Fake face detection system for detecting artificially generated or manipulated faces in digital images and videos, has data preprocessing module configured to receive and preprocess input images or video frames
	ARYA A; GUPTA P; CHANDAN; SINGHAL P; KUMAR P; CHOUDHARY P
	2025-03-29
专利权人	KIET GROUP INST (KIET-Non-standard)
申请日期	2025-03-29
专利号	IN202511030602-A
成果简介	NOVELTY - The system has a data preprocessing module configured to receive and preprocess input images or video frames. A feature extraction module extracts facial features and landmarks from preprocessed images or video frames. A deep learning model comprises a Convolutional Neural Network (CNN)trained to classify faces as real or fake based on the extracted features. An output module provides a classification label and a confidence score. The data preprocessing module is configured to resize input images or video frames to a consistent dimension, normalizes pixel values of the input images or video frames and applies data augmentation techniques including one of rotation, flipping, scaling, or adding noise. USE - Fake face detection system for detecting artificially generated or manipulated faces e.g. deepfakes, in digital images and videos. ADVANTAGE - The system provides versatile solution for combating deepfakes and ensures system's ability to evolve and adapt to changing landscape of synthetic media and continuously collects data and periodically retrains CNN, thus monitoring performance metrics and ensuring accuracy. The system uses machine learning and deep learning techniques to enhance security and prevent identity fraud. DESCRIPTION OF DRAWING(S) - The drawing shows a flowchart illustrating operation of a fake face detection system.
IPC 分类号	G06N-003/02 ; G06Q-050/00 ; G06V-010/82 ; G06V-040/40
国家	印度
专业领域	信息技术
语种	英语
成果类型	专利
文献类型	科技成果
条目标识符	http://119.78.100.226:8889/handle/3KE4DYBR/13385
专题	中国科学院新疆生态与地理研究所
作者单位	KIET GROUP INST (KIET-Non-standard)
推荐引用方式 GB/T 7714	ARYA A,GUPTA P,CHANDAN,et al. Fake face detection system for detecting artificially generated or manipulated faces in digital images and videos, has data preprocessing module configured to receive and preprocess input images or video frames. IN202511030602-A[P]. 2025.

条目包含的文件
条目无相关文件。

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。