A CNN-OSELM Multi-Layer Fusion Network with Attention Mechanism for Fish Disease Recognition in Aquaculture

• Published in: IEEE access 2023-01, Vol.11, p.1-1
• Main Authors: Huang, Yo-Ping, Khabusi, Simon Peter
• Format: Article
• Language: English
• Subjects: Aquaculture; Artificial neural networks; attention mechanism; Classification; Datasets; Disease; Disease control; Diseases; Extreme learning; extreme learning machines; Feature extraction; Feature maps; Fish; Fish disease; Image quality; Image recognition; Machine learning; Medical imaging; Modules; multilayer fusion; Multilayers; Nonhomogeneous media; Underwater
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3280540

The increasing global population has escalated the demand for fish products necessitating a stable supply. This can only be met through improved aquaculture practices. The automatic recognition of fish diseases from diseased underwater images is one of such practices that aims to control disease, improve fish production and optimize profits. However, due to lack of public fish disease dataset, there has been limited research towards fish disease recognition. Moreover, due to low quality of underwater images and complex underwater environments, traditional hand-designed feature extraction methods or convolutional neural networks (CNNs)-based classifiers cannot adequately recognize fish diseases in real underwater scenes. Therefore, this paper proposes a novel hybrid approach based on multilayer fusion, attention mechanism and online sequential extreme learning machine (OSELM) to recognize fish diseases in aquaculture. Feature extraction is enhanced by integrating same level features and focusing on salient features for fish disease recognition. The characteristic information of fish disease is refined by using strongly discriminative features of the infected fish regions and weakening regions of low interest using convolutional block attention module (CBAM). The module is added to the multilayer fusion network to sequentially infer attention maps along the channel and spatial dimensions for every intermediate feature map. Fish disease recognition is done by using OSELM for faster learning and improving classification performance. The models are trained, validated and tested on a custom dataset with image samples collected from various internet sources. The proposed method achieves 94.28% of accuracy, precision of 92.67%, recall of 92.17% and 92.42% of F1- score with background elimination. The proposed method can be used for fish identification in complex underwater environments in aquaculture.