C3 Effective features inspired from Ventral and dorsal stream ofvisual cortex for view independent face recognition

  • سال انتشار: 1395
  • محل انتشار: مجله بین المللی پیشرفت در علوم کامپیوتر، دوره: 5، شماره: 1
  • کد COI اختصاصی: JR_ACSIJ-5-1_001
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 382
دانلود فایل این مقاله

نویسندگان

Somayeh Saraf Esmaili

Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University,Tehran, Iran.

Keivan Maghooli

Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University,Tehran, Iran.

Ali Motie Nasrabadi

Department of Biomedical Engineering, Faculty of Engineering, Shahed University,Tehran, Iran.

چکیده

This paper presents a model for view independent recognitionusing features biologically inspired from dorsal and ventralstream of visual cortex. The presented model is based on the C3features inspired from Ventral stream and Itti s visual attentionmodel inspired from the dorsal stream of visual cortex. The C3features, which are based on the higher layer of the HMAX of theventral stream of visual cortex, are modified to extract importantfeatures from faces in various viewpoints. By Itti s visualattention model, visual attention points are detected from faces invarious views of faces. Effective features are extracted fromthese visual attention points and the view independent C3effective features (C3EFs) are created from faces. These C3EFsare used to distinct multi-classes of different subjects in variousviews of faces. The presented model is tested using FERET facedatasets with faces in various views of faces, and compared withC2 features (C2SMFs) and C3 features of standard HMAX model(C3SMFs). The results illustrated that our presented viewindependent face recognition model has high accuracy and speedin comparison with standard model features, and can recognizefaces in various views by 97% accuracy.

کلیدواژه ها

view independent face recognition, HMAX model, Itti s visual attention model, C3 effective features, ventral stream, dorsal stream

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.