Author Archives: Martino Jerian

Amped Support Portal Available Now!

Normally, we release new stuff for your desktop, but this time we released a little new section on our website to help you with the management of your Amped Software licenses and training: the Amped Support Portal.

In the portal, you can find all the essential information about your software licenses and the training classes that you have attended.

Just head to https://support.ampedsoftware.com and you will see a typical Email / Password login page.

login

If you are an Amped Software user and we have received your details when you purchased a license, you should already be able to log into the system. Just insert your email address and hit the button “Reset password”. Then check your email and follow the instructions to change the password and then log in. If you don’t receive an email, this means that we don’t have you in our records. But no worries, just send an email to support@ampedsoftware.com and we’ll create an account for you once we have identified your available licenses.

You can see all your licenses and their expiration dates, you can download the latest versions of the software, and you can generate license certificates that your administration or management may require.

Additionally, you will also see all the training classes that you have attended and download the related training certificate.

We plan to add additional features soon, for example, adding the possibility to receive email notifications before the expiration of your SMS (software updates). So, stay tuned!

As usual, feel free to contact us if you have any comments or suggestions about the new portal.

Google’s CSI-Like Algorithm Is Not Enhancing Images, It’s Creating Them!

In the last few days, there’s been a lot of noise about the latest impressive research by Google. This is a selection of articles with bombastic titles:

The actual research article by Google is available here.

First of all, let me say that technically, the results are amazing. But this system is not simply an image enhancement or restoration tool. It is creating new images based on a best guess, which may look similar but also completely different than the actual data originally captured. Continue reading

Computational Photography is the Biggest Upcoming Authentication Challenge

mobile-photography

I assume most of the readers of this blog are video / photo / gadget / phone / camera geeks. I am sure you didn’t miss the reviews of the latest Apple iPhone 7 Plus and Google Pixel phones. They have a lot in common, but there is one major aspect that is interesting for our applications: things are slowly moving from photography to computational photography. We are no longer just capturing light coming from optics and applying some minor processing to the pixel values to make the picture more pleasant to the viewer.

Phones must be slim and light and yet we still expect to have near DLSR quality. So, now computational photography comes into play. The iPhone 7 Plus, for example, uses two different cameras to calculate a depth of field and then tries to simulate the “bokeh” effect via software you would normally get in bulky professional cameras, by using fast optics at a wide aperture.

On the other side, when you hit the button on the Pixel phone, it is capturing a bunch of pictures and then decides what to keep from every picture in order to give the user the final result.

This challenges the concepts of originality and authenticity. The light captured by the camera is no longer the output of the photography process, but just the first step of a more complex process based on a multitude of factors. There is little doubt that this is just the beginning of a trend which will explode in the next few years. Continue reading

What PC do you have handy?

Customers often ask us about the hardware requirements for our products before purchasing. While we have some recommendation, the reality is that many of our customers use Amped FIVE (or our other products) on unbelievably old computers. Sure, Amped FIVE would be slower, but for working on low-resolution CCTV videos, even a 10-year-old PC with Windows XP (not recommended!) still works mostly fine.


I recently taught one of our courses at a customer’s premises. Since the class was quite full and they didn’t have enough recent laptops to bring into the training room, about half of the students had pretty old laptops. During the training, we normally provide the software installer and training examples on USB drives. Some people claimed that their PC was not able to see the drive. We figured out that they were using Windows XP SP2, they were not connected to the Internet and had not updated in ages. Continue reading

Be Conscious of the Algorithms You Use in a Forensic Setting

Our customers often ask us for specific functions and filters to be included in our software. Paying attention to user requests and managing our development priorities according to them is probably one of the things Amped Software is best known for.

However, not all requests, even if technically feasible, are a match for the purpose of our solutions. Take for example Amped FIVE: some of the most common use cases are enhancing license plates or faces.

Quite a few customers asked for some functions to perform super resolution of faces from a single image. While this may be technically very interesting, most of the implementations have a fatal flaw that prevents them from being used for forensic applications: they introduce data external to the case.

Yesterday a GitHub project called “srez” caught my attention.

Image super-resolution through deep learning. This project uses deep learning to upscale 16×16 images by a 4x factor. The resulting 64×64 images display sharp features that are plausible based on the dataset that was used to train the neural net.

Here’s an random, non cherry-picked, example of what this network can do. From left to right, the first column is the 16×16 input image, the second one is what you would get from a standard bicubic interpolation, the third is the output generated by the neural net, and on the right is the ground truth.
Example output Continue reading

Istanbul Airport Attack: a Multimedia Forensics Perspective

After the attacks of Paris, Brussels (and unfortunately many others), three days ago there was another major event at Istanbul Airport. While its origin is yet to be officially confirmed, strong hints are again at ISIS terror strategy. The number of victims is currently set at more than 40 and growing, with more than 160 persons injured. This is, again and again, a very sad story and our prayers are with the victims, the wounded and their family.

As usual, in these major events, it is interesting to analyze the different audio and video sources and their use.  Continue reading

Amped Software at IH&MMSEC 2016

I am very excited to announce that next week I’ll be at the ACM Workshop on Information Hiding and Multimedia Security, in Vigo, Spain from June 20 to 22, 2016.ihmmsec

Why am I so excited? While I love visiting customers, going to trade shows and partner events, this is a purely scientific conference. Our roots are in the academic world, and we are still cooperating with different universities and research institutions very often. And this time, I have the honor of giving a keynote in front of some of the world most well-known researcher in our discipline.

The title of the presentation is “Bringing Multimedia Security from the Research Lab to the Forensic Lab”. This is the abstract of the presentation: Continue reading