Implementasi Jaringan Syaraf Tiruan Menggunakan Metode Self-Organizing Map Pada Klasifikasi Citra Jenis Ikan Kakap
Implementasi Jaringan Syaraf Tiruan Menggunakan Metode Self-Organizing Map Pada Klasifikasi Citra Jenis Ikan Kakap
复制标题
Implementasi Jaringan Syaraf Tiruan Menggunakan Metode 自组织映射 Pada Klasifikasi Citra Jenis Ikan Kakap
DOI：
10.47065/bits.v4i3.2558
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
R. Nuraini
中科院分区：
文献类型：
--
作者：
R. Nuraini
鲷鱼是最受欢迎的鱼类之一，因为它对人体有无数的好处。笛鲷有很多种类，尤其是经常在印度尼西亚沃茨发现的笛鲷。了解笛鲷的种类是很重要的知识，因为笛鲷有不同的特性，例如有可以食用的笛鲷，也有可以养殖的笛鲷。然而，由于缺乏信息和相似的笛鲷类型，人们很难识别笛鲷的类型。本研究旨在应用自组织映射神经网络（SOM），以颜色与纹理特征为基础，对笛鲷科鱼类进行分类。为了提供关于要分类的笛鲷对象的信息，使用颜色和纹理特征提取。在颜色特征提取中，使用RGB和HSV参数，纹理特征，灰度共生矩阵（GLCM）的方法被应用。此外，所获得的特征结果将使用自组织映射（SOM）算法进行分类，该算法将输入模式划分为某些类别，使得网络输出是与给定输入具有相似性的类别的形式。根据准确性测试的结果，所建立的模型能够产生89.89%的准确性。因此，SOM模型建立的笛鲷物种的图像分类是在良好的类别。
Snapper is one of the favorite fish for consumption because it has a myriad of benefits for the human body. There are many types of snapper, especially snapper which is often found in Indonesian waters. Knowing the types of snapper is important knowledge because snapper has different characteristics, for example there are snapper that can be consumed and there are also types of snapper that can be cultivated. However, the lack of information and similar types of snapper makes it difficult for people to identify the type of snapper. This study aims to implement a Self-Organizing Map (SOM) artificial neural network for classification of snapper species based on color and texture characteristics. In order to provide information about the snapper object to be classified, color and texture feature extraction is used. In color feature extraction, RGB and HSV parameters are used and for texture features, the Gray Level Co-occurrence Matrix (GLCM) approach is applied. Furthermore, the characteristic results obtained will be classified using the Self-Organizing Map (SOM) algorithm which divides the input patterns into certain classes so that the network output is in the form of classes that have similarities to the given input. Based on the results of the accuracy test, the built model is capable of producing an accuracy of 89.89%. Thus, the SOM model built for image classification of snapper species is in the good category.