Chapter 765 Amazing success rate
Mike Connor reached out to support the microphone, with a faint smile on his face: "Before the report officially begins, I would like to explain to you what computer vision is."
"Some people may think that computer vision is very complicated, but it is very simple and can be understood from the literal meaning."
"Computer vision is actually a science that studies how to make machines "see". Furthermore, it refers to using cameras and computers instead of human eyes to identify, track and measure targets and become a technology that is more suitable for human eyes to observe."
"We have done a lot of research on this, such as image classification, object detection, object tracking, language segmentation, and instance segmentation."
"These research results promote the vigorous development of computer vision, so today, I want to propose another topic, which is to apply computer vision to the field of intelligent robots! Let intelligent robots have vision just like humans!"
"Just recently, our computer vision development team at Imperial College conducted an experiment. We have transplanted the constructed neural network to a machine, allowing him to replace humans in digital image forensics, and identify those that have been altered through real tampered image training. past pictures."
quiet!
It was deadly quiet, and everyone was staring at Mike Connor intently. They all knew that this was the first trial of computer vision applied to the field of intelligent robots.
If successful, it will set off a huge storm in the computer field, and this storm may change the pattern of several industries!
"Gulu~" Everyone swallowed their saliva in unison, and asked cautiously: "What's the result? Was the experiment successful?"
"It's neither a success nor a failure..." After thinking for a while, Mike Connor said slowly.
"Before the experiment, we selected 20 pictures and modified 10 of them to a certain extent, but the results of the experiment were not satisfactory."
"Professor Connor, what do you mean?" After a long silence, someone in the crowd asked.
If computer vision can't be 100% correct, Mike Connor certainly doesn't think he's successful.
"Of the 10 altered pictures, the computer only found 7!" Mike Connor said blankly, "So, I can't consider him a success or a failure for this result."
The overall test process is okay, but the test results are not satisfactory.
This is very important because of the 100% success rate.
Success is success, failure is failure, what does it mean that this is not considered success?
Forgive them for their lack of reading, they kind of don't understand what Mike Connor means.
Just like the face payment system in his future application field, if the computer can't even recognize the face 100%, then the situation of fraudulent payment will easily occur.
This will not only bring huge economic losses to people, but also have a great impact on the discipline of computer vision.
The first trial has already reached a 70% success rate!
What about the second and third time?
To put it bluntly, this is already an extremely high success rate.
They really couldn't figure out why Mike Connor was still not satisfied!
"Professor Connor, the first test has achieved a success rate of 70%, which is already a remarkable achievement..."