Jeffrey Ng's Cortexica Models Human Visual Perception
By wchung | 22 Apr, 2026

Jeffrey Ng is co-founder of visual-identification developer Cortexica.

Jeffrey Ng and co-founder Anil Bharath have developed visual-recognition software that makes positive identifications of products in photos and videos. A user of Cortexica’s WINEfindr can comparison shop for a specific bottle of wine by taking a photo of it, doing away with the need to scan a bar code.

“It’s a bit like the bar-code scanning apps that link a physical object in the real world to online content,” says Bharath. “But rather than having to create a QR code, it recognizes the object itself.”

Cortexica’s VisualSearch platform is more accurate and scalable than other similar software because it models the way the human vision compensates for different lighting conditions and angles, says Ng. It zeroes in on key features irrespective of their size, lighting or orientation, making it possible to identify products at a distance or even while they are moving. Cortexica has also used the technology to develop an app that can spot and evaluate the impact of logos within videos.

Ng and Bharath started up Cortexica with technology they developed from research they conducted at London’s Imperial College London. In 2006 they succeeded in modeling how human neurons react to visual stimulus, accurately mimicking the Primary Visual Cortex, also known as V1, and its indifference to variance of lighting conditions (e.g. bright or dark scenes), orientation (rotation in and out of plane) or geometric distortion (e.g. curvature). The company recently launched an application-programming interface (API) for its technology to let others build visual recognition apps.

Ng’s research and development work has focused on machine learning, face detection, pose estimation, object tracking, behaviour recognition, computational biology, the human visual system and adaptive wavelet filters. He has recently been working on real-time vision systems based on Graphics Processing Units.

Ng has a PhD in Computer vision from Queen Mary University of London. He has published more than 35 scientific papers in international journals and conferences. He is the inventor of three pending patents.