More Real Than Real: a Chat About Deepfakes with Dr. Cecilia Pasquini (University of Trento)

Deepfakes and computer-generated images have been around for a few years now, and they’ve become quite popular. We’ve recently authored an article in the Evidence Technology Magazine about the challenging task of Dealing with deepfakes. Much like it happens for cryptography-vs-cryptanalysis, a fight is going on here between those developing advanced neural networks, capable of creating more and more realistic fakes, and those aiming at detecting them. This fight is mostly guided by researchers, but video forensic analysts and everyone dealing with forensic image analysis are necessarily involved, since they may soon have to face deepfakes in their investigations!

Continue reading

Amped FIVE Does Not Use A.I. And Implements Forensically Safe Algorithms to Enhance Video Evidence

TL;DR

In recent days, following the media attention on the Kenosha Shooting trial (“STATE OF WISCONSIN – VS – Kyle H. Rittenhouse”) in which Amped FIVE has been used for evidence analysis, a previous article on this blog about the use of Artificial Intelligence on image and video forensics has been misunderstood and instrumentalized.

The applicability of image interpolation and image enhancement at large as evidence in court has been discussed, sometimes without the needed in-depth knowledge of the field.

In this article, we will clarify some very important concepts related to forensic video analysis at large and Amped FIVE.

1) Amped FIVE does NOT use Artificial Intelligence

Amped FIVE has been designed specifically for evidentiary use. It does not use Artificial Intelligence: image and video enhancement in Amped FIVE are implemented in a forensic workflow based on carefully selected algorithms that guarantee reliability, repeatability, and reproducibility. Thanks to this, Amped FIVE has become widely accepted as the standard tool for forensic image and video analysis, being used in 100 countries worldwide.

2) Interpolation DOES NOT TAMPER with the image

We need interpolation to show things as they are: interpolation is not only used to “zoom on” an image, but it is an essential part of the creation and display of a digital photo or video. Interpolation does not add image information, but improves visualization of image data 1,2,3. Questioning the general acceptability of interpolation means questioning the acceptability of images and videos as evidence.

3) Image enhancements performed by a competent analyst with the right tools are INSTRUMENTAL FOR COURT USE

An analyst with the right tools, technical preparation, and workflow can enhance the image in a way that can help the trier of fact and be accepted in court. Image enhancement is a fundamental part of forensic video analysis and it’s the duty of the forensic video analyst to properly enhance images and videos to give a more accurate representation of the scene, compensating, when possible, the imperfections introduced by the image generation process.

We hope this new take on the argument will help to better comprehend the topic and will clarify some of the misinterpretations of the original post. And if you want to learn more on these topics, please keep reading!

Continue reading

Amped DVRConv Update 22526: New Important Formats and Codec Variations

We have been working hard to support a number of user-submitted proprietary video files over the past few months so we have decided to get these into a new Amped DVRConv update to quickly benefit all users.

For those people not familiar with Amped DVRConv, this is the stand-alone conversion tool that utilizes the powerful Amped Conversion Engine. Conversion is a small (but important) part when using Amped FIVE or Amped Replay but with Amped DVRConv, it is the sole purpose.

DVRConv was designed with flexibility in mind. If you are a single user, it gives you full control over the various options you have for processing and sorting. However, if you have DVRConv shared within a small team or entire organization, it can simply be set as a drag and dropper, and the same settings will be applied to any ingested media.

You can even set it to ‘watch’ a specific Folder or Drive. When any media is placed into it – it will be scanned and converted as set within the options!

The program really could not be simpler. It really is Drag > Drop > Done!

It is very important to us that we get newly supported formats out to you quickly so here we go! In this latest update we have added:

1 A completely new format: .MVA
5 New variations of already supported file formats
4 New Time/Date formats

Finally, it is worth refreshing what DVRConv is doing to the file and what a format variation is.

There are thousands of proprietary media files created by video surveillance systems. A native proprietary video file usually has lots of other data that is not video or audio. This includes proprietary date and time info, camera info, and maybe a proprietary index system specific to that manufacturer. These details can, and often do, cause standard decoders and converters to skip frames, duplicate frames, and cause block errors.
Amped DVRConv will clean the data first to separate the media, date and time information, and any other data. After cleaning, the media will be placed into a standard media container. It is necessary to do this for the correct forensic workflow. Without cleaning, you could easily be viewing and making decisions on damaged or incorrect video.

A format variation is a new pattern of data within a known format. Remember, the format is the extension type, such as .vid.

As the industry surrounding video surveillance is un-regulated, hundreds of different companies can store their data within this same extension, but all use different structures. Even the same company can change their structure for different systems or versions of the same system.

DVRConv, and all the other products using the Amped Conversion Engine, will scan the format and compare the data with all known variations. If matched, the conversion will proceed.

What are you waiting for? Get access to the new format and variations.

Don’t Delay – Update Today

If you have an active support plan you can update straight away by going into the menu About > Check for Updates within Amped DVRConv. If you need to renew your SMS plan, please contact us or one of our authorized partners. And remember that you can always manage your license and requests from the customer support portal.


How to Use Variable Motion Deblurring in Amped FIVE

screenshot of a blurry video frame of a bus path of travel

One of the biggest challenges in Forensic Video Analysis (FVA), is the restoration and enhancement of motion blur. In this latest ‘How To’ article, published on Forensic Focus, David Spreadborough returns to Amped FIVE and takes us through one of this year’s new filters, Variable Motion Deblurring.

Learn how the filter works to turn blurred noise into restored and actionable data.

Read the full article here.

Continue reading

Summing Up: How Do I Convert, Play, Enhance, Annotate, and Export Video Evidence With a Single Tool?

Today we’d like to start with a huge THANKS to all you, loyal followers of the Amped Replay: How Do I Do This? series! We started nothing less than 25 weeks ago, and now it’s coming to an end. This post wraps up and concludes the series: we’ll briefly walk through a complete video processing workflow. You’ll see how Amped Replay helps investigators stick to a forensically sound and lean process. Keep reading!

Continue reading

LEVA 2021 – Annual Digital Multimedia Evidence Training Symposium

LEVA’s 32nd annual video and audio evidence symposium will be held in Franklin, Tennessee from October 18-22.
This annual training event provides valuable workshops and lectures focused on the science of forensic video analysis and on the needs of digital multimedia evidence. This premiere event also offers great networking opportunities and video forensic examiners are coming from all over the world to attend.

Amped Software is excited to be exhibiting in person so don’t miss any of our interesting workshops and presentations:

Continue reading