Close
0%
0%

Prosthetic Photographer

The Prosthetic Photographer forces its users with electrical impulses to unwillingly take beautiful pictures.

Similar projects worth following
The Prosthetic Photographer enables anybody to unwillingly take beautiful pictures.
It forces its user with electrical impulses to take a picture if the current scene in front of it is beautiful enough.
The computer inside of it was trained with a neural network to distinguish between high and low quality photos. It constantly analyzes the image in front of it. When satisfied with the current scene, a electric impulse forces the user to unwillingly press the release of the connected camera and eventually taking a picture.
With advancements in machine learning and especially with neural networks computers can learn and decide about information of any kind more precisely than humans ever could.
This system is part of a new aesthetic, based on computer-generated decisions that were taught by previous human skill.
The Prosthetic Photographer is a prosthetic skill extension making everyone using it an as good photographer as the data it was trained on.

This project is one of three projects of the master thesis: „Experiments on Human-Computer Interaction through electrical body part stimulation“ where each project combines the given hardware and technology of a TENS (transcutaneous electrical nerve stimulation) unit with various theoretical aspects.
This way not only the human can operate the device, but the device itself can use the human as an interface.

The computer within the enclosure is a Raspberry Pi(3) connected to a camera module. It is continuously running an image classifier script that is analyzing the currently seen picture. When the classifier gets results of over 95% for a high-quality image, it sends out a signal to the connected TENS unit.

A neural network was trained beforehand on a dataset consisting of images labeled as high- or low quality. Transfer learning was used as a training method. The trained weights were then transferred to the Raspberry Pi.

Google’s Inception Model, which is a neural network specialized on image classification was used.
The dataset used for this particular application is called CUHKPQ and consists of 17,613 images. They were obtained from a variety of online communities and are divided into seven semantic categories. They were also labeled in categories of high- and low-quality pictures. A photographic community has done this by hand.

The programing language is Python(3).
The software library that was mainly used in this particular project is TensorFlow.

A TENS unit within the enclosure is responsible for the electrical impulse that is sent to the user. Every time the classifier is satisfied, it sends a signal and electrical current starts flowing between the electrodes on the handle and the user’s hand causing the index finger to twitch.
The button underneath the index finger then gets pressed and the digital camera takes a picture of the current scene.  

Because every person reacts differently to the electrical impulse one can change the intensity of the TENS unit by turning the knob until the contraction of the hand becomes unavoidable.
The TENS unit is powered by a 9V battery while the Raspberry has to be connected to a power bank that is placed underneath the handle.

Aluminum tape extends the electrodes on the handle. It runs around the back of it to cover a larger area ensuring enough current to run through the user.
There is no need to attach anything additional to the user. The user gets automatically connected to the two electrodes by just holding the handle.

JPEG Image - 820.19 kB - 03/22/2018 at 12:08

Preview
Download

JPEG Image - 665.33 kB - 03/22/2018 at 12:08

Preview
Download

JPEG Image - 323.28 kB - 03/22/2018 at 12:08

Preview
Download

8.JPG

Photo made by the Prosthetic Photographer

JPEG Image - 30.01 kB - 02/08/2018 at 12:26

Preview
Download

7.JPG

Photo made by the Prosthetic Photographer

JPEG Image - 145.31 kB - 02/08/2018 at 12:26

Preview
Download

View all 14 files

  • 1 × TENS (TNS SM 2 MF) Transcutaneous Electrical Nerve Stimulation
  • 1 × Raspberry Pi 3
  • 1 × Raspberry Pi Camera Module V2
  • 1 × San Disk 16 GB micro SD Card
  • 1 × Anker 10000mAh Powerbank

View all 9 components

View all 4 project logs

Enjoy this project?

Share

Discussions

Paula Davies Rezende wrote 04/05/2018 at 12:56 point

Hello Peter, I am a PhD candidate, and my research is about images produced by non-humans, in the Art Theory field. I wonder if you could spare some time to help me with some doubts about this project, specially regarding the classification of the images. In a few words, I am very interested in how did you (or your team) defined what is a high and low quality image. You said in the text above that  a photographic community has done this claffisication by hand, but what were the parameters? Do you have an e-mail address I could write? It would be very helpful to me If you could help me with some questions.

  Are you sure? yes | no

Stephen Tranovich wrote 02/14/2018 at 01:40 point

This is amazing!

  Are you sure? yes | no

Philip wrote 02/09/2018 at 08:59 point

I am interested in Hackbox# 0026. I looked at you tube but I did not see any reference to EEG signals. I may be having a senior moment.

  Are you sure? yes | no

Richard Hogben wrote 02/09/2018 at 01:28 point

Really great, how high can you go with the intensity before it's 'uncomfortable' ? Does the action of the finger cause any blur at lower shutter speeds?

  Are you sure? yes | no

Peter wrote 02/09/2018 at 12:02 point

Hey, thanks. 

Inside of it is a commercial TENS unit ( TNS SM 2 MF http://tenswelt.de/products/tns-sm-2-mf-tens-reizstromgeraet-mit-burst-und-modulation) one can turn it up to 75mA. Every person reacts differently. So for me half of the max intensity was enough to lose control. Others had to use the max intensity or even enhance the signal by using special electrode gel like this one (https://www.amazon.com/SPECTRA-360-12-08-Electrode-Tube/dp/B0093J2GM4).

The camera that was used is a sony alpha 6300. It was used in automatic mode and with the good iso and super fast auto focus there were no problems regarding blurriness. 

  Are you sure? yes | no

Similar Projects

Does this project spark your interest?

Become a member to follow this project and never miss any updates