Gesture recognition for Indonesian Sign Language (BISINDO)

Handhika, Tri; Zen, Revaldo Ilfestra Metzi; Murni, Murni; Lestari, Dewi; Sari, Ilmiyati

doi:10.1088/1742-6596/1028/1/012173

Cited by 28 publications

(26 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This movement is slightly different from BISINDO [27] and considerably different from SIBI [28]. The main difference is that the Quantum Maki movement does not only use hand movements, but also other limb movements in particular circumstances.…”

Section: A the Sign Movement Of Quantum Makimentioning

confidence: 83%

A Hybrid Background Subtraction and Artificial Neural Networks for Movement Recognition in Memorizing Quran

Prabuwono¹,

Maula²,

Usino³

et al. 2018

ijacsa

View full text Add to dashboard Cite

Movement change beyond the duration of time and the variations of object appearance becomes an interesting topic for research in computer vision. Object behavior can be recognized through movement change on video. During the recognition of object behavior, the target and the trace of an object in a video must be determined in the sequence of frames. To date, the existence of object on a video has been widely used in different areas such as supervision, robotics, agriculture, health, sports, education, and traffic. This research focuses on the field of education by recognizing the movement of Quantum Maki Quran memorization through a video. The purpose of this study is to enhance the existing computer vision technique in detecting the Quantum Maki Quran memorization movement on a video. It combines the Background Subtraction method and Artificial Neural Networks; and evaluates the combination to optimize the system accuracy. Background Subtraction is used as object detection method and Back propagation in Artificial Neural Networks is used as object classification. Nine videos are obtained by three different volunteers. These nine videos are divided into six training and three testing data. The experimental result shows that the percentage of accuracy system is 91.67%. It can be concluded that there are several factors influencing the accuracy, such as video capturing factors, video improvements, the models, feature extraction and parameter definitions during the Artificial Neural Networks training.

show abstract

Section: A the Sign Movement Of Quantum Makimentioning

confidence: 83%

A Hybrid Background Subtraction and Artificial Neural Networks for Movement Recognition in Memorizing Quran

Prabuwono¹,

Maula²,

Usino³

et al. 2018

ijacsa

View full text Add to dashboard Cite

show abstract

“…The first model was using 3 blocks of 3D-CNN, then the second was using one block of 3D-CNN, the third model was using eight blocks of CNN and last was using 2 blocks of B-RNN by using SIBI as objects. The result was by calculating the average of WER (Word Error Rate) equal to 88,79% and CER (Character Error Rate) equal to 65.33% [5]. According to table 1, CNN, and LSTM were the best combinations to sign language by using such as kind of object sign language.…”

Section: Methodsmentioning

confidence: 99%

“…Moreover, some research already studied this topic such as Leap Motion Controller (LMC), and HMM (Hidden Markov Model) vision base approach dan Microsoft Kinect dataset [3], [4]. For example, by using HMM and BISINDO object, the experiment got around 60% of accuracy [5]. It is because of how complex this system is.…”

Section: Introductionmentioning

confidence: 99%

BISINDO (Bahasa Isyarat Indonesia) Sign Language Recognition Using CNN and LSTM

Aljabar¹,

Suharjito²

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Sign language is one of the languages which are used to communicate with deaf people. By using it, they can communicate and understand each other. In Indonesia, there are two standards of sign language which are SIBI (Sistem Bahasa Isyarat) and BISINDO (Bahasa Isyarat Indonesia). Deep learning is a model that is used to apply to this topic. In this model, there are a lot of methods such as convolutional neural network, recurrent neural network, long-sort term memory, and each model has its characteristics. There are also some issues in deep learning by sign language recognition as the object such as data training, object position, pose, lighting, and the background of objects. This research will describe how to combine background subtraction and gaussian blur pre-processing, forwarding preprocessing background subtraction with CNN by using BISINDO, LSTM, and a combination between CNN and LSTM. In conclusion, this research shows that a combination between CNN and LSTM is the best model by explaining the accuracy and testing with sign language BISINDO as the object. The accuracy showed that for CNN 96%, LSTM 86%, and combination CNN and LSTM 96%, and the loss showed that for CNN 18%, LSTM 41%, and combination CNN and LSTM 17%.

show abstract

“…In dataset collection, there are two type of dataset that is used in the studies, which are vision-based data and sensor-based data. Sensor-based data need additional equipment which is used to get more accurate feature to be used in the researches, like Kinect [3]- [6], Leap Motion [4], Myo Armband [7]. On the other hand, vision-based data consists of video which is used as an input in sign language recognition to make it easier to be implemented.…”

Section: A Dataset Collectionmentioning

confidence: 99%

“…It is caused by the availability of many public dataset which could be used for sign language recognition, the development of computer vision field which lead to more accurate features, and the improvement of artificial intelligence field especially on machine learning and deep learning. With this development, there are researchers that review these studies to make it easier to be compared and improved [1][2].While the result is indeed improved, the improvement of vision-based recognition is still far behind sensor-based recognition because sensor-based recognition gives far more accurate feature using additional equipment like Kinect [3]- [6], Leap motion [4], and Myo armband [7]. Consequently, vision-based recognition remains as a distant solution for actual application.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Modified Hidden Markov Model for Vision-Based Indonesian Sign Languages Recognition

Suharjito*,

Gunawan,

Thiracitta

2020

IJRTE

View full text Add to dashboard Cite

Sign language is one of the most popular language which is used as a communication bridge that depends on hand movement. As it is used worldwide, the variety of sign languages is very large and most of the people doesn’t understand it which makes the communication between deaf and normal people interrupted. This makes sign language recognition popular as it makes people doesn’t need to understand the sign but still understand the meaning of the sign. But sign language itself has many problems such as the possibility of different dataset has the same movement but different meaning, the method used of each dataset could be ineffective in other dataset, and many other else which makes it difficult to be implemented. Other than that, vision-based recognition is not as popular as sensor-based recognition because of the difference in feature accuracy even though it could give more area of improvement. That’s why the aim of this paper is to presents the combination of methods used to recognize vision-based Indonesian Sign Language and enhance the method using optimization technique. The methodology used in this study follows four steps framework of sign language recognition which is dataset collection, preprocessing, feature extraction, and recognition. Each method is improved in order to be compared and checked what is the method combination and optimization method is the best for sign language recognition. For dataset collection, the dataset that is used is formal Indonesian Sign Language which is called Sistem Isyarat Bahasa Indonesia (SIBI) with some constraint in order to make sure the quality of the dataset is good. The preprocessing methods are differentiated into two categories which is image enhancement and hand detection. Image enhancement methods include no image enhancement, Gaussian blur, Bilateral blur, and Contrast Limited Adaptive Histogram Equalization and hand detection methods include skin detection using YCbCr color space and edge detection using Canny algorithm. Feature that is used in this study is pair of left and right-side movement for each frame that is extracted by calculating the average value of each pixels from left and right-side image that could be a representative value of each frame. Lastly the recognition system that is used is Gaussian Hidden Markov Model and its’ state optimization which includes no optimization, Latin Hypercube optimization, Hill Climbing optimization, and Combination of Latin Hypercube and Hill Climbing optimization. The experiment result of the proposed method could recognize up to 82% accuracy rate. The improvement of this research could be implemented on

show abstract

Gesture recognition for Indonesian Sign Language (BISINDO)

Cited by 28 publications

References 8 publications

A Hybrid Background Subtraction and Artificial Neural Networks for Movement Recognition in Memorizing Quran

A Hybrid Background Subtraction and Artificial Neural Networks for Movement Recognition in Memorizing Quran

BISINDO (Bahasa Isyarat Indonesia) Sign Language Recognition Using CNN and LSTM

Optimization of Modified Hidden Markov Model for Vision-Based Indonesian Sign Languages Recognition

Contact Info

Product

Resources

About