Issn 2091-5446 ilmiy axborotnoma научный вестник scientific journal
Download 1.19 Mb. Pdf ko'rish
|
ilovepdf merged
- Bu sahifa navigatsiya:
- ILMIY AXBOROTNOMA INFORMATIKA 2021 - yil, 1 - son
Ключевые слова: SIFT, распознавание узбекского жестового языка, SVM, k-NN, LDA,
классификация. Introduction For thousands of years, sign languages are the default communication languages between deaf people. These languages have been used to successfully teach generations of deaf children. However, a ILMIY AXBOROTNOMA INFORMATIKA 2021 - yil, 1 - son 108 communication gap between deaf and nondeaf people is obvious. This is because the normal people find it difficult to learn and comprehend sign languages [1–3]. A sign language is a collection of gestures, movements, postures, and facial expressions corresponding to letters and words in natural languages. So, there should be a way for the non-deaf people to recognize the deaf language (i.e. sign language). Such process is known as a sign language recognition. The aim of the sign language recognition is to provide an accurate and convenient mechanism to transcribe sign gestures into meaningful text or speech so that communication between deaf and hearing society can easily be made. To achieve this aim, many proposal attempts are designed to make fully automated systems or Human Computer Interaction(HCI) to facilitate interaction between deaf and non-deaf individuals [1, 4]. The sign language recognition is mainly based on gesture recognition. There are two main categories for gesture recognition glove-based systems and vision-based systems. – Glove-based systems: In these systems, electromechanical devices are used to collect data about deaf’s gestures. With this systems, the deaf person should wear a wired glove connected to a number of sensors to collect the gestures of the person’s hand. So, such gestures can be recognized through a computer interface. This way gives a good result but it is inconvenient because the user must always carry wired sensors (gloves) and this is not natural way to communicate between deaf and non-deaf people [4]. – Vision-based systems: These systems make image processing and machine learning techniques to identify, recognize and interpret hand gestures. Such system can overcome the inconvenience problem of gloved-based systems as there is no need for the deaf users to wear any electromechanical devices. In other words, vision-based systems are more flexible to use [4]. Download 1.19 Mb. Do'stlaringiz bilan baham: |
Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©fayllar.org 2024
ma'muriyatiga murojaat qiling
ma'muriyatiga murojaat qiling