4
views
0
recommends
+1 Recommend
0 collections
    0
    recommends
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Enhanced deep learning models for automatic fish species identification in underwater imagery

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Underwater cameras are crucial in marine ecology, but their data management needs automatic species identification. This study proposes a two-stage deep learning approach. First, the Unsharp Mask Filter (UMF) preprocesses images. Then, an enhanced region-based fully convolutional network (R–FCN) detects fish using two-order integrals for position-sensitive score maps and precise region of interest (PS-Pr-RoI) pooling for accuracy. The second stage integrates ShuffleNetV2 with the Squeeze and Excitation (SE) module, forming the Improved ShuffleNetV2 model, enhancing classification focus. Hyperparameters are optimized with the Enhanced Northern Goshawk Optimization Algorithm (ENGO). The improved R–FCN model achieves 99.94 % accuracy, 99.58 % precision and recall, and a 99.27 % F-measure on the Fish4knowledge dataset. Similarly, the ENGO-based ShuffleNetV2 model, evaluated on the same dataset, shows 99.93 % accuracy, 99.19 % precision, 98.29 % recall, and a 98.71 % F-measure, highlighting its superior classification accuracy.

          Highlights

          • Two-stage deep learning approach using UMF for preprocessing and R-FCN for precise fish detection.

          • Improved ShuffleNetV2 with SE module enhances classification and species identification accuracy.

          • R-FCN model achieved 99.94% accuracy, 99.58% precision, 99.58% recall, and 99.27% F-measure.

          • ENGO-based ShuffleNetV2 achieved 99.93% accuracy, 99.19% precision, 98.29% recall, and 98.71% F-measure.

          • ENGO algorithm optimized hyperparameters, improving precision and overall performance.

          • Research aids sustainable fisheries management and conservation amidst climate change in tropical regions.

          Related collections

          Most cited references42

          • Record: found
          • Abstract: found
          • Article: not found

          Automatic fish detection in underwater videos by a deep neural network-based hybrid motion learning system

          It is interesting to develop effective fish sampling techniques using underwater videos and image processing to automatically estimate and consequently monitor the fish biomass and assemblage in water bodies. Such approaches should be robust against substantial variations in scenes due to poor luminosity, orientation of fish, seabed structures, movement of aquatic plants in the background and image diversity in the shape and texture among fish of different species. Keeping this challenge in mind, we propose a unified approach to detect freely moving fish in unconstrained underwater environments using a Region-Based Convolutional Neural Network, a state-of-the-art machine learning technique used to solve generic object detection and localization problems. To train the neural network, we employ a novel approach to utilize motion information of fish in videos via background subtraction and optical flow, and subsequently combine the outcomes with the raw image to generate fish-dependent candidate regions. We use two benchmark datasets extracted from a large Fish4Knowledge underwater video repository, Complex Scenes dataset and the LifeCLEF 2015 fish dataset to validate the effectiveness of our hybrid approach. We achieve a detection accuracy (F-Score) of 87.44% and 80.02% respectively on these datasets, which advocate the utilization of our approach for fish detection task.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found
            Is Open Access

            Automating the Analysis of Fish Abundance Using Object Detection: Optimizing Animal Ecology With Deep Learning

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Smart deep learning-based approach for non-destructive freshness diagnosis of common carp fish

                Bookmark

                Author and article information

                Contributors
                Journal
                Heliyon
                Heliyon
                Heliyon
                Elsevier
                2405-8440
                27 July 2024
                15 August 2024
                27 July 2024
                : 10
                : 15
                : e35217
                Affiliations
                [a ]Department of CSE, Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad, India
                [b ]Department of Information Technology, MLR Institute of Technology, Hyderabad, India
                [c ]Department of Computer Science and Engineering, Malla Reddy University, Hyderabad, 500043, India
                [d ]Department of Computer Science and Engineering, Lakireddy Bali Reddy College of Engineering, India
                [e ]School of Computer Science and Engineering, VIT-AP University, Vijayawada, 522237, India
                Author notes
                [* ]Corresponding author. v2ramesh634@ 123456gmail.com
                Article
                S2405-8440(24)11248-0 e35217
                10.1016/j.heliyon.2024.e35217
                11336429
                39170344
                9f7b2068-bf9f-4747-9b59-3e7eacda2dd9
                © 2024 The Authors

                This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

                History
                : 22 July 2024
                : 24 July 2024
                Categories
                Research Article

                region-based fully convolutional network,unsharp mask filter,northern goshawk optimization,shufflenet,squeeze and excitation

                Comments

                Comment on this article