تم إصدار العدد الأول من المجلد الواحد والعشرون لعام 2024 حيث تضمن
بحوث ضمن مجالات مختلفة، تجده عبر أعداد المجلة المجلد الواحد والعشرون - العدد الأول.
آخر موعد لإستقبال الأبحاث:
10 /05/ 2024 م
موعد النشر للعدد القادم:
15 / 05 / 2024 م
لا يتم نشر الاوراق العلمية الا بعد موافقة المشاركين في تأليفها
لاي نقاش حول موضوع بحث يجب الاتصال مباشره بالمؤلفين الموقعين ادناه
By: Imad Mohammed Elsayid Abdalla.
Assistant professor.
Chief of General Programs - CDC, College of Information Technology and Computer Science,
University of Holy Quran and Islamic Science - Sudan.
سنة النشر: 2021 – 2022 م
Abstract
The science of reading lip movements is processing significantly, such as getting to know character, sentences, phrases from lip movements, the problem of the research is how to convert User Lip Movements (ULM) to Voice Command (VC), and the camera used in interaction must accelerate the speeds of taking pictures to control of continuous taking of ULM and tongue, also the confusion system in discrimination any ULM or overlap one picture into another picture, the research objective convert the ULM to VC, The methodology of research is descript the ULM system and VC in ULM Treatment System (ULMTT), and collected data for analysis phase as dataset, in practical used python to build the model through Viola-Jones Algorithm, and deep neural networks, we follow “DETPCA” converter model in research, the result of research through the processing ULM we have alternatives picture for each different ULM, a certain ULM can be displayed for the user to choose the correct ones as a helping process for user in interactive system, we build converter Model of ULM to product Speech.
تحميل الملف