Abstract
Segmentation is an important aspect of translating finger spelling of sign language into Latin alphabets. Although the sign language devices that are currently available can translate the finger spelling into alphabets, there is a limitation where the output is stored in a long continuous string without spaces between words. The system proposed in this work is meant to be used together with a text-generating glove device. The system used text input string and the string is then fed into the system, one character at a time, and then it is segmented into words that is semantically correct. The proposed text segmentation method in this work is by using the dynamic programming and back-off algorithm, together with the probability score using word matching with an English language text corpus. Based on the results, the system is able to properly segment words with acceptable accuracy. ABSTRAK: Segmentasi adalah aspek penting dalam menterjemahkan ejaan bahasa isyarat ke dalam huruf Latin. Walaupun terdapat peranti bahasa isyarat yang menterjemahkan ejaan jari menjadi huruf, namun begitu, huruf-huruf yang dihasilkan disimpan dalam rentetan berterusan yang panjang tanpa jarak antara setiap perkataan. Sistem yang dicadangkan di dalam jurnal ini akan diselaraskan bersama dengan sarung tangan bahasa isyarat yang boleh menghasilkan teks. Sistem ini akan mengambil rentetan input teks di mana huruf akan dimasukkan satu persatu dan huruf-huruf itu akan disegmentasikan menjadi perkataan yang betul secara semantik. Kaedah pembahagian yang dicadangkan ialah segmentasi yang menggunakan pengaturcaraan dinamik dan kaedah kebarangkalian untuk mengsegmentasikan huruf-huruf tersebut berdasarkan padanan perkataan dengan pengkalan data di dalam Bahasa Inggeris. Berdasarkan hasil yang telah diperolehi, sistem ini berjaya mengsegmentasikan huruf-huruf tersebut dengan berkesan dan tepat.
Highlights
Sign language is the main language used by deaf people around the world
There are a number of segmentation systems proposed using different approaches and algorithms to improve the accuracy of the output due to the challenges faced in many areas such as language translation and spelling correction
Segmentation Algorithm There are some steps involved in implementing the word segmentation system, which involves the division of characters into possible words and matching the words with the words contained in the text corpus
Summary
Sign language is the main language used by deaf people around the world. there is always a gap between them and people without disability, since communication is a problem between them. One of the biggest challenges in making a sign language device is the segmentation issue [1] This issue is faced differently based on the types of input for the device. A glove-type device that can produce character output based on hand signs is being researched. It is not working properly as it faces the text segmentation issue. There are a number of segmentation systems proposed using different approaches and algorithms to improve the accuracy of the output due to the challenges faced in many areas such as language translation and spelling correction. Proposed a model that performs segmentation at syllable boundaries using vowel offset point (VOP) identification and zero-crossing rate (ZCR) technique
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
