Human Face Detection

Lattice sensAI Reference Design

Add Human Face detection (or any specific object of interest) to any Device – The human face detection reference design enables systems to always search for the presence of a human face via a CMOS image sensor. With an updated training model using the deep learning framework, Caffe (without any other changes), systems can use our design and detect any object of interest.

Reduce Power without Compromising Performance – Systems can now enable artificial intelligence with an always-on image sensor, while consuming less than 1 mW of active power.

Production-priced, Space-efficient Design – The complete inference engine fits inside of the 2.15 mm x 2.55 mm iCE40 UltraPlus-5K FPGA and can work with various popular image sensors. Featuring proven functionality with Omnivision’s OVM7692 and Himax’s HM01B0.


  • Frame-rate detection can be adjusted and set at 5 frames per second to keep the power consumption under 1 mW
  • Hardware platform used to demonstrate this reference design is the iCE40 UltraPlus MDP board, which uses the Omnivision OVM7692
Lattice sensAI

Jump to

Block Diagram


Technical Resources
Human Face Detection Using Compact CNN Accelerator IP - Documentation
FPGA-RD-02034 1.1 9/25/2018 PDF 438.5 KB
Human Face Detection Using Compact CNN Accelerator IP Project Files
1.0 9/25/2018 ZIP 1.1 MB

Like most websites, we use cookies and similar technologies to enhance your user experience. We also allow third parties to place cookies on our website. By continuing to use this website you consent to the use of cookies as described in our Cookie Policy.