Provide a way to detect manipulated facial images using deep learning techniques

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: Provide a way to detect manipulated facial images using deep learning techniques

ارائه دهنده: Provider: Marziyeh Abdolmaleki

اساتید راهنما: Supervisors: Dr. MirHossein Dezfoulian

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: Dr. Mehdi Abbasi Dr. Reza Mohammadi

زمان و تاریخ ارائه: Time and date of presentation: March 13,2021

مکان ارائه: Place of presentation:

چکیده: Abstract: Advanced and low-cost tools of the digital age have made it possible to easily make and manipulate subtle changes to digital images. This makes it difficult to identify the originality of the image. Therefore, in recent years, researchers in the field of image have proposed various methods to identify manipulated images and separate them from the original images. In recent years, the use of deep learning techniques has been used as the most practical methods in data classification. Convulsive neural networks are one of these techniques. There are many meta-parameters in the design of the convolutional neural network, and changing each of these meta-parameters affects the performance of the model. The proposed model consists of 4 cannulation layers. The results obtained from this model show 96.84% accuracy in a standard data set.

فایل: ّFile: Download فایل