License Plate Recognition

What We Do?

Equonix Tech Lab’s License Plate Recognizer™ is a Deep Learning-based powerful license plate detection, recognition, and search solution for ANPR/ALPR. It has industry-leading accuracy and works with various camera types and archived video.

Over many years of application Equonix Tech Lab’s License Plate Recognizer has performed and matured, taking into account variables such as movement and high speeds which are natural to the environment of vehicle monitoring. Using still images or video feeds, the product can recognize and capture information located on car number plates and automatically log this information for future inspection. Real-time searching can also be performed on each plate detected, comparing the information gathered with a stored database of license plates.

Features

Key Features of LPR

Automatic Matching

Automatic matching against a watch list with real-time alerting.

Diverse Situation

Detects and recognizes license plates on moving or stationary vehicles

Record & Logs

Records and logs all number plates at a scene for later forensic investigation

Multicamera Support

Vehicles can be tracked across multiple cameras or locations

Effieciency

License plate recognition accuracy up to 98% in actual customer usage

Full Stack Components.

Platforms

  • Server grade plaforms
  • Embedded platforms such as NVIDIA TX2, Qualcomm 820A, 625, 635, NXP’s S32V234 and TI’s TDA2x/3x, Candence Vision P5,P6,

Frameworks

  • Caffe/Caffe2
  • Tensorflow
  • PyTorch
  • SciktLearn

ToolKits

  • Computation backend – CUDA, OpenBLAS
  • Data visualization : Pandas, Tensorboard, Matplotlib
  • Stats workbench : Python

Interested to Know more about this product!

Download the White Paper

Close Menu