Electronics detector demo
There are different sorts of electronica that can be detected with image recognition. Think about identifying X-ray images, or even checking retour applications to see if the right electrical device is delivered. It is even possible to automatically detect damages on devices and what kind of damage it contains. To show how the algorithm can make a separation between electronics we have made an online demo where you can test your own image.
Common Objects in COntext
The COCO dataset calculates a percentage of different kinds of recognizable objects in an image. The learning algorithm is trained to detect the following electronics:
- Remote control
- Telephone
- Laptop
- TV
- Mouse
Common Objects in COntext
The COCO dataset calculates a percentage of different kinds of recognizable objects in an image. The learning algorithm is trained to detect the following electronics:
- Remote control
- Telephone
- Laptop
- TV
- Mouse
Image recognition with deep learning
For this example we have used an algorithm that is trained on a thousand photos with all sorts of electronics from the COCO dataset (Common Objects in COntext). This database includes images of the chosen electronics where you can exactly see where the automatic device is hidden on the photo. Therefore, a learning algorithm can train itself to automatically recognize devices in different photos. Off course you can also use this technique to detect other objects as well. We use tools like Keras and TensorFlow to see how well the algorithm performs.
