An audio fingerprint is extracted from an audio sample, where the fingerprint contains information that is characteristic of the content in the sample. The fingerprint may be generated by computing an energy spectrum for the audio sample, resampling the energy spectrum logarithmically in the time dimension, transforming the resampled energy spectrum to produce a series of feature vectors, and computing the fingerprint using differential coding of the feature vectors. The generated fingerprint can be compared to a set of reference fingerprints in a database to identify the original audio content.

Extraction and matching of characteristic fingerprints from audio signals

A digitally encoded video fingerprinting system for generating and comparing/matching fingerprints from digitally encoded video which has been encoded according to an encoding method which involves the generation of residual macroblocks of pixels and the generation of quantized transform coefficients of the residual macroblocks, or of portions of the residual macroblocks, comprises a fingerprint database (5) and a video processing subsystem (10). The video processing subsystem (10) includes a fingerprint sequence selection module (14, 24) which is operable to select one or more sets of frames from input video content to be processed in order to generate a fingerprint; a fingerprint calculation module (14, 26) which is operable to generate a fingerprint based on a set of frames selected by the fingerprint sequence selection module; and a fingerprint comparator module (14, 28) which is operable to compare two fingerprints and to output a similarity score of the compared fingerprints. The method used by the fingerprint selection and fingerprint calculation modules includes selecting a group of frames of the encoded video content; processing the digitally encoded video content to obtain a set of quantized transform coefficients of residual macroblocks or portions of residual macroblocks associated with each of the selected frames; identifying a set of residual macroblocks per frame whose transform coefficients satisfy a threshold criterion; and generating a digital video fingerprint for the encoded video content in dependence upon the identified macroblocks or some property thereof within each of the selected frames.

Digital video fingerprinting

Region duplication is one of the most common methods of video forgery. Existing forgery detection algorithms generally suffer from inefficiency and are not effective for the forged regions with mirroring. To address these problems, we present a fast forgery detection algorithm based on Exponential-Fourier moments (EFMs) for detecting region duplication in videos. The algorithm first extracts EFMs features from each block in the current frame, and performs a fast match to find potential matching pairs. Then, a postverification scheme is designed to eliminate falsely matched pairs and locate the altered regions in the current frame. Finally, an adaptive parameter-based fast compression tracking algorithm is used to track the tampered regions in the subsequent frames. The experimental results show that our proposed algorithm has higher detection accuracy and computational efficiency than those of previous algorithms.

A Fast Forgery Detection Algorithm Based on Exponential-Fourier Moments for Video Region Duplication

In a Content Distribution Network (CDN), there are m servers storing the data; each of them has a specific bandwidth. All the requests from a particular client should be assigned to one server because of the routing protocol used. The goal is to minimize the total cost of these assignments—cost of each is proportional to the distance between the client and the server as well as the request size—while the load on each server is kept below its bandwidth limit. When each server also has a setup cost, this is an unsplittable hard-capacitated facility location problem. As much attention as facility location problems have received, there has been no nontrivial approximation algorithm when we have hard capacities (i.e., there can only be one copy of each facility whose capacity cannot be violated) and demands are unsplittable (i.e., all the demand from a client has to be assigned to a single facility). We observe it is NP-hard to approximate the cost to within any bounded factor in this case. Thus, for an arbitrary constant e>0, we relax the capacities to a 1+e factor. For the case where capacities are almost uniform, we give a bicriteria O(log n, 1+e)-approximation algorithm for general metrics and a (1+e, 1+e)-approximation algorithm for tree metrics. A bicriteria (α,β)-approximation algorithm produces a solution of cost at most α times the optimum, while violating the capacities by no more than a β factor. We can get the same guarantees for nonuniform capacities if we allow quasipolynomial running time. In our algorithm, some clients guess the facility they are assigned to, and facilities decide the size of the clients they serve. A straightforward approach results in exponential running time. When costs do not satisfy metricity, we show that a 1.5 violation of capacities is necessary to obtain any approximation.It is worth noting that our results generalize bin packing (zero connection costs and facility costs equal to one), knapsack (single facility with all costs being zero), minimum makespan scheduling for related machines (all connection costs being zero), and some facility location problems.

Assignment problem in content distribution networks: Unsplittable hard-capacitated facility location

As an increasing amount of crime takes on a digital aspect, law enforcement bodies must tackle an online environment generating huge volumes of data. With manual inspections becoming increasingly infeasible, law enforcement bodies are optimising online investigations through data-mining technologies. Such technologies must be well designed and rigorously grounded, yet no survey of the online data-mining literature exists which examines their techniques, applications and rigour. This article remedies this gap through a systematic mapping study describing online data-mining literature which visibly targets law enforcement applications, using evidence-based practices in survey making to produce a replicable analysis which can be methodologically examined for deficiencies.

/pdf/a-systematic-survey-of-online-data-mining-technology-1cwmh0kw0y.pdf

A Systematic Survey of Online Data Mining Technology Intended for Law Enforcement

The invention discloses a content-based video copy monitoring method and a device, and aims to solve the problem of higher consumption for content-based video copy monitoring resources. The method comprises the following steps: extracting a portion of video frames as the video frame to be monitored from videos to be monitored according to the predefined extract rules through the network; extracting the characteristic vector of the video frames to be monitored; and selecting the characteristic vector of a key frame similar to the video frame to be monitored from the key frame characteristic vectors of objectionable videos in a video fingerprint database, wherein the distance between the similar key frame characteristic vector and the characteristic vector of the video frames to be monitored is smaller than a given matching threshold. By selecting a portion of the video frames as the video frame to be monitored, the method can acquire the key frame without a large amount of calculation,and the video acquired through the network has less content and needs less storage space after downloading, thereby reducing the resource consumption during the monitoring.

Method and apparatus for monitoring video copy base on content

The increasing transmission of illegal videos over the Internet imposes the needs to develop large-scale digital video forensics systems for prosecuting and deterring digital crimes in the Internet. In this paper, we propose, design, and implement a novel large-scale Digital Forensics Service Platform (DFSP) that can effectively detect illegal content from Internet videos. More specifically, we propose a distributed architecture by taking advantage of Content Delivery Network (CDN) to improve scalability, which can process enormous number of Internet videos in real time. We propose CDN-based Resource-Aware Scheduling (CRAS) algorithm, which schedules the tasks efficiently in the DFSP according to resource parameters, such as delay and computation load. We deploy the DFSP system in the Internet, which integrates the CDN-based distributed architecture and CRAS algorithm with a large-scale video detection algorithm, and evaluate the deployed system. Our evaluation results demonstrate the effectiveness of the platform.

A Novel Large-Scale Digital Forensics Service Platform for Internet Videos

The invention discloses a video retrieval method based on contents and a system thereof which are used for solving the problem of lower efficiency of the video retrieval based on contents. The method comprises the following steps: a characteristic vector of a video frame to be detected is acquired; a corresponding cartesian coordinate is searched according to the index number of the characteristic vector of a sensitive video frame to be compared in a video fingerprint database and a predefined transformation rule; the characteristic vector of the video frame to be detected is sent to a retrieval module of a corresponding server according to the searched cartesian coordinate; and the retrieval module judges the similarity between the characteristic vector of the video frame to be detected and the characteristic vector of the sensitive video frame to be compared. As a content addressable network is employed to reasonably organize the video fingerprint database, create indexes, and acquire the video example to be detected, the method utilizes a certain retrieval algorithm to search the best matched characteristic vector of the sensitive video frame from the fingerprint database, which improves the video retrieval efficiency.

Video retrieval method and system based on contents

The invention discloses a method for detecting a content-based video copy and a system thereof, so as to solve the problem that the prior art has weaker search matching capability in the same copy. The method comprises the following steps: selecting a key frame in video to be detected so as to acquire a characteristic vector of the selected key frame which is an image frame representing a group of image frames; searching a proper phasor with a distance to the acquired characteristic vector smaller than a presetting threshold value in a proper phasor of the key frame of sensitive video of a video fingerprint bank; and determining copy content the same as content of the video to be detected in the sensitive video of the video fingerprint bank. In the proper phasor of the fingerprint bank, the method searches the proper phasor belonging to the same copy with the characteristic vector selected from the video to be detected so as to determine that a plurality of image frames represented bythe key frame of the video to be detected belong to the sensitive video of the video fingerprint bank, so the search matching capability of the same copy can be improved.

Method and system for monitoring video copy based on content

The invention discloses a CDN-based multimedia content monitoring system, a method and a device thereof. The method comprises the following steps: receiving task configuration information generated according to a multimedia content monitoring task which comprises a URL of the multimedia content to be monitored; selecting a first CDN node acquired by execution content according to the acquired node information of a CDN node and the task execution state information, and instructing the first CDN node to acquire the multimedia content according to the URL of the multimedia content to be monitored; selecting a second CDN node generated by an execution fingerprint according to the acquired node information of the CDN node and the task execution state, and instructing the second CDN node to generate a fingerprint for the multimedia content acquired by the first CDN node; and processing the multimedia content to be monitored according to a result of matching between the fingerprint generated by the second CDN node and the fingerprint in a fingerprint database. The technical scheme can help improve the efficiency of monitoring the multimedia content.

Wen Hui

Papers

Method and apparatus for monitoring video copy base on content

A Novel Large-Scale Digital Forensics Service Platform for Internet Videos

Video retrieval method and system based on contents

Method and system for monitoring video copy based on content

Multimedia content monitoring system, method and device based on content distributing network