Word recognition and automated epenthesis removal for Indonesian sign system sentence gestures

نویسندگان

چکیده

This research <span>focuses on building a system to translate continuous Indonesian sign (SIBI) gestures into text. In gesture, signer will add an epenthesis (transitional) which is hand movement with no meaning but needed connect the of one word next in gesture. Reducing number irrelevant inputs model through automated removal can improve system's ability recognize words gestures. We implemented threshold conditional random fields (TCRF) identify The dataset consists 2,255 videos representing 28 common sentences SIBI. translation MobileNetV2 as feature extraction technique, removing found by TCRF, and long short-term memory (LSTM) for classifier. With MobileNetV2-TCRF-bidirectional LSTM model, best error rate (WER) sentence accuracy (SAcc) were 33.4% 16.2%, respectively. Intermediate-stage processing steps consisting sandwiched majority voting TCRF labels whose frames less than two frames, along output grouping, able reduce WER from 3.4% increase SAcc 16.2% 80.2%.</span>

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An Automated System for Indian Sign Language Recognition

Sign Language is a non-verbal communication mode which is used by the people with hearing disabilities, who cannot use voice sounds for communication. Instead, they need signs or actions to express themselves. Normal people are usually unaware of these signs. Therefore, the need of a computer based intelligent system is highly demanding for the dumb community that will enable them significantly...

متن کامل

Novel Technique for Background Removal from Sign Images for Sign Language Recognition System

The Sign Language Recognition (SLR) system involves recognition of signs and their translation into normal spoken language. The hearing and speech impaired people are deeply associated with Sign Language as it is their fundamental medium of communication. Although such people can easily communicate amongst themselves, they face a serious challenge when they try to integrate into the educational...

متن کامل

Word repetitions in sentence recognition.

When some items on a list are strengthened by extra study time or repetitions, recognition of other, unrelated, list items is not harmed (Ratcliff, Clark, & Shiffrin, 1990). Shiffrin, Ratcliff, and Clark (1990) accounted for this list-strength finding with a model assuming that different items are stored separately in memory, but that repetitions are accumulated together into a single stronger ...

متن کامل

Sentence context, word recognition, and repetition blindness.

When the sentence She ran her best time yet in the rice last week is displayed using rapid serial visual presentation, viewers sometimes misread rice as race (M. C. Potter, A. Moryadas, I. Abrams, & A. Noel, 1993). Seven experiments combined misreading and repetition blindness (RB) paradigms to determine whether misreading of a word because of biasing sentence context represents a genuine perce...

متن کامل

MAN-MACHINE INTERACTION SYSTEM FOR SUBJECT INDEPENDENT SIGN LANGUAGE RECOGNITION USING FUZZY HIDDEN MARKOV MODEL

Sign language recognition has spawned more and more interest in human–computer interaction society. The major challenge that SLR recognition faces now is developing methods that will scale well with increasing vocabulary size with a limited set of training data for the signer independent application. The automatic SLR based on hidden Markov models (HMMs) is very sensitive to gesture's shape inf...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Indonesian Journal of Electrical Engineering and Computer Science

سال: 2022

ISSN: ['2502-4752', '2502-4760']

DOI: https://doi.org/10.11591/ijeecs.v26.i3.pp1402-1414