ANovel Method for Eye Blink Recognition Based on Image Processing and Artificial Neural Networks

  • سال انتشار: 1395
  • محل انتشار: اولین کنفرانس بین المللی چشم انداز های نو در مهندسی برق و کامپیوتر
  • کد COI اختصاصی: NPECE01_361
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 702
دانلود فایل این مقاله

نویسندگان

Seyyed Amir Ziafati Bagherzadeh

Department of Biomedical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

Alireza Noei Sarcheshmeh

Department of Biomedical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran

Seyyed Hassan Ziafati Bagherzadeh

Department of Electrical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

Seyyed Ehsan Tahami

Department of Biomedical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

چکیده

Eye blink recognition is widely useful in many applications, such as human-computer interface,driver awareness detection, and so on. Artificial Neural networks (ANNs) are used in image processing and classifications. In this paper a new algorithm proposed which takes RGB image as input containing a face that will recognize using a conventional face recognition method. Then an image enhancement algorithm will apply to specified face region to prepare it for eye region detection. The next step is find the eyes location which implemented using proposed image processing approach. The obtained region will extract from the original image and convert to YCbCr color space to use as input for our MLP classifier. In this study an eye blinking recognition algorithm using image processing and MLP neuralnetwork has proposed including image processing method which finds the eyes regions and the ANN classifier to define whether the eyes are open or close. Moreover the proposed method can recognize winking by recognizing the blinking for each eye separately. The obtained recognition results show that this approach significantly outperforms recognition using proposed algorithm. For selected images from the CAS-PEAL face database, the averaged recognition accuracy is about 86%

کلیدواژه ها

blink recognition; image processing; artificial neural network; multi-layer perceptron

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.