Towards Underwater Image Enhancement Using Super-Resolution Convolutional Neural Networks

Underwater objects detection and recognition is challenging because of the degradation of underwater images, such as color casts, blurring and low contrast. To tackle this problem, a novel underwater image enhancement method is proposed. It consists of two main steps. First, an adaptive color correction algorithm is used to compensate color casts and produce natural color corrected images. Second, a super-resolution convolutional neural network is applied to color corrected images in order to remove blurring. The proposed network learns a relationship which can be employed into image de-blurring from a large amount of blurry images and the corresponding clear images. Based on the relationship, the color corrected image will be de-blurred and sharpened. The experimental results show that the proposed strategy improves the quality of underwater images efficiently and arrives at good results in underwater objects detection and recognition.

[1]  Runmin Cong,et al.  Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior , 2016, IEEE Transactions on Image Processing.

[2]  Nor Ashidi Mat Isa,et al.  Enhancement of low quality underwater image through integrated global and local contrast correction , 2015, Appl. Soft Comput..

[3]  Dacheng Tao,et al.  DehazeNet: An End-to-End System for Single Image Haze Removal , 2016, IEEE Transactions on Image Processing.

[4]  Raimondo Schettini,et al.  Underwater Image Processing: State of the Art of Restoration and Image Enhancement Methods , 2010, EURASIP J. Adv. Signal Process..

[5]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Patricia Ladret,et al.  The blur effect: perception and estimation with a new no-reference perceptual blur metric , 2007, Electronic Imaging.

[7]  Codruta O. Ancuti,et al.  Enhancing underwater images and videos by fusion , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Jun Zhang,et al.  Review on underwater image restoration and enhancement algorithms , 2015, ICIMCS '15.

[9]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Jian Sun,et al.  Single image haze removal using dark channel prior , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  M. S. Hitam,et al.  Mixture contrast limited adaptive histogram equalization for underwater image enhancement , 2013, 2013 International Conference on Computer Applications Technology (ICCAT).

[12]  Yafei Wang,et al.  Fusion-based underwater image enhancement by wavelet decomposition , 2017, 2017 IEEE International Conference on Industrial Technology (ICIT).

[13]  Zhou Wang,et al.  A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images , 2015, IEEE Signal Processing Letters.

[14]  Uwe von Lukas,et al.  Learning-based underwater image enhancement with adaptive color mapping , 2015, 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA).

[15]  Krista A. Ehinger,et al.  SUN Database: Exploring a Large Collection of Scene Categories , 2014, International Journal of Computer Vision.

[16]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.