Researchers have been endlessly searching for ways to use computers beyond the typical mouse, keyboard, remote control, or touch screen. Much of their effort is geared toward unlocking more natural forms of communication. For example, voice commands have been a prominent feature in many smartphones and virtual assistants.
Hand gestures are another form of human communication that can be utilized to maneuver computer interactions. Camera systems, image analysis, and machine learning have made strides in optical-based gesture recognition; however, they are hindered by computational complexity, low speed, poor accuracy, or a small number of recognizable gestures.
A team at Sun Yat-sen University in China is set on improving hand gesture recognition and has created a new algorithm that seems promising so far. According to their research, the team integrated innovative strategies to overcome known challenges in consumer devices. By identifying different hand types, palm width, length, and finger length, the hand gesture recognition process is more refined.
The researchers said, “Traditional simple algorithms tend to suffer from low recognition rates because they cannot cope with different hand types. By first classifying the input gesture by hand type and then using simple libraries that match this type, we can improve the overall recognition rate with almost negligible resource consumption.”
There is also a pre-recognition step in the algorithm, which calculates a ratio of the hand area to determine the three most likely gestures out of the possible nine.
According to researchers, “The gesture pre-recognition step not only reduces the number of calculations and hardware resources required but also improves recognition speed without compromising accuracy.”
Tested in a real-life situation, the algorithm showed more than 93 percent accuracy. Hand gestures were rotated, translated, and scaled in the process. The team will focus on improving the algorithm in situations with poor lighting and increase the number of possible gestures overall.
Founded in 1994, Creative Programs and Systems provides professional results for all computer needs. We design, create, and code an array of custom software programs and websites; offer top-notch digital marketing services including enhanced Search Engine Optimization (SEO) and paid advertising; repair and provide support for computers of both residential and professional nature; build custom systems and servers, and offer secure data backups. Need assistance or want to learn more? Call us at 810-224-5252 or e-mail firstname.lastname@example.org.
Written by the digital marketing staff at Creative Programs & Systems: www.cpsmi.com.