Comparison of Recognition Accuracy on Dynamic Hand Gesture Using Feature Selection

Sooai, Adri Gabriel; Batarius, Patrisius; Siki, Yovinia Carmeneja Hoar; Nani, Paskalis Andrianus; Mamulak, Natalia Magdalena R.; Ngaga, Emerensiana; Rosiani, Ulla Delfana; Sumpeno, Surya; Purnomo, Mauridhi Hery; Mau, Sisilia Daeng Bakka

doi:10.1109/cenim.2018.8711397

Cited by 11 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bunga memiliki bentuk dan warna yang beragam sehingga dibutuhkan solusi yang dapat digunakan untuk pengembangan pembelajaran mesin. Agar mendapatkan hasil aplikasi pendeteksi jenis warna bunga lantana camara yang baik, maka dibutuhkan pemodelan warna terlatih dengan tingkat akurasi yang harus dinaikkan dengan cara melewati proses pengenalan pola yang baik, dikarenakan hal ini sangat penting dan mendasar dalam computer vision [8].…”

Section: Pendahuluanunclassified

Pemodelan Warna Pada Dataset Baru Citra Bunga Lantana Camara Menggunakan Algoritma Yolov5

Putu Sugiati Keraf,

Aristo Jansen Sinlae,

Batarius

2024

Mnemonic

View full text Add to dashboard Cite

Lantana camara merupakan salah satu tumbuhan tropis invasif yang berpotensi sebagai tanaman hias yang memiliki keunikan pada kelopak bunga berwarna-warni dan dapat diklasifikasikan menjadi beberapa jenis warna. Meskipun demikian tumbuhan ini dapat ditemukan di pekarangan rumah dan pengetahuan masyarakat tentang tumbuhan ini terkait manfaat khususnya masih terbatas. Selain itu, proses identifikasi warna pada bunga lantana camara dalam produksi massal masih sulit dan memakan waktu serta pemilihan warna secara manual dapat menyebabkan kelelahan pada mata manusia. Oleh karena itu, diperlukan solusi yang memanfaatkan computer vision, seperti penerapan algoritma YOLOv5 untuk pemodelan warna. Metode yang digunakan melibatkan pengumpulan data berupa citra gambar bunga lantana sebanyak 1266 citra yang terbagi dalam 6 jenis warna (merah, putih, kuning, jingga, ungu, merah muda), penyimpanan data berupa citra gambar lantana dilakukan anotasi dan penyesuaian ukuran piksel, pelatihan data dilakukan pada citra gambar yang sudah dianotasi dan ukurannya sama untuk mendapatkan dataset menggunakan roboflow dan google collab, dan evaluasi model untuk mendapatkan hasil prediksi berdasarkan putaran pelatihan sebanyak 50 epoch dan membutuhkan waktu selama 0.483 jam. Hasil yang diperoleh berupa nilai persentase precision sebesar 95%, recall sebesar 99%, dan nilai MAP sebesar 99%, sehingga nilai rata-rata akurasinya di atas 90%. Berdasarkan hasil tersebut penelitian ini berhasil menghasilkan model pada dataset citra bunga lantana camara dengan rata-rata parameter teruji mencapai 90%.

show abstract

Section: Pendahuluanunclassified

Pemodelan Warna Pada Dataset Baru Citra Bunga Lantana Camara Menggunakan Algoritma Yolov5

Putu Sugiati Keraf,

Aristo Jansen Sinlae,

Batarius

2024

Mnemonic

View full text Add to dashboard Cite

show abstract

“…In addition to direct tools for data acquisition, the participant's ergonomics in recording data was also prepared, which aims to provide comfort and reduce student's stress levels in doing cursive handwriting. This ergonomic determination is following the model developed by [21].…”

Section: Experiments Scenariomentioning

confidence: 99%

Two Stages Outlier Removal as Pre-processing Digitizer Data on Fine Motor Skills (FMS) Classification Using Covariance Estimator and Isolation Forest

Fanani¹

2021

IJIES

View full text Add to dashboard Cite

The increase of the classification accuracy level has become an important problem in machine learning especially in diverse data-set that contain the outlier data. In the data stream or the data from sensor readings that produce large data, it allows a lot of noise to occur. It makes the performance of the machine learning model is disrupted or even decreased. Therefore, clean data from noise is needed to obtain good accuracy and to improve the performance of the machine learning model. This research proposes a two-stages for detecting and removing outlier data by using the covariance estimator and isolation forest methods as pre-processing in the classification process to determine fine motor skill (FMS). The dataset was generated from the process of recording data directly during cursive writing by using a digitizer. The data included the relative position of the stylus on the digitizer board. x position, y position, z position, and pressure values are then used as features in the classification process. In the process of observation and recording, the generated data was very huge so some of them produce the outlier data. From the experimental results that have been implemented, the level of accuracy in the FMS classification process increases between 0.5-1% by using the Random Forest classifier after the detection and outlier removal by using covariance estimator and isolation forest. The highest accuracy rate achieves 98.05% compared to the accuracy without outlier removal, which is only about 97.3%.

show abstract

“…Four microexpression classes were used for all experiments (disgust, happiness, surprise, and sadness) via a multi-classification approach. The motion feature from the POC-ABS feature extraction method is recognized using Supports Vector Machine (SVM)[ [35] with Radial Base Function (RBF) [6] and K-Nearest Neighbor (KNN) with Euclidean distance metric [36]. In this study, ten-fold crossvalidation was used to train and test all samples of each class.…”

Section: Micro-expression Classificationmentioning

confidence: 99%

A Novel Approach on Motion Estimation for Micro-Expression Recognition Using Phase Only Correlation with All Block Search (POC-ABS)

Rosiani¹,

Choirina²,

Muna³

et al. 2020

IJIES

Self Cite

View full text Add to dashboard Cite

Micro-expression is an expression when a person tries to held or hidden, but the leak of this emotion still occurs in one or two areas of the face or maybe a short expression that across in the whole-face. Not more than 500ms, micro-expressions can be difficult to recognize and detect where the leakage area is located. This study presents a new method to recognize and detect the subtle motion on the facial components area using Phase Only Correlation algorithm with All Block Search (POC-ABS) to estimate the motion of all block areas. This block matching method is proposed by comparing each block in the two frames to determine whether there is movement or not. If the two blocks are identical, then the motion vector value is not displayed, whereas if the blocks are non-identical, the motion vector value of the POC is displayed. The motion vector, which is as a motion feature, estimates whether or not there are movements in the same block. In order to further confirm the reliability of the proposed method, two different classifiers were used for the micro-expression recognition of the CASME II dataset. The highest performance results are for SVM at 94.3 percent and for KNN at 95.6 percent. Finally, this algorithm detects leaks of motion based on the ratio of the motion vectors. The left and right eyebrows are dominant when expressing disgust, sadness, and surprise. Meanwhile, the movements of the right eye and left eye were the most dominant when the happiness expression.

show abstract

Comparison of Recognition Accuracy on Dynamic Hand Gesture Using Feature Selection

Cited by 11 publications

References 20 publications

Pemodelan Warna Pada Dataset Baru Citra Bunga Lantana Camara Menggunakan Algoritma Yolov5

Pemodelan Warna Pada Dataset Baru Citra Bunga Lantana Camara Menggunakan Algoritma Yolov5

Two Stages Outlier Removal as Pre-processing Digitizer Data on Fine Motor Skills (FMS) Classification Using Covariance Estimator and Isolation Forest

A Novel Approach on Motion Estimation for Micro-Expression Recognition Using Phase Only Correlation with All Block Search (POC-ABS)

Contact Info

Product

Resources

About