Pengenalan ASL Menggunakan Metode Ekstraksi HOG dan Klasifikasi Random Forest

Bahasa isyarat memiliki banyak jenis salah satunya yaitu American Sign Language (ASL). Pada Penelitian ini digunakan citra handshape alfabet ASL yang diekstraksi menggunakan fitur Histogram of Oriented Gradient (HOG) selanjutnya fitur yang dihasilkan digunakan untuk klasifikasi Random Forest. Hasil pengujian menunjukan bahwa dengan menggunakan fitur HOG dan metode klasifikasi Random Forest untuk pengenalan ASL memberikan tingkat accuracy yang baik, dengan nilai accuracy overall sebesar 99.10%, nilai rata - rata accuracy per class 77.43%, nilai rata - rata precission 88.81%, dan nilai rata - rata recall 88.65% .

Download Full-text

Hand detection in American Sign Language depth data using domain-driven random forest regression

2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG) ◽

10.1109/fg.2015.7163135 ◽

2015 ◽

Cited By ~ 1

Author(s):

Zahoor Zafrulla ◽

Himanshu Sahni ◽

Abdelkareem Bedri ◽

Pavleen Thukral ◽

Thad Starner

Keyword(s):

Random Forest ◽

American Sign Language ◽

Sign Language ◽

American Sign ◽

Hand Detection ◽

Random Forest Regression ◽

Depth Data

Download Full-text

Klasifikasi American Sign Language Menggunakan Ekstraksi Fitur Histogram of Oriented Gradients dan Jaringan Syaraf Tiruan

Jurnal Teknik Informatika dan Sistem Informasi ◽

10.28932/jutisi.v6i3.2844 ◽

2020 ◽

Vol 6 (3) ◽

Author(s):

Muhammad Ezar Al Rivan ◽

Mochammad Trinanda Noviardy

Keyword(s):

American Sign Language ◽

Sign Language ◽

Network Architecture ◽

American Sign ◽

Test Results ◽

Sign Languages ◽

Histogram Of Oriented Gradient ◽

Artificial Neural ◽

Hidden Layer

Sign languages have various types, one of which is American Sign Language (ASL). In this study, ASL images from the handshape alphabet were extracted using Histogram of Oriented Gradient (HOG) then these features were used for the classification of Artificial Neural Networks (ANN) with various training functions using 3 variations of multi-layer network architecture where ANN architecture consists of one hidden layer. Based on ANN training, trainbr test results have a higher success rate than other training functions. In architecture with 15 neurons in the hidden layer get an accuracy value of 99.29%, a precision of 91.84%, and a recall of 91.47%. The test results show that using the HOG feature and ANN classification method for ASL recognition gives a good level of accuracy, with an overall accuracy of 5 neurons 95.38%, 10 neurons 96.64%, and 15 neurons with 97.32%. Keywords— Artificial Neural Network; American Sign Language; Histogram of Oriented Gradient; Training Function

Download Full-text

Pengenalan Alfabet American Sign Language Menggunakan K-Nearest Neighbors Dengan Ekstraksi Fitur Histogram Of Oriented Gradients

Jurnal Teknik Informatika dan Sistem Informasi ◽

10.28932/jutisi.v5i3.1936 ◽

2020 ◽

Vol 5 (3) ◽

Author(s):

Muhammad Ezar Al Rivan ◽

Hafiz Irsyad ◽

Kevin Kevin ◽

Arta Tri Narta

Keyword(s):

American Sign Language ◽

Sign Language ◽

Euclidean Distance ◽

Nearest Neighbor ◽

Manhattan Distance ◽

American Sign ◽

K Nearest Neighbor ◽

K Nearest Neighbors ◽

Histogram Of Oriented Gradient ◽

Chebychev Distance

Sign Language use to communicate to people with dissabilities. American Sign Language (ASL) one of popular sign language. Histogram of Oriented Gradient (HOG) can be use as feature extraction. Then feature stored in database. K-Nearest Neighbor use to measure distance between feature train and feature test. There are three distance use in this paper consist of Euclidean Distance, Manhattan Distance and Chebychev Distance. The best result are 0,99 when using Euclidean Distance and Manhattan Distance with k=3 dan k=5

Download Full-text