NHN has been granted a patent for a system and method using convolutional neural networks to detect image forgery, especially in compressed or color images. The system enhances features, extracts manipulated information, refines features, and classifies manipulation, providing a detailed forgery confirmation map. GlobalData’s report on NHN gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on NHN, Video game monitoring was a key innovation area identified from patents. NHN's grant share as of January 2024 was 19%. Grant share is based on the ratio of number of grants to total number of patents.
Image forgery detection system using convolutional neural network
A recently granted patent (Publication Number: US11861816B2) discloses a system and method for detecting image forgery using a convolutional neural network. The system includes processors and memory storing executable instructions to apply an input image to a high-pass filter, extract manipulated feature information using a pre-trained convolutional neural network, refine the information, determine image forgery based on manipulated features, and output an image forgery confirmation map displaying probability values of manipulated pixels. The system can process input images into blocks, extract features using convolutional and pooling layers, and utilize a Visual Geometry Group (VGG) 19 convolutional neural network model for feature extraction. The system can detect various types of image alterations such as Gaussian blurring, noise, filtering, and resampling.
Additionally, the method for detecting image forgery involves receiving an input image, applying a high-pass filter, extracting manipulated features through a pre-trained convolutional neural network, refining the information, determining image forgery based on manipulated features, and outputting a forgery confirmation map displaying probability values of manipulated pixels. The method can process images into blocks, utilize a pre-trained VGG19 convolutional neural network model, and handle color images. It also includes deep learning of the forgery confirmation map, highlighting areas with high forgery probability, displaying forgery type information, and confirming the absence of forgery with a stamp image. The method provides a comprehensive approach to detecting image forgery by analyzing manipulated features and probabilities within the input image.
To know more about GlobalData’s detailed insights on NHN, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
