Implementation of Naïve Bayes for Fish Freshness Identification Based on
Image Processing
Dublin Core
Title
Implementation of Naïve Bayes for Fish Freshness Identification Based on
Image Processing
Image Processing
Subject
Identification, image, fisheye, naïve bayes, RGB
Description
Consumption of fish as a food requirement for the fulfillment of community nutrition is increasing. This was followed by an
increase in the amount of fish caught that were sold at fish markets. Market managers must be concerned about the dispersion
of huge amounts of fish in the market in order to determine the freshness of the fish before it reaches the hands of consumers.
So far, market managers have relied on traditional ways to determine the freshness of fish in circulation. The issue is that
traditional solutions, such as the use expert assessment, demand a human physique that quickly experiences fatigue.
Technological developments can be a solution to these problems, such as utilizing image processing techniques classification
method. Image processing with the use of color features is an effective method to determine the freshness of fish. The
classification method used in this research is the Naive Bayes method. This study aims to identify the freshness of fish based
on digital images and determine the performance level of the method. The identification process uses the RGB color value
feature of fisheye images. The stages of fish freshness identification include cropping, segmentation, RGB value extraction,
training, and testing. The classification data are 210 RGB value of extraction images which are divided into 147 data for
training and 63 data for testing. The research data were divided into fresh class, started to rot class, and rotted class. The
research shows that the Naive Bayes algorithm can be used in the process of identifying the freshness level of fish based on
fisheye images with a test accuracy rate of 79.37%
increase in the amount of fish caught that were sold at fish markets. Market managers must be concerned about the dispersion
of huge amounts of fish in the market in order to determine the freshness of the fish before it reaches the hands of consumers.
So far, market managers have relied on traditional ways to determine the freshness of fish in circulation. The issue is that
traditional solutions, such as the use expert assessment, demand a human physique that quickly experiences fatigue.
Technological developments can be a solution to these problems, such as utilizing image processing techniques classification
method. Image processing with the use of color features is an effective method to determine the freshness of fish. The
classification method used in this research is the Naive Bayes method. This study aims to identify the freshness of fish based
on digital images and determine the performance level of the method. The identification process uses the RGB color value
feature of fisheye images. The stages of fish freshness identification include cropping, segmentation, RGB value extraction,
training, and testing. The classification data are 210 RGB value of extraction images which are divided into 147 data for
training and 63 data for testing. The research data were divided into fresh class, started to rot class, and rotted class. The
research shows that the Naive Bayes algorithm can be used in the process of identifying the freshness level of fish based on
fisheye images with a test accuracy rate of 79.37%
Creator
Sabarudin Saputra1
, Anton Yudhana2
, Rusydi Umar3
, Anton Yudhana2
, Rusydi Umar3
Publisher
Ahmad Dahlan University
Date
30-06-2022
Contributor
Fajar bagus W
Format
PDF
Language
Indonesia
Type
Text
Files
Collection
Citation
Sabarudin Saputra1
, Anton Yudhana2
, Rusydi Umar3, “Implementation of Naïve Bayes for Fish Freshness Identification Based on
Image Processing,” Repository Horizon University Indonesia, accessed June 4, 2025, https://repository.horizon.ac.id/items/show/9182.
Image Processing,” Repository Horizon University Indonesia, accessed June 4, 2025, https://repository.horizon.ac.id/items/show/9182.