Automatic classification of the phenotype textures of three Thunnus species based on the machine learning SVM algorithm

Abstract

Tuna resources are an important part of China’s pelagic fishery production. However, for China’s tuna fishery, tuna species caught at sea are still manually classified, which is a time-consuming and inefficient process, so China’s tuna fishery needs to develop towards automation. This study uses GLCM (gray level co-occurrence matrix) and VGG16 to visualize phenotypic texture through local images of three Thunnus species. At the same time, texture feature index data (TFD), deep feature data (DFD) and their combined feature data (CFD) are obtained from texture images. SVM with different kernel functions is used to classify phenotypic texture of tuna automatically. The study shows that visualized texture images of different tuna using GLCM and VGG16 have biological characteristics. In the classification results without cross-validation, the average classification accuracy of TFD in polynomial was 83%, the average classification accuracy of DFD in RBF was 93%, and the average classification accuracy of CFD in RBF was 95%. It is concluded that tuna phenotype texture can be efficiently classified by using SVM with different kernel functions.

Fish Freshness Detection Through Artificial Intelligence Approaches: A Comprehensive Study

“…In experimental evaluations, they reported that they achieved a high performance of 98.8% with ANN (Kaya et al, 2017). Ou et al (2023) proposed a two-stage study to identify the species of tuna caught in the high seas of China. In the first stage, morphological expressions were obtained from images using VGG16 and GLCM model.…”

“…In the first stage, morphological expressions were obtained from images using VGG16 and GLCM model. Afterwards experimental evaluations were made with the SVM machine learning algorithm and as a result, they reported that they achieved a high performance of 95% in classifying the species of tuna (Ou et al, 2023). Lanjewar and Panchbhai (2023) balanced two merged but highly imbalanced datasets from Kaggle using SMOTEENN and Random Under Sampler methods.…”

Research on Measuring the Bodies of Underwater Fish with Inclined Positions Using the YOLOv8 Model and a Line-Laser System

“…Two-dimensional methods can be subdivided into out-of-water and underwater techniques. In the examination of 2D measurements of fish out of water, Ou Liguo et al [11] utilized computer vision technology to determine the positions of key points on tuna specimens. They conducted automated measurements of the pixel length of morphological features for three tuna species and calculated their actual lengths.…”

Fusing Local Shallow Features and Global Deep Features to Identify Beaks

“…CNN is the most prominent deep learning method in which the multiple layers are trained and tested robustly. In recent years, deep learning has been broadly applied in various domains [ 22 ], since it autonomously extracts image features for image recognition [ 23 , 24 ]. Deep features are high-level feature representations that are learned from original image data by deeply learned models.…”