Processing

Please wait...

Settings

Settings

Goto Application

1. CN109598231 - Video watermark identification method, device and equipment and storage medium

Office China
Application Number 201811465129.4
Application Date 03.12.2018
Publication Number 109598231
Publication Date 09.04.2019
Publication Kind A
IPC
G06K 9/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/46
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
G06K 9/62
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
H04N 21/8358
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
21Selective content distribution, e.g. interactive television or video on demand
80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
83Generation or processing of protective or descriptive data associated with content; Content structuring
835Generation of protective data, e.g. certificates
8358involving watermark
CPC
G06K 9/00718
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
00711Recognising video content, e.g. extracting audiovisual features from movies, extracting representative key-frames, discriminating news vs. sport content
00718Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
G06K 9/00744
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
00711Recognising video content, e.g. extracting audiovisual features from movies, extracting representative key-frames, discriminating news vs. sport content
00744Extracting features from the video content, e.g. video "fingerprints", or characteristics, e.g. by automatic extraction of representative shots or key frames
G06K 9/4642
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
4642by performing operations within image blocks or by using histograms
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6277
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
6277based on a parametric (probabilistic) model, e.g. based on Neyman-Pearson lemma, likelihood ratio, Receiver Operating Characteristic [ROC] curve plotting a False Acceptance Rate [FAR] versus a False Reject Rate [FRR]
G06K 2209/21
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
2209Indexing scheme relating to methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
21Target detection
Applicants GUANGZHOU BIGO INFORMATION TECHNOLOGY CO., LTD.
广州市百果园信息技术有限公司
Inventors ZOU YU
邹昱
YANG XUAN
杨轩
LIU ZHENQIANG
刘振强
PAN YUE
潘跃
LI ZHEN
李振
Agents 北京品源专利代理有限公司 11332
Title
(EN) Video watermark identification method, device and equipment and storage medium
(ZH) 一种视频水印的识别方法、装置、设备及存储介质
Abstract
(EN)
The invention discloses a video watermark identification method and device, equipment and a storage medium. The method comprises the following steps: dividing a video frame in a video into two or morethan two image blocks to obtain an image sequence of each video frame; Inputting the image sequence of each video frame into a target detection model to obtain a classification result of each image block, and obtaining a video feature vector according to the classification result of each image block; And inputting the video feature vector into a watermark recognition model, and if the obtained watermark recognition probability is greater than or equal to a probability threshold, determining that the video contains the watermark. According to the embodiment of the invention, each image block is input into the target detection model; a watermark identification result of each video frame is obtained; According to the video watermark identification method and device, the watermark identification result of each video frame is input into the watermark identification model to obtain the watermark identification result of the video, and due to the fact that the watermark identification resultof each video frame is utilized, when the watermark position is not fixed, whether the video contains the watermark can still be accurately identified, and the identification precision of the video watermark is improved.

(ZH)
本发明公开了一种视频水印的识别方法、装置、设备及存储介质。该方法包括:将视频中的视频帧划分为两个或两个以上的图像块,得到各视频帧的图像序列;将各视频帧的图像序列输入至目标检测模型,得到各图像块的分类结果,并根据各图像块的分类结果得到视频特征向量;将视频特征向量输入至水印识别模型,得到的水印识别概率大于等于概率阈值,则确定所述视频包含水印。本发明实施例将各图像块输入至目标检测模型中,得到各视频帧的水印识别结果,将各视频帧的水印识别结果输入至水印识别模型中得到视频的水印识别结果,由于利用了各视频帧的水印识别结果,因此,当水印位置不固定时,仍可准确识别视频中是否包含水印,提高了视频水印的识别精度。

Also published as