Compv Save

This is our R&D Computer Vision project. For now there is no documentation and it's not intended to be used by other companies.

Speed comparison against OpenCV: speed_compare (core i7 quad@4ghz).txt

Insanely faaaaast

• Hand-written assembler (10% of the code)
• SIMD (SSE, AVX, NEON)
• GPGPU (CUDA, OpenVINO, OpenCL, OpenGL, NNAPI and Metal)
• Smart multithreading (minimal context switch, no false-sharing, no boundaries crossing..)
• Smart memory access (data alignment, cache pre-load, cache blocking, non-temporal load/store for minimal cache pollution, smart reference counting...)
• Fixed-point math
• ... and many more

SDKs using our code

• KYC documents recognition & verification
• 3D Passive Face Liveness Detection (Anti-Spoofing)
• ANPR/ALPR SDK for embedded devices (ARM) and desktops (x86)
• MRZ/MRP SDK for embedded devices (ARM) and desktops (x86)
• Bank credit card recognition/OCR SDK for embedded devices (ARM) and desktops (x86)
• Bank check information extraction/OCR from Magnetic Ink Character Recognition [MICR] (E-13B & CMC-7) using deep learning for embedded devices (ARM) and desktops (x86)

Online demo apps using our code

• KYC documents recognition & verification
• Cloud-based 3D Passive Face Liveness Detection (Anti-Spoofing)
• Cloud-based Automatic Number/License Plate Recognition (ANPR/ALPR)
• Cloud-based Machine-readable zone/passport (MRZ/MRP)
• Cloud-based Bank credit card recognition/OCR (ScanToPay)
• Cloud-based Magnetic ink character recognition (MICR E-13B & CMC-7)
• Cloud-based Content-Based Image Retrieval (CBIR)
• Cloud-based Scene text recognition (TextInWild)

Technical questions

Please check our discussion group or twitter account