scholarly journals Pengenalan Motif Batik Pandeglang Menggunakan Deteksi Tepi Canny dan Metode K-NN Berbasis Android

Respati ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. 83
Author(s):  
Rizki Ripai, Imelda
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Computer Technology ◽  
Nearest Neighbor ◽  
Scientific Discipline ◽  
Similar Data ◽  
Simple Arithmetic ◽  
Average Accuracy ◽  
Extraction Test ◽  
Short Time

INTISASIBatik yang merupakan warisan budaya Indonesia telah ditetapkan UNESCO pada tanggal 2 Oktober 2009 sebagai hak kebudayaan intelektual bangsa Indonesia. Kabupaten Pandeglang pada awalnya tidak memiliki tradisi membatik, namun perkembangan dunia pariwisata di KEK Tanjung Lesung Pandeglang, Banten turut mendorong warga sekitar kawasan wisata KEK Pariwisata Tanjung Lesung untuk menampakan geliatnya. Teknologi komputer juga telah berkembang secara pesat, diawali dengan operasi hitung sederhana hingga bisa melakukan pekerjaan dengan waktu yang singkat. Teknologi komputer yang sedang berkembang adalah pengenalan pola. Pengenalan pola merupakan disiplin ilmu untuk mengklasifikasikan atau menggambarkan sesuatu berdasarkan pengukuran kuantitatif fitur (ciri) atau sifat utama dari suatu obyek. Penelitian ini menggunkan deteksi tepi Canny dan metode K-NN yang merupakan sebuah metode untuk melakukan klasifikasi terhadap objek berdasarkan data yang paling mirip (tetangga terdekat) dengan jumlah k yang telah ditentukan dan mengklasifikasikannya ke dalam kelas baru. Berdasarkan hasil pengujian pada ekstraksi ciri HOG dengan k terbaik yaitu k=1 persentase rata–rata accuracy sebesar 72%, Untuk persentase tertinggi yaitu pada batik 4 dan batik 14 dengan nilai persentase yang didapat sebesar 100%. Sedangkan persentase terendah yaitu pada batik 1, batik 5, dan batik 13 dengan nilai persentase yang didapat sebesar 40%. Sedangkan pada pengujian ekstraksi ciri GLCM dengan k terbaik yaitu k=9 mendapatkan nilai akurasi sebesar 85%. Untuk persentase tertinggi yaitu pada batik 1, batik 2, batik 3, batik 4, batik 9 dan batik 14 dengan nilai persentase yang didapat sebesar 100%. Sehingga ekstraksi ciri GLCM lebih baik dari ekstraksi ciri HOG. Kata Kunci : Pola, Batik, Klasifikasi, Canny, dan K-NN.                                                ABSTRACT Batik, which is a cultural heritage of Indonesia, was established by UNESCO on October 2, 2009 as the intellectual property rights of the Indonesian people. Pandeglang Regency initially did not have a batik tradition, but the development of the world of tourism in the Tanjung Lesung SEZ, Pandeglang, Banten helped encourage residents around the tourism area of the Tanjung Lesung SEZ to display their stretching. Computer technology has also developed rapidly, beginning with simple arithmetic operations so that it can do work in a short time. Computer technology that is developing is pattern recognition. Pattern recognition is a scientific discipline to classify or describe something based on quantitative measurements of features or the main characteristics of an object. This research uses Canny edge detection and K-NN method which is a method to classify objects based on the most similar data (nearest neighbor) with a predetermined number of k and classify them into new classes. Based on the results of testing on the extraction of HOG features with the best k is k = 1 percentage average accuracy of 72%, the highest percentage is in batik 4 and batik 14 with a percentage value obtained by 100%. While the lowest percentage is in batik 1, batik 5, and batik 13 with a percentage value of 40%. Whereas in the GLCM feature extraction test with the best k, k = 9 get an accuracy value of 85%. For the highest percentage, namely in batik 1, batik 2, batik 3, batik 4, batik 9 and batik 14 with a percentage value of 100%. So that GLCM feature extraction is better than HOG feature extraction. Keywords: Pattern, Batik, Classification, Canny, and K-NN     

Identification of Authenticity and Nominal Value of Indonesia Banknotes Using Fuzzy KNearest Neighbor Method

2019 ◽  
Vol 6 (1) ◽  
pp. 32-37
Author(s):  
Ricky Ramadhan ◽  
Jayanti Yusmah Sari ◽  
Ika Purwanti Ningrum
Keyword(s):  
Feature Extraction ◽  
Nearest Neighbor ◽  
Threshold Value ◽  
Segmentation Method ◽  
K Nearest Neighbor ◽  
Real Money ◽  
The Public ◽  
Average Accuracy ◽  
Segmentation Methods ◽  
The Government

The existence of counterfeit money is often troubling the public. The solution given by the government to be careful of counterfeit money is by means of 3D (seen, touched and looked at). However, this step has not been perfectly able to distinguish real money and fake money. So there is a need for a system to help detect the authenticity of money. Therefore, in this study a system was designed that can detect the authenticity of rupiah and its nominal value. For data acquisition, this system uses detection boxes, ultraviolet lights and smartphone cameras. As for feature extraction, this system uses segmentation methods. The segmentation method based on the threshold value is used to obtain an invisible ink pattern which is a characteristic of real money along with the nominal value of the money. The feature is then used in the stage of detection of money authenticity using FKNN (Fuzzy K-Nearest Neighbor) method. From 24 test data, obtained an average accuracy of 96%. This shows that the system built can detect the authenticity and nominal value of the rupiah well.

PENENTUAN DAERAH PRIORITAS PELAYANAN AKTA KELAHIRAN DENGAN METODE K-NN DAN K-MEANS

2020 ◽  
Vol 17 (1) ◽  
pp. 319-328
Author(s):  
Ade Muchlis Maulana Anwar ◽  
Prihastuti Harsani ◽  
Aries Maesya
Keyword(s):  
Nearest Neighbor ◽  
Information Gain ◽  
Birth Certificate ◽  
Population Data ◽  
Community Services ◽  
Birth Certificates ◽  
Similar Data ◽  
K Nearest Neighbor ◽  
Civil Registration ◽  
The Family

Population Data is individual data or aggregate data that is structured as a result of Population Registration and Civil Registration activities. Birth Certificate is a Civil Registration Deed as a result of recording the birth event of a baby whose birth is reported to be registered on the Family Card and given a Population Identification Number (NIK) as a basis for obtaining other community services. From the total number of integrated birth certificate reporting for the 2018 Population Administration Information System (SIAK) totaling 570,637 there were 503,946 reported late and only 66,691 were reported publicly. Clustering is a method used to classify data that is similar to others in one group or similar data to other groups. K-Nearest Neighbor is a method for classifying objects based on learning data that is the closest distance to the test data. k-means is a method used to divide a number of objects into groups based on existing categories by looking at the midpoint. In data mining preprocesses, data is cleaned by filling in the blank data with the most dominating data, and selecting attributes using the information gain method. Based on the k-nearest neighbor method to predict delays in reporting and the k-means method to classify priority areas of service with 10,000 birth certificate data on birth certificates in 2019 that have good enough performance to produce predictions with an accuracy of 74.00% and with K = 2 on k-means produces a index davies bouldin of 1,179.

Handwritten Balinesse Character Recognition using K-Nearest Neighbor

2018 ◽  
Author(s):  
I Wayan Agus Surya Darma
Keyword(s):  
Feature Extraction ◽  
Success Rate ◽  
Character Recognition ◽  
Nearest Neighbor ◽  
Recognition System ◽  
Extraction Process ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
K Nearest Neighbor Algorithm ◽  
Character Feature

Balinese character recognition is a technique to recognize feature or pattern of Balinese character. Feature of Balinese character is generated through feature extraction process. This research using handwritten Balinese character. Feature extraction is a process to obtain the feature of character. In this research, feature extraction process generated semantic and direction feature of handwritten Balinese character. Recognition is using K-Nearest Neighbor algorithm to recognize 81 handwritten Balinese character. The feature of Balinese character images tester are compared with reference features. Result of the recognition system with K=3 and reference=10 is achieved a success rate of 97,53%.

Construction of Visual Features of Indonesian Digital Poetry

2017 ◽  
Vol 3 (5) ◽  
pp. 1
Author(s):  
Johan Mahyudi ◽  
Djoko Saryono ◽  
Wahyudi Siswanto ◽  
Yuni Pratiwi
Keyword(s):  
Computer Technology ◽  
Visual Art ◽  
Feature Space ◽  
Digital Art ◽  
Visual Features ◽  
Technology Application ◽  
Digital Poetry ◽  
Textual Space ◽  
Neutral Space ◽  
Short Time

In short time, Indonesian digital poetry attracts its audience through a series of visualization features of the digital art. This research uses a short segment analysis on Indonesian videography digital poetry to demonstrate the existence of visual conglomeration practices through the creation of objects, features, a feature of space, measuring distance in feature space, and dimension reduction. These five approaches are proposed by Manovich (2014) in ​​grouping millions of visual artworks based on simple criteria. Of the three common objects are found, Indonesian animators, prefer individuals and texts as the main impression. The movement features are found in cinematic poetry and its rely depend on kinetic texts. Meanwhile, non-movement features can be found in the form of human imitation or part of them, portraits, silhouettes, and comics. Indonesian digital poetry of space features in form of textual space is prioritizing on the kinetics text, the space of time is prioritizing the presentation of objects association of words are spoken, the neutral space is prioritizing the use of computer technology application. The grouping of visual art composition is based on two criteria: the technique of creating and artistic impressions. The dimensional reducing is prominently practiced by Afrizal Malna.

scholarly journals A Comparative Survey of Feature Extraction and Machine Learning Methods in Diverse Acoustic Environments

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1274
Author(s):  
Daniel Bonet-Solà ◽  
Rosa Ma Alsina-Pagès
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Best Practice ◽  
Nearest Neighbor ◽  
Gaussian Mixture ◽  
Machine Learning Algorithms ◽  
Multimedia Retrieval ◽  
Natural Environments ◽  
K Nearest Neighbor ◽  
Acoustic Environments

Acoustic event detection and analysis has been widely developed in the last few years for its valuable application in monitoring elderly or dependant people, for surveillance issues, for multimedia retrieval, or even for biodiversity metrics in natural environments. For this purpose, sound source identification is a key issue to give a smart technological answer to all the aforementioned applications. Diverse types of sounds and variate environments, together with a number of challenges in terms of application, widen the choice of artificial intelligence algorithm proposal. This paper presents a comparative study on combining several feature extraction algorithms (Mel Frequency Cepstrum Coefficients (MFCC), Gammatone Cepstrum Coefficients (GTCC), and Narrow Band (NB)) with a group of machine learning algorithms (k-Nearest Neighbor (kNN), Neural Networks (NN), and Gaussian Mixture Model (GMM)), tested over five different acoustic environments. This work has the goal of detailing a best practice method and evaluate the reliability of this general-purpose algorithm for all the classes. Preliminary results show that most of the combinations of feature extraction and machine learning present acceptable results in most of the described corpora. Nevertheless, there is a combination that outperforms the others: the use of GTCC together with kNN, and its results are further analyzed for all the corpora.

Sign in / Sign up

Export Citation Format

Share Document