In the field of Artificial Intelligence, deep neural networks are continuously pushing the boundaries of visual recognition.
Even though the computing power of smartphones and tablets has increased at a breath-taking pace, visual recognition needs to run quickly and with high accuracy, not always easy with the relatively limited computational power and space of a mobile device.
Thankfully, this is where TensorFlow MobileNets come into their own. TensorFlow is an open source software library for high-end computation developed following many years of work by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organisation and is the Artificial Intelligence technology which powers Google Photos to Google Cloud Speech.
TensorFlow MobileNets are designed to effectively maximise image recognition accuracy within the constraints of limited computational power of a mobile device. MobileNets are small, low-latency, low-power machine learning models which can be built upon for classification and detection of your particular image-type requirements.
Click on the "browse to select your image" button below to select an image on your device to see real-time image recognition in action!
Recognition of the image contents will most likely be pretty poor because we are using an artificial intelligence model which was pretrained on ImageNet (an ongoing research effort to provide researchers around the world an easily accessible image database). Of course for your business requirements you would be looking for an artificial intelligence model which was pretrained on images relevant to your business requirements which we can organise for you.