Communications of the ACM
Machines Still Way Behind Humans in Image Recognition
Credit: www.geekamongus.com
Computers can copy many aspects of human behavior, but they don't yet possess our ability to recognize distorted images, says a team of researchers. "Our goal is to seek a better understanding of the fundamental differences between humans and machines and utilize this in developing automated methods for distinguishing humans and robotic programs," says James Z. Wang, an associate professor in Penn State University (PSU) College of Information Sciences and Technology.
Wang and associates explored the difference in human and machine recognition of visual concepts under various image distortions. Although the scope of the human users was limited, the results proved that robotic programs were not able to recognize distorted images. In other words, a computer recognition program had to rely on an accurate picture, while humans were able to tell what the picture was even though it was distorted.
Wang says he hopes to work with developers in the future to make a CAPTCHA program that Web sites can use to strengthen the prevention of automated network attacks.
From Taragana
View Full Article
No entries found