Image recognition technology has progressed significantly over the years, and Microsoft is the company that’s leading that progression. You’d think that Google would be the one leading, but at the sixth annual ImageNet image recognition competition this year, Microsoft’s research team managed to beat not only Google, but Intel and Qualcomm as well. Its technology is so good at recognizing images that it’s accuracy matches, or even exceeds what a human can do. Naturally, the researchers are able to do this by using something called a deep neural network, which essentially mimics the way the human brain works to improve a computer’s problem-solving abilities.
Microsoft researchers on Thursday announced a major advance in technology designed to identify the objects in a photograph or video, showcasing a system whose accuracy meets and sometimes exceeds human-level performance. Microsoft’s new approach to recognizing images also took first place in several major categories of image recognition challenges Thursday, beating out many other competitors from academic, corporate and research institutions in the ImageNet and Microsoft Common Objects in Context challenges. Like many other researchers in this field, Microsoft relied on a method called deep neural networks to train computers to recognize the images. Their system was more effective because it allowed them to use extremely deep neural nets, which are as much as five times deeper than any previously used. The researchers say even they weren’t sure this new approach was going to be successful – until it was. “We even didn’t believe this single idea could be so significant,” said Jian Sun, a principal research manager at Microsoft Research who led the image understanding project along with teammates Kaiming He, Xiangyu Zhang and Shaoqing Ren in Microsoft’s Beijing research lab.
