Skip to main content



Image Recognition and Artificial Intelligence

Advances in artificial intelligence has helped engineers build software that can recognize and describe content in photos. There are artificial intelligent programs in new cars that can recognize pedestrians and stop the car to avoid collisions. As you can imagine there is a multitude of beneficial applications that can be achieved through artificially intelligent programs.

These image recognition algorithms use artificial neural networks. The idea of artificial neural networks is inspired by the human brain. In this network there are perceptrons which carry a weight function. These perceptrons are the nodes and they are connected to other perceptrons in a network. These perceptions are like the neurons in the human brain and the connections are like the synapses between neurons. So the way image recognition works is that you train these artificial neural networks by sending in thousands of images and having the computers look at several characteristics that are sent in as inputs and varying the weights of the perceptrons based on if the output during this training step is correct or not. After the training step these programs would be able to recognize images more accurately.

Although these artificially intelligent programs are able to recognize images it is still nowhere near human perception. This is because, these artificial neural networks is a simplified model of the human brain.

 

http://www.nytimes.com/2014/11/18/science/researchers-announce-breakthrough-in-content-recognition-software.html

Comments

Leave a Reply

Blogging Calendar

September 2015
M T W T F S S
« Aug   Oct »
 123456
78910111213
14151617181920
21222324252627
282930  

Archives