TY - GEN
T1 - A novel feature extraction model to enhance underwater image classification
AU - Irfan, Muhammad
AU - Zheng, Jiangbin
AU - Iqbal, Muhammad
AU - Arif, Muhammad Hassan
N1 - Publisher Copyright:
© Springer Nature Switzerland AG 2020.
PY - 2020
Y1 - 2020
N2 - Underwater images often suffer from scattering and color distortion because of underwater light transportation characteristics and water impurities. Presence of such factors make underwater image classification task very challenging. We propose a novel classification convolution autoencoder (CCAE), which can classify large size underwater images with promising accuracy. CCAE is designed as a hybrid network, which combines benefits of unsupervised convolution autoencoder to extract non-trivial features and a classifier, for better classification accuracy. In order to evaluate classification accuracy of proposed network, experiments are conducted on Fish4Knowledge dataset and underwater synsets of benchmark ImageNet dataset. Classification accuracy, precision, recall and f1-score results are compared with state-of-the-art deep convolutional neural network (CNN) methods. Results show that proposed system can accurately classify large-size underwater images with promising accuracy and outperforms state-of-the-art deep CNN methods. With the proposed network, we expect to advance underwater image classification research and its applications in many areas like ocean biology, sea exploration and aquatic robotics.
AB - Underwater images often suffer from scattering and color distortion because of underwater light transportation characteristics and water impurities. Presence of such factors make underwater image classification task very challenging. We propose a novel classification convolution autoencoder (CCAE), which can classify large size underwater images with promising accuracy. CCAE is designed as a hybrid network, which combines benefits of unsupervised convolution autoencoder to extract non-trivial features and a classifier, for better classification accuracy. In order to evaluate classification accuracy of proposed network, experiments are conducted on Fish4Knowledge dataset and underwater synsets of benchmark ImageNet dataset. Classification accuracy, precision, recall and f1-score results are compared with state-of-the-art deep convolutional neural network (CNN) methods. Results show that proposed system can accurately classify large-size underwater images with promising accuracy and outperforms state-of-the-art deep CNN methods. With the proposed network, we expect to advance underwater image classification research and its applications in many areas like ocean biology, sea exploration and aquatic robotics.
KW - Convolutional autoencoder
KW - Convolutional neural network
KW - Deep learning
KW - Underwater images
UR - http://www.scopus.com/inward/record.url?scp=85082479495&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-43364-2_8
DO - 10.1007/978-3-030-43364-2_8
M3 - 会议稿件
AN - SCOPUS:85082479495
SN - 9783030433635
T3 - Communications in Computer and Information Science
SP - 78
EP - 91
BT - Intelligent Computing Systems - 3rd International Symposium, ISICS 2020, Proceedings
A2 - Brito-Loeza, Carlos
A2 - Espinosa-Romero, Arturo
A2 - Martin-Gonzalez, Anabel
A2 - Safi, Asad
PB - Springer
T2 - 3rd International Symposium on Intelligent Computing Systems, ISICS 2020
Y2 - 18 March 2020 through 19 March 2020
ER -