al.  Change-Point Detection in Autoregressive Processes via the Cross-Entropy Method , 2020, Algorithms.

[29]  T. Teo,et al.  INTEGRATION OF IMAGE-DERIVED AND POS-DERIVED FEATURES FOR IMAGE BLUR DETECTION , 2016 .

[30]  R. GUERAICHI,et al.  Blurred Image Detection In Drone Embedded System , 2020, 2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).

[31]  Blurring Detection Based on Selective Features for Iris Recognition , 2020 .

[32]  Wei Xu,et al.  Detecting and classifying blurred image regions , 2013, 2013 IEEE International Conference on Multimedia and Expo (ICME).

[33]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[34]  Srinivasan Jagannathan,et al.  Estimating Precisions for Multiple Binary Classifiers Under Limited Samples , 2020, ECML/PKDD.

[35]  Xiao Liang,et al.  Accurate and Fast Blur Detection Using a Pyramid M-Shaped Deep Neural Network , 2019, IEEE Access.

[36]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .