Bionic hand guided by 99p camera

Biomedical engineers have created a bionic hand that allows amputees to “automatically” pick up objects without conscious thought using images from a 99p webcam.

The researchers from Newcastle University claim their technology acts “just like a real hand”, without time-consuming processes used by traditional prosthetics. 

Current models require users to see an object and physically stimulate muscles in their arms. Electrical signals are then picked up and control the hand’s motion, in a process that takes practice, concentration and time.

The new bionic hand uses the built-in webcam and computer vision to automatically analyse objects in front of the user and work out the appropriate gesture, from one of four set grasps. The prosthetic then starts picking up the object within milliseconds.

The team, led by co-authors Kianoush Nazarpour and Ghazal Ghazaei, showed the webcam pictures of many objects at different angles. They then used neural networks so the machine could “learn” the best way to pick up similar objects.

The researchers are preparing to offer the technology to patients.

The research was published in the Journal of Neural Engineering.