Professional Documents
Culture Documents
1
Abstract— Poisonous plants are plants that must be avoided is by second-order feature extraction (d=2) to calculate the
and not consumed by humans, because the presence of probability of the relationship between pixels that have
poisonous plants is also often found in the surrounding exactly the same value as the pixel distance (d) and use
environment without realizing it. Because of the lack of angles of 0°, 45°, 90 °, and 135° [7]. From the results of
knowledge to classify poisonous plant species, it will be extraction with various types of poisonous leaves, for the
more difficult to find out. With the help of a computer classification process using the Neural Network method.
system, it will be easier to identify the types of poisonous
plants. There are 3 types of poisonous plants that will be
used in this study, namely cassava, jatropha, and amethyst. II. THEORETICAL BASIS
There are also 3 types of non-toxic plants with almost the
same morphology as a comparison, namely cassava, figs, and A. Related Research
eggplant. In this study, researchers tried to classify poisonous Related research on poisonous plants, methods Neural
plant species using leaf pattern features that would be Networkand algorithm GLCM consists of:
extracted using shape features and GLCM to take the values 1. The research carried out by Kannika Thongkhao,
of area, width, diameter, perimeter, slender, and round for Chayapol Tungphatthong, Thatree Phadungcharoen,
shape feature attributes. And the value of contrast, entropy, and Suchada Sukrong described the use of DNA
correlation, energy, and homogeneity for GLCM attributes. barcoding in plants with HRM analysis to distinguish
and use the Neural Network to classify a data using the edible vegetables from poisonous plants. Four DNA
RapidMiner application. From this study, it is known that barcodes M. Suavis, S. Androgynus, and U-
from 300 total datasets used, the highest accuracy is 96.13% siamensis (rbcL, matK, ITS2 and psbH trnH) have
using the Neural Network method. With an AUC value of been successfully implemented. Bar-HRM analysis
0.986 and is included in the very good category. and use the based on matK chloroplast gene to differentiate M.
Neural Network to classify a data using the RapidMiner Suasiv and S. Androgynus which can be digested by
application. From this study, it is known that from 300 total U-siamensis toxin proved to be an effective method
datasets used, the highest accuracy is 96.13% using the for species differentiation using different melting
Neural Network method. With an AUC value of 0.986 and is profiles. This strategy may be extended to other
included in the very good category. and use the Neural manufacturers for security issues in order to avoid
Network to classify a data using the RapidMiner application. misidentification of problems [2].
From this study, it is known that from 300 total datasets 2. The approach in this study is to study InceptionV3,
used, the highest accuracy is 96.13% using the Neural VGG16 and Resnet50 which have been applied to
Network method. With an AUC value of 0.986 and is identify fungi based on their categories with 8190
included in the very good category. mushroom images. where the ratio of training and
test data is 8:2. In this study, the Contrast limited
Keywords— Poisonous plants, GLCM, Neural Network. adaptive histogram equalization (CLAHE) and
InceptionV3 methods were used to obtain the highest
test accuracy. A comparison was obtained between
I. INTRODUCTION the contrast-enhanced and non-contrast-enhanced
Poisonous plants are plants that must be avoided and not for methods. with the final result, InceptionV3 has
human consumption, because the presence of poisonous achieved 88.40% accuracy which is the highest
plants is also often found in the surrounding environment accuracy among other implemented algorithms. [4].
without realizing it [1]. There are many types of plants in the 3. The research carried out by Fittria Shofrotun Ni'mah,
environment that can be consumed by humans and animals, T. Sutojo, and De Rosal Ignatius Moses Setiadi
but some plants contain toxins in them [2]. From the many describes the identification of herbal plants. The
types of plants, it makes us less able to distinguish which method adopted in this research is using the KNN
plants contain toxins and which do not [3]. Because of the method. The accuracy of the algorithm in identifying
types of plants that contain toxins and those that are not, and training image data. The accuracy of the
several types of plants tend to have similarities in their algorithm in identifying herbal medicinal plants
morphology [4]. So we need a system that can classify the based on leaf images has an average accuracy of
types of poisonous plants. 83.33% [5].
Along with its development in the world of technology, 4. Research by Mira Musrini, Andriana, and Ari Seisar
researchers use models based on the application of image Hidayat describes the application of cholesterol
textures, because in this way, computers can recognize the detection through the iris with the GLCM and MED
characteristics of a leaf from density, diversity, regularity, algorithms. In this study, the accuracy of the GLCM
and roughness [5]. From this process, it can be seen the value angle (θ) 0 degrees and distance (d) 1 reached a
of the characteristics or characteristics of the leaf pattern value of 70.83%. One of the factors that influence
which will be processed for classification. There are several the success of the study is that not all images can be
models for analyzing image textures, one of which is by processed, there are some eye images whose results
using the GLCM model. cannot be detected by the iris and pupil circles as a
GLCM is a method that is often used as a reference to whole, because the image is taken at a distance that
identify images in texture processing [6]. The accuracy is so close that is less than 17 or even too far ie with
obtained from the GLCM method used for feature extraction a distance of more than 26cm. Testing with the level
2
of light intensity is very influential on the success of
the system by 70.83% [7]. Where :
5. Penelitian yang dilakukan oleh Muhammad Jurnalies lp = leaf length
Habibie yaitu dalam menentukan tanaman beracun Wp = leaf width
dengan cara menggunakan metode jaringan syaraf A = area / leaf area.
tiruan Learning Vector Quantification yaitu dengan
data daun yang sudah didapat nantinya akan 5. Large
ditentukan polanya terlebih dahulu dengan tanda The calculation of the area value is taken from the
ceklis pada beberapa data dari ciri yang sudah number of pixels in an object. Here is the calculation
dimiliki oleh daunnya. Hasil yang didapatkan dari to get the area value.
proses pemilihan pola nantinya berupa informasi
mengenai tanaman beracun, dan gambar berguna
untuk user lebih mudah mengenali tanaman beracun
tersebut [15]. 6. Wide
B. Image Processing Is the longest measure of the line that connects the
Image processing merupakan metode untuk melakukan pixels on the edge of the destination that has a
beberapa operasi pada gambar/ image untuk perpendicular line to the object with the maximum
mendapatkan gambar yang ditingkatkan atau length.
ditransformasikan. Dimana gambar/image menjadi input
deangan gambar lain menjadi output yang ditingkatkan
dengan tehnik dan metode tertentu[8].
Citra digital dapat dianggap sebagai representasi dikrit D. GLCM
dari sebuah data yang keduanya memiliki informasi This algorithm is used as an assessment of the textures
spesial (layout) dan intensitas (warna) [9]. Image contained in the 2nd order. The measured value taken on
Processing cenderung mengarah pada analisis kuantitatif the texture of the 1st order uses a statistical assessment
atau algoritma yang diterapkan pada data citra digital. based on the pixel value of the original image.This model
Image Processing juga semakin canggih serta has at least five attributes in obtaining a value in an
kecenderungannya dalam mengembangkan otomatisasi image. of the five attributes include ASM, Entropy, IDM,
sebanyak mungkin. Contrast, Correlation. There are four angle directions in
GLCM, namely the angle of 0°, 45°, 90°, and 135° [6].
C. Shape Features The GLCM direction used in this study uses an angle of
The extraction used in leaf feature extraction uses six 90°.
types of features, including:
1. Slimness
The slenderness value is taken from the ratio of the
length and width of the leaf.
Where :
lp = leaf length Figure 1. GLCM . angle
wp = leaf width.
2. roundness
The roundness value is taken from the ratio between
the area of the object and the square of the perimeter.
Where :
A = leaf area
P = perimeter of the leaf.
3. Diameter
Diameter is the distance that has the longest size
between two edge points of the object.
3
Signal with vector dimension n T will
4. Entropy
It is a measure of the irregularity of the intensity
distribution. Entropy equation:
Where :
Information :
4
accuracy value of the testing data obtained in the amount of
92.22% with AUC value = 0.989. for accuracy results from
class precision and class recall are in (table 1) and (table 2).
REFERENSI
Figure 11 Figure 12 Figure 13 [1] Zheng, X., An, W., Yao, H., Xu, J., & Chen, S. (2020). Rapid
Original Image Gray Image Binary Image Authentication of the Poisonous Plant Gelsemium elegans by
Combining Filter-Paper-Based DNA Extraction and RPA-LFD
Detection. Engineering. doi:10.1016/j.eng.2020.02.012.
F. Data Set [2] Thongkhao, K., Tungphatthong, C., Phadungcharoen, T., & Sukrong,
Dari fitur bentuk dan GLCM terdapat total 11 atribut, S. (2019). The use of plant DNA barcoding coupled with HRM
diantaranya : Perimeter, Luas, Diameter, Bulat, Ramping, analysis to differentiate edible vegetables from poisonous plants for
dan Lebar yang diambil dari fitur bentuk. Serta ASM, food safety. Food Control, 106896.
doi:10.1016/j.foodcont.2019.106896
Energi, Entropi, Korelasi, dan Kontras yang diambil dari [3] Zahan N, Hasan Z MD, et al. A Deep Learning-Based Approach for
GLCM. Edible, Inedible and Poisonous Mushroom Clasification. ICICT4SD,
2021; doi: 10.1109/ICICT4SD50815.2021.9396845
G. Test [4] Nithanial L., at al. (2021) forensic aplication of DNA barcoding in
The testing phase is carried out using the RapidMiner the identificationn of commonly occurring poisonous plants. Journal
application. The result of this test is to know the value of of Forensic and legal medicine, 2021; doi: Department of Botany,
Bishop Heber College (Autonomous), Tiruchirappalli, Tamil Nadu,
accuracy. The accuracy value obtained from the training data 620017, India
in this trial is 96.19% +/- 4.03% (micro: 96.17%). While the
5
[5] Ni'mah FS., at al. 2018. Identification of Herbal Medicinal Plants
Based on Leaf Image Using Gray Level Co-Occurrence Matrix and
K-Nearest Neighbor Algorithm, doi: 10.14710/jtsiskom.6.2.2018.51-
56
[6] Niampradit., et al. (2018). A method of Thai Main Dish and Shoup
Clasification By Gray Level Co-occurrence Matrix Algorithm,
ISBN : 978-1-5386-2318-3, doi: 10.1109/IEECON.2018.8712294
[7] Musrini, Mira,. Andriana., & Hidayat, Ari S. (2017). Implementation
of the GLCM And Algorithm MED on Cholesterol Detection
Application Through Iris. Mind journals.
DOI :doi.org/10.26760/mindjournal
[8] Solomon, Chris., Breckon, Toby. (2011). Fundamentals of Digital
Image Processing. A John Wiley & Sons, 291, eBook
9780470689783
[9] Yauri-Machaca, M., Meneses-Claudio, B., Vargas-Cuentas, N.,
& Roman-Gonzalez, A. (2018). Design of a Vehicle Driver
Drowsiness Detection System Through Image Processing
using Matlab. 2018 IEEE 38th Central America and Panama
Convention (CONCAPAN
XXXVIII). doi:10.1109/concapan.2018.8596513
[10] Huang, Y., Capretz, L. F., & Ho, D. (2019). Neural Network Models
for Stock Selection Based on Fundamental Analysis. 2019 IEEE
Canadian Conference of Electrical and Computer Engineering
(CCECE). doi:10.1109/ccece.2019.8861550
[11] Moore1 BJ., et al. (2020). Validation of a Convolutional Neural
Network Model for Spike Transformation Using a Generalized Linear
Model. IEEE. 10.1109/EMBC44109.2020.9176458.
[12] Ramdhani, Yudi., et al. (2018). Application of Neural Network
Algorithm for Cardiotocography Classification. Journal of
Informatics, ISSN : 2355-6579
[13] Reghin, D., & Lopes, F. (2019). Value-at-Risk prediction for the
Brazilian stock market: A comparative study between Parametric
Method, Feedforward and LSTM Neural Network. 2019 XLV Latin
American Computing Conference
(CLEI). doi:10.1109/clei47609.2019.235095
[14] Liu, H., Ma, L., Wang, Z., Liu, Y., & Alsaadi, FE (2020). An
Overview of Stability Analysis and State Estimation for Memristive
Neural Networks. Neurocomputing.
doi:10.1016/j.neucom.2020.01.066
[15] Habibie, MJ., (2019). Mengidentifikasi Tanaman Beracun pada Pola
Daun dengan Jaringan Syaraf Tiruan Learning Vector Quantification.
Jurnal JTIK. Doi: 10.35870/jtik.v3i1.47