دانشگاه سمنان

 آمار

تعداد نشریات22
تعداد شماره‌ها712
تعداد مقالات10,258
تعداد مشاهده مقاله72,013,226
تعداد دریافت فایل اصل مقاله63,762,220
Rikhtegar, Arash, Pooyan, Mohammad, Manzuri, Mohammad Taghi. (1399). Comparing performance of metaheuristic algorithms for finding the optimum structure of CNN for face recognition. هنرهای کاربردی, 11(1), 301-319. doi: 10.22075/ijnaa.2020.4296
Arash Rikhtegar; Mohammad Pooyan; Mohammad Taghi Manzuri. "Comparing performance of metaheuristic algorithms for finding the optimum structure of CNN for face recognition". هنرهای کاربردی, 11, 1, 1399, 301-319. doi: 10.22075/ijnaa.2020.4296
Rikhtegar, Arash, Pooyan, Mohammad, Manzuri, Mohammad Taghi. (1399). 'Comparing performance of metaheuristic algorithms for finding the optimum structure of CNN for face recognition', هنرهای کاربردی, 11(1), pp. 301-319. doi: 10.22075/ijnaa.2020.4296
Rikhtegar, Arash, Pooyan, Mohammad, Manzuri, Mohammad Taghi. Comparing performance of metaheuristic algorithms for finding the optimum structure of CNN for face recognition. هنرهای کاربردی, 1399; 11(1): 301-319. doi: 10.22075/ijnaa.2020.4296

Comparing performance of metaheuristic algorithms for finding the optimum structure of CNN for face recognition

International Journal of Nonlinear Analysis and Applications
مقاله 24، دوره 11، شماره 1، تیر 2020، صفحه 301-319    اصل مقاله (2.58 M)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22075/ijnaa.2020.4296
نویسندگان
Arash Rikhtegar1؛ Mohammad Pooyan* 2؛ Mohammad Taghi Manzuri3
1Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
2Engineering faculty, Shahed University, Tehran, Iran
3Computer Engineering Department, Sharif University of Technology, Tehran, Iran
تاریخ دریافت: 26 آذر 1398،  تاریخ بازنگری: 13 بهمن 1398،  تاریخ پذیرش: 02 اسفند 1398 
چکیده
Local and global based methods are two main trends for face recognition. Local approaches extract salient features by processing different parts of the image whereas global approaches find a general template for face of each person. Unfortunately, most global approaches work under controlled environments and they are sensitive to changes in the illumination. On the other hand, local approaches are more robust but finding their optimal parameters is a challenging task. This work proposes a new local-based approach that automatically tunes its parameters. The proposed method incorporates different techniques. In the first step, convolutional neural network (CNN) is employed as a trainable feature extraction procedure. In the second step, different metaheuristic methods are merged with CNN so that its best structure is found automatically. Finally, in the last step the decision is made by employing proper multi-class support vector machine (SVM). In this fashion a fully automated system is developed that is self-tuned and do not need manual adjustments. Simulation results demonstrate efficacy of the proposed method.
کلیدواژه‌ها
Face Recognition؛ Convolutional Neural Network؛ Support Vector Machine؛ Multi-Class Classification؛ Metaheuristic Algorithm
آمار
تعداد مشاهده مقاله: 16,586
تعداد دریافت فایل اصل مقاله: 10,018


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب