Adaptive gesture recognition based on human physical characteristic

Ikram, K.; Khairunizam, Wan; Aziz, Azri A.; Bakar, Shahriman Abu; Razlan, Z. M.; Zunaidi, I.; Hazry, D.

doi:10.1109/cspa.2018.8368699

Cited by 4 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The geometrical shapes gesture is shown in Figure 2 and is presented in (1). Qualisys Track Manager System (QTM) [19] was used in the experiments. Ten (10) subjects were chosen to perform the gestures with the repetition of 10 trials for each.…”

Section: Geometrical Shape Gesturementioning

confidence: 99%

Analysis of attribute domain for geometrical gesture performed by arm movements

Khairunizam

Ikram

Halim

et al. 2019

IJEECS

Self Cite

View full text Add to dashboard Cite

<span>Hand gesture recognition commonly uses a camera to track hand movements and transformed into gesture database by using various computational approaches. Motion tracking utilized to map coordinate point of the subject movement, either in skeletal model or marker tracing. Data from motion trackers usually contains massive coordinate sequences of marker movement. A reliable method is required to select best features and analyze these data. However, the current issue whether the selected features and data presentation are significant for the research or not. This research brings the concept of ontology design for arm gesture recognition systems by utilizing the motion capture system. Ontology is the conceptual structure mainly used to retrieve information by establishing relation in complex data model. The proposed ontology framework is divided into three domains which are knowledge domain, attribute domain and process domain. Knowledge domain holds pre-processed gestural data from motion capture. The attribute domain is that the level where all the attribute elements were presented. This paper shows the analysis of the datasets in attribute domain. The analysis is divided into two parts which is precision measure and ANOVA test. Both analyses are to prove the reliability of datasets in attribute domain. The precision measure is used to remove all the common data for all gesture. A statistical analysis of p-value is lower than 0.01 which means the gestural data are statistically significant to be used for the similarity measure.</span>

show abstract

Section: Geometrical Shape Gesturementioning

confidence: 99%

Analysis of attribute domain for geometrical gesture performed by arm movements

Khairunizam

Ikram

Halim

et al. 2019

IJEECS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kekurangan dari penelitian yang pernah dilaksanakan sebelumnya diketahui bahwa belum adanya jumlah dan variasi dataset pada neural network agar prediksi neural network dapat menjadi lebih baik, juga perlu pengembangan proses segmentasi dalam menghilangkan background dibelakang objek dapat dihasilkan output yang lebih baik, dan mencoba pengujian lainnya agar mendapat model yang lebih baik lagi sehingga bisa membangun pengembangan lanjut (Aljabar & Suharjito, 2020;Ikram et al, 2018).…”

unclassified

Pengembangan Deteksi Realtime untuk Bahasa Isyarat Indonesia dengan Menggunakan Metode Deep Learning Long Short Term Memory dan Convolutional Neural Network

Altiarika,

Sari

2023

JTIK

View full text Add to dashboard Cite

Kehadiran Computer Vision mampu mempengaruhi bidang kajian Sign Language Recognition System (SLRS). Adapun penelitian dibidang SLRS terhadap dua standar bahasa isyarat di Indonesia yaitu standar SIBI (Sistem Bahasa Isyarat Indonesia) dan BISINDO (Bahasa Isyarat Indonesia). Tantangan dalam penelitian ini adalah kendala dalam memproses gambar dinamis dan gambar statis ketika setelah melalui preprocessing rekognisi. Perlakuan yang berbeda saat recognisi awal pada gambar bergerak dengan gambar statis mempengaruhi waktu memunculkan hasil dengan cepat sehingga dibutuhkan model dengan training yang baik dan cepat. Tujuan penelitian ini adalah untuk mengetahui faktor akurasi yang mempengaruhi tingkat akurasi penerapan objek deteksi dan klasifikasi gambar maupun video secara realtime untuk BISINDO (Bahasa Isyarat Indonesia) dengan menggunakan metode Deep Learning Long Short Term Memory (LSTM) dan Convolution Neural Network (CNN). Pentingnya penelitian ini karena hasilnya dapat dijadikan dasar untuk mempercepat pengembangan lebih lanjut aplikasi sign language recognition khusus untuk BISINDO yang bisa dimanfaatkan oleh penyandang disabilitas maupun masyarakat agar komunikasi dua arah lebih mudah dilakukan dimasa depan secara real-time.

show abstract