Classification of facial expressions using SVM and HOG

Tanjung, Juliansyah Putra; Muhathir, Muhathir

doi:10.31289/jite.v3i2.3182

Cited by 13 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Cara kerja HOG adalah dengan menghitung nilai gradient dari suatu daerah tertentu dari gambar. Setiap gambar memiliki gambar karateristik yang di tunjukkan oleh gradient nilai yang diperoleh dengan membagi suatu citra menjadi wilayah terkecil yang disebut sel (Girsang & Muhathir, 2021) (Tanjung & Muhathir, 2020).…”

Section: B Histogram Of Oriented Gradientunclassified

Identification of Pneumonia using The K-Nearest Neighbors Method using HOG Fitur Feature Extraction

Khairina

Sibarani

Muliono³

et al. 2022

JITE

Self Cite

View full text Add to dashboard Cite

Pneumonia is a wet lung disease. Pneumonia is generally caused by viruses, bacteria or fungi. Not infrequently Pneumonia can cause death. The K-Nearest Neighbors method is a classification method that uses the majority value from the closest k value category. At this time people are not too worried about pneumonia because this pneumonia has symptoms like a normal cough. However, fast and accurate information from health experts is also very necessary so that pneumonia symptoms can be recognized early and how to deal with them can also be done faster. In this study, researchers will diagnose pneumonia to obtain information quickly about the symptoms of pneumonia. This information will adopt human knowledge into computers designed to solve the problem of identifying pneumonia. In this study, the K-Nearest Neighbors method will be combined with the HOG Extraction Feature to identify pneumonia more accurately. The KNN classification used is Fine KNN, Cosine KNN, and Cubic KNN. Where will be seen how the value of accuracy, precision, recall, and fi-score. The results showed that the classification could run well on the Fine KKN, Cosine KNN, and Cubic KNN methods. Fine KNN has an accuracy rate of 80.67, Cosine KNN has an accuracy rate of 84,93333, and Cubic KNN has an accuracy rate of 83,13333. Fine KNN has precision, recall and f1-score values of 0.794842, 0.923706, and 0.854442. Cosine KNN has precision, recall and f1-score values of 0.803048, 0.954039, and 0.872056. Cubic KNN has precision, recall and f1-score values of 0.73388, 0.964561, and 0.833555. From the test results, positive and negative identification of pneumonia was found to be more accurate with the Cosine KNN classification which reached 84,93333.

show abstract

Section: B Histogram Of Oriented Gradientunclassified

Identification of Pneumonia using The K-Nearest Neighbors Method using HOG Fitur Feature Extraction

Khairina

Sibarani

Muliono³

et al. 2022

JITE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Arsitektur yang dibangun dalam penelitian ini diilustrasikan pada gambar 1 Gambar 1. Arsitektur Penelitian (Muhathir et al, 2019) (Tanjung & Muhathir, 2020) Gambar 1 Mengilustrasikan arsitektur penelitian secara umum, dalam arsitektur tersebut terdapat proses pelatihan dan proses pengujian, pada proses pelatihan citra inputan berwarna akan diubah menjadi citra keabuan untuk menghemat waktu komputasi dari tiga kanal warna menjadi 1 kanal warna, proses pembentukan grid 8 akan dilakukan pada citra keabuan sebagai dasar untuk mendeteksi stronglest feature yang terdapat pada citra wajah autis, setelah pemebentukan grid 8 pada citra dilanjutkan dengan pendeteksian stronglest feature yang ditandai dengan blob warna hijau pada citra, hasil pendeteksian stronglest feature akan di ekstraksi dengan menggunakan Histogram of Oriented Gradient (HoG) serta hasil ekstraksi akan di simpan dalam Bag of Visual Words sebagai model pola. Sedangkan pada proses pengujian melalui tahapan yang sama dengan tahapan yang dilewati pada saat pelatihan, hanya saja ketika pada tahapan ekstraksi HoG perolehan bobotnya akan diklasifikasi dengan menggunakan metode Naïve Bayes.…”

Section: A Arsitektur Penelitianunclassified

Image Classification of Autism Spectrum Disorder Children Using NaÃ¯ve Bayes Method With Hog Feature Extraction

Muhathir

Muliono

Hafni

2022

JITE

Self Cite

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD) is a developmental disorder that affects a person's ability to communicate and interact socially. Every year, the number of people diagnosed with Autism Spectrum Disorder rises, necessitating early detection in order to limit the number of people affected and provide proper treatment. As a result, a system was developed in this study to detect Autism Spectrum Disorder in facial photos utilizing versions of the Nave Bayes approach and HoG feature extraction. HoG feature extraction is a local intensity gradient distribution or edge direction perpendicular to the gradient direction without influencing the geometric and photometric transformations, and Nave Bayes is a method that classifies images based on probability. The experimental results of three types of naive Bayes, Bernoulli naive Bayes is the most reliable than Multinomial naive Bayes and Gaussian Naive Bayes. Accuracy, Precision, Recall, and the highest F1-Score using this method, with each value of 89.72%; 90.54%; 89.72%; and 89.9%. The next best performing Gaussian Naive Bayes, the most laborious results were obtained using Naive Bayes multinomials, which had Accuracy, Precision, Recall, and F1-Score of 65.91% each; 68.09%; 65.91%, and 64.19%.

show abstract

“…Oleh karena itu, SVM telah diterapkan dalam berbagai tugas klasifikasi (M. Wang & Chen, 2020). Algoritma SVM awalnya diusulkan untuk membangun sebuah pengklasifikasi linier pada tahun 1963 oleh Vapnik (Ahmad et al, 2018) (Tanjung & Muhathir, 2020). Penggunaan alternatif untuk SVM adalah metode kernel, yang memungkinkan kita untuk model dimensi yang lebih tinggi, non-linear model.…”

Section: Support Vector Machine (Svm)unclassified

Wayang Image Classification Using SVM Method and GLCM Feature Extraction

Muhathir

Santoso²,

Larasati³

2021

JITE

Self Cite

View full text Add to dashboard Cite

Wayang is a masterpiece of art that has been able to survive centuries of change and development as a reflection of life for the majority of society. Wayang has a high value because it does not only function as a "entertainment" spectacle, but also has many lessons and life values that can be learned from a wayang show. Puppet itself has various types and forms, and these forms have their own uniqueness, because of the many types of Puppet, many people do not know all the names and types of wayang. Therefore, in this research, we will discuss how to recognize wayang objects based on wayang images using the SVM and GLCM methods as feature extraction. The results showed that the classification of wayang using the SVM (Support Vector Machine) method and the GLCM (Gray Level Co-Occurrence Matrix) feature extraction can recognize wayang objects based on wayang images and classify them quite accurately and a maximum total accuracy of 83.2% is obtained.

show abstract

Classification of facial expressions using SVM and HOG

Cited by 13 publications

References 0 publications

Identification of Pneumonia using The K-Nearest Neighbors Method using HOG Fitur Feature Extraction

Identification of Pneumonia using The K-Nearest Neighbors Method using HOG Fitur Feature Extraction

Image Classification of Autism Spectrum Disorder Children Using NaÃ¯ve Bayes Method With Hog Feature Extraction

Wayang Image Classification Using SVM Method and GLCM Feature Extraction

Contact Info

Product

Resources

About