Claim Missing Document
Check
Articles

Found 6 Documents
Search

Penerapan Savitzky Golay Filter Pada Citra Hiperspektral Dari Buah Kelapa Sawit Anand, Barri; Candra, Feri; Shiddiq, Minarni
Jurnal Online Mahasiswa (JOM) Bidang Teknik dan Sains Vol 8 (2021): Edisi 1 Januari s/d Juni 2021
Publisher : Jurnal Online Mahasiswa (JOM) Bidang Teknik dan Sains

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research is entitled Application of SG Filter to Hyperspectral Image of Palm Fruit Head. This research is motivated by one of the biggest sources of livelihood for the Indonesian people, namely oil palm plantations. In measuring the maturity level of oil palm fruit in the next process, there is an obstacle in the form of hyperspectral data having a lot of noise. As a result of the large amount of noise, the hyperspectral image is not good. The impact is that the hyperspectral image cannot be processed and a program is implemented to overcome the maturity level of the palm fruit. The purpose of this study is to provide a solution to the problem of the amount of noise in a hyperspectral image, thus making the hyperspectral image smoother. The solution is to use SG Filter with the help of MATLAB software. The stages of this research began with literature study, data collection, method application, comparison of results, and conclusions. This study uses the SG filter to smooth the data with the help of the MATLAB program. The result of this research is a hyperspectral image model which is smoother without much noise. Keywords: Savitzky Golay Filter, MATLAB, Hyperspectral Imaging, Normalisasi
Multispectral imaging and deep learning for oil palm fruit bunch ripeness detection Shiddiq, Minarni; Saktioto, Saktioto; Salambue, Roni; Wardana, Fiqra; Dasta, Vicky Vernando; Harmailil, Ihsan Okta; Rabin, Mohammed Fisal; Arpyanti, Nisa; Wahyudi, Dilham
Bulletin of Electrical Engineering and Informatics Vol 13, No 6: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i6.8120

Abstract

Oil palm fresh fruit bunches (FFBs) are the raw material of crude palm oil (CPO) on which ripeness levels of FFBs are essential to obtain good quality CPO. Most palm oil mills use experienced graders to evaluate FFB ripeness levels. Researchers have developed rapid and non-destructive methods for ripeness detection using computer vision (CV) and deep learning. However, most of the experiments used color cameras, such as a webcam or a smartphone, limited to visible wavelengths, and used still FFBs on–trees or on the ground. This study developed a light-emitting diode (LED)-based multispectral imaging system with deep learning for rapid and real-time ripeness detection of oil palm FFBs on a moving conveyor. The ripeness levels used were unripe and ripe. We also evaluated the spectrum of reflectance intensities for the ripeness levels. The ripeness detection system employed a two-class you only look once version 4 (YOLOv4) detection model using a dataset of 2000 annotated unripe and ripe FFB multispectral images and a video of 30 moving FFBs for real-time testing. The results show a promising method to detect oil palm FFB ripeness with an average accuracy of 99.66% and a speed range of 3.32-3.62 frame per second (FPS).
Wavelength dependence of optical electronic nose for ripeness detection of oil palm fresh fruits Husein, Ikhsan Rahman; Shiddiq, Minarni; Sari, Dewi Laila; Putri, Annisa
Science, Technology and Communication Journal Vol. 2 No. 3 (2022): SINTECHCOM Journal (June 2022)
Publisher : Lembaga Studi Pendidikan and Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v2i3.212

Abstract

Electronic noses have been developed as an artificial sense to imitate the human nose based on volatile gases. They have been used in agriculture to monitor and predict fruit qualities such as ripeness and chemical contents. Electronic noses with semiconductor gas sensors have a limitation of volatile gases detected. Therefore, optical electronic noses using an output coupler become an alternative due to the wavelength dependency of the gas types. The ripeness of oil palm fresh fruit bunches (FFBs) is one of the main factors in determining the quality of crude palm oil. Electronic detection is preferable to substitute the manual methods for ripeness detection. This study built an optical electronic nose and analyzed the wavelength dependence on the detection performance. The electronic nose consisted of an infrared LED and a photodiode enclosed in a chamber, a microcontroller, and a sample chamber. We tested four infrared LEDs with 760, 780, 840, and 910 nm wavelengths. The samples were fruitlets taken from oil palm FFBs, previously categorized as unripe, ripe, and overripe. The fruits were grounded, inserted into the sample chamber, and preheated to increase the volatile gas concentration.  Trapezoid areas represented the time-varying output voltages for each LED. The results showed that overripe fruits had slightly higher trapezoid areas. LED of 840 nm wavelength obtained higher trapezoid areas. LED of 780 nm was the best candidate for the electronic nose due to linearity in increasing trapezoid areas. The results showed the potential of the optical electronic nose for oil palm fruits.
Fluorescence spectrum analysis on leaf and fruit using the ImageJ software application Defrianto, Defrianto; Shiddiq, Minarni; Malik, Usman; Asyana, Vepy
Science, Technology and Communication Journal Vol. 3 No. 1 (2022): SINTECHCOM Journal (October 2022)
Publisher : Lembaga Studi Pendidikan and Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v3i1.218

Abstract

In this study, ImageJ has been used to process fluorescence spectroscopic images of spinach leaf treated with three variations of sunlight. In addition, apples and tomatoes are also used in imaging by treatment immersed in hot water, pierced, and pressed. Leaf and fruits are illuminated by laser diodes and LEDs of different wavelengths. ImageJ is used to calculate the RGB and gray values of the image with two segmentations, namely the intact image and the threshold. The results show that the thresholding method gives the best results because it automatically reduces the image background. In addition, the threshold background can also be easily set in this imaging. For the spinach leaf experiment, LED with a wavelength of 680 nm showed significant differences in each treatment of sunlight intensity. Meanwhile, in the apple and tomato experiment, the diode laser with a wavelength of 405 nm showed significant results. Both types of fruit with this puncture treatment turned out to provide higher intensity than pressed fruit.
Imaging and Programming Based Computation of Logistic Package Volumes Application on Automatic Mail Machines Prayitno, Adhy; Shiddiq, Minarni; Arief, Dodi Sofyan; Mirdanies, Midriem; Ayunita, Dyna
Journal of Ocean, Mechanical and Aerospace -science and engineering- Vol 62 No 1 (2018): Journal of Ocean, Mechanical and Aerospace -science and engineering- (JOMAse)
Publisher : International Society of Ocean, Mechanical and Aerospace -scientists and engineers- (ISOMAse)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (511.287 KB) | DOI: 10.36842/jomase.v62i1.150

Abstract

At present the determination of weight and volume has been widely used to assist in the process of determining costs for freight forwarding services. Shipping costs are determined by the weight of the goods, but the weight of the goods consists of two types, namely actual weight and volume weight. The weight of the weighing will be used directly if the item or box is small, but if the item is large but the weight is real then the weight of the volume will be used. Algorithms that combine triangulation and 2D measurement techniques can be used to build 3D surfaces so they can measure the volume of a product. Determination of volume in the optical scoring system can be done using the laser triangulation method and the area of 2D image measurement, then using a computer algorithm to get the results of 3D images to determine the volume of the object. The calculation process used in this study uses MATLAB software. MATLAB is the most efficient software for matrix-based numerical calculations and is widely used in mathematical calculations, development and algorithms, programming modeling, prototyping and simulation, data analysis, exploration and visualization, numerical and statistical analysis, and technical application development. The results of the study using MATLAB include students becoming more interested in learning and more independent in learning mathematics, can visualize data graphically to help analyze the data analyzed, and help in modeling the characteristics of variations in fuel mixtures which include density, viscosity, dynamic and kinematic viscosity.
Relation of reflectance intensity and chemical contents of oil palm fresh fruit bunches using multispectral imaging Arpyanti, Nisa; Shiddiq, Minarni; Setiadi, Rahmondia Nanda; Rabin, Mohammad Fisal; Harmailil, Ihsan Okta; Dasta, Vicky Vernando
Indonesian Physics Communication Vol 22, No 2 (2025)
Publisher : Universitas Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31258/jkfi.22.2.149-156

Abstract

Multispectral imaging has been widely used for the classification of fruits and vegetables. This technique offers both spectral and spatial resolution, enabling the evaluation of fruit quality based on its chemical properties. This study aims to analyze the relationship between reflectance intensity obtained from multispectral imaging and the chemical composition of oil palm fresh fruit bunches (FFBs), specifically oil content and free fatty acid (FFA) levels, measured using the Soxhlet extraction method. The multispectral imaging system consists of a monochrome camera and an LED light source with eight wavelengths ranging from 680 nm to 900 nm. FFB images were processed using Python scripts to extract reflectance intensity. The Python scripts were also used to analyze the correlation between reflectance intensity and both oil content and FFA levels. A total of 15 unripe and 15 ripe FFB samples were used. Correlation analysis was focused on the 780 nm wavelength due to its high reflectance intensity. The results showed that the correlation coefficient between reflectance intensity and oil content was r = -0.39 for unripe fruits and r = 0.29 for ripe fruits, while the combined data yielded a strong correlation of r = 0.92. For FFA, the correlation was r = -0.41 for unripe fruits, r = -0.34 for ripe fruits, and r = 0.72 for the combined dataset. These findings demonstrate that multispectral imaging is a promising non-destructive method for classifying the ripeness of oil palm FFBs based on oil content and FFA levels.