dfm covers
 
 

Improving Image Recovery Rates in Big Data


Improving Image Recovery Rates in Big Data

The current problem with identifying objectionable images is that there are an enormous number of images on the internet that require analysing. forensic investigators are currently using two techniques for identification, namely; content based image retrieval (cbir) that uses visual aspects of an image for identification and concept based image indexing (cbii) that uses the metadata of the image for identification. the current challenge for investigators is to resolve the dilemma of one technique that is accurate, but very slow against the other that is inaccurate, but very fast for image retrieval. the utilization of both techniques to solve the problem is cost prohibitive in terms of time and resources in professional practice. our research was to investigate other methods of identifying images, which resulted with a ‘hashing’ based methodology that had the potential for providing an improvement in performance overall.




Find out more - subscribe to DFM today and read the full article. Or if you're a subscriber, login and read the article online.


 
Please make cache directory writable.
 

Submit an Article

Call for Articles

We are keen to publish new articles from all aspects of digital forensics. Click to contact us with your completed article or article ideas.

Featured Book

Learning iOS Forensics

A practical hands-on guide to acquire and analyse iOS devices with the latest forensic techniques and tools.

Meet the Authors

Andrew Hoog

Andrew Hoog is the Chief Investigative Officer at viaForensics'

 

Coming up in the Next issue of Digital Forensics Magazine

Coming up in Issue 41 on sale from November 2019:


Forensic Syntactical & Linguistic Investigation

Mark Iwazko presents a case study regarding a Forensic Syntactical & Linguistic investigation: Instructed by the Moscow General Council of one of the actual big four accountants. Read More »

Forensic Readiness: A Proactive Approach to Support Forensic Digital Analysis

An increasing number of criminal actions are inflicting financial and brand damage to organizations around the globe. An impressive number of such cases do not reach the courts, mainly because of the organization’s inefficiency to produce robust digital evidences that are acceptable in the courts of law. Read More »

Subscribe today


Using Error-Patterns for Attribution: An Applied Linguistics Technique

Corpus Linguistics within Second Language Acquisition has developed models of error patterns made by defined groups of second language learners. This knowledge base can be leveraged by a knowledgeable analyst to attribute content to a subset of authors. Read More »

Every Issue
Plus the usual Competition, Book Reviews, 360, IRQ, Legal

Click here to read more about the next issue