DUICM Deep Underwater Image Classification Mobdel using Convolutional Neural Networks

被引:10
作者
Aridoss, Manimaran [1 ]
Dhasarathan, Chandramohan [2 ]
Dumka, Ankur [3 ]
Loganathan, Jayakumar [4 ]
机构
[1] Madanapalle Inst Technol & Sci, Dept Comp Applicat, Madanapalle, Andhra Pradesh, India
[2] Madanapalle Inst Technol & Sci, Dept Comp Sci & Engn, Madanapalle, Andhra Pradesh, India
[3] Graph Era Deemed Be Univ, Dehra Dun, Uttarakhand, India
[4] Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci &, Dept Comp Sci, Cognit Radio Spectrum Management Schemes, Morai, Tamil Nadu, India
关键词
Benchmark Turbid Image Dataset; Convolutional Neural Network; Deep Learning; DUCIM; Underwater Image Classification;
D O I
10.4018/IJGHPC.2020070106
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Classification of underwater images is a challenging task due to wavelength-dependent light propagation, absorption, and dispersion distort the visibility of images, which produces low contrast and degraded images in difficult operating environments. Deep learning algorithms are suitable to classify the turbid images, for that softmax activation function used for classification and minimize cross-entropy loss. The proposed deep underwater image classification model (DUICM) uses a convolutional neural network (CNN), a machine learning algorithm, for automatic underwater image classification. It helps to train the image and apply the classification techniques to categorise the turbid images for the selected features from the Benchmark Turbid Image Dataset. The proposed system was trained with several underwater images based on CNN models, which are independent to each sort of underwater image formation. Experimental results show that DUICM provides better classification accuracy against turbid underwater images. The proposed neural network model is validated using turbid images with different characteristics to prove the generalization capabilities.
引用
收藏
页码:88 / 100
页数:13
相关论文
共 23 条
  • [1] [Anonymous], 2017, 2017 IEEE INT C SIGN, DOI DOI 10.1109/ICSPCC.2017.8242527
  • [2] [Anonymous], P 2017 IEEE 56 ANN C
  • [3] [Anonymous], 2016, INT J CONTROL THEORY
  • [4] [Anonymous], 2017, ADV COMPUTATIONAL SC
  • [5] [Anonymous], P AS C MACH LEARN
  • [6] [Anonymous], UNDERWATER IMAGE ENH
  • [7] Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks
    Cha, Young-Jin
    Choi, Wooram
    Buyukozturk, Oral
    [J]. COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2017, 32 (05) : 361 - 378
  • [8] PCANet: A Simple Deep Learning Baseline for Image Classification?
    Chan, Tsung-Han
    Jia, Kui
    Gao, Shenghua
    Lu, Jiwen
    Zeng, Zinan
    Ma, Yi
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (12) : 5017 - 5032
  • [9] Codevilla F., 2004, International journal of computer vision, V60, P91
  • [10] Jin LL, 2017, OCEANS-IEEE