OCR

Optical Character Recognition

OCR is used for translating ‘images of text’ into ‘text’. Such text is then understandable by machines, and can be used for further processing. KritiKal has developed a strong in-house OCR engine, which has powered various products and applications like vehicle license plate recognition, container text identification, industrial inspection, document digitization etc. We have experience in designing custom OCR solutions based on client specific requirements; including real time optimized embedded electronic implementations of OCR. The solutions include localization of regions containing text in images, and then using core OCR engine to ‘read’ text out of these sub-images.

APPLICATIONS OF OCR

The Vehicle shows two lanes of traffic, with a sign board on the left, saying the speed limit is 30 mph. KritiKal's Sign Board Recognition is based on their Vision Systems strength and is seen here, detecting this sign board and enabling this intelligence for the driver / vehicle to take appropriate action. KritiKal is a leading Automotive Technology provider. KritiKal's work ranges from Electric Vehicle Chargers to Advanced Driver Assistance Solutions (ADAS), working towards, Driverless Cars or Autonomous Driving. KritiKal's Traffic Sign OCR & Road Sign OCR, is a part of the ADAS Bucket, which enables the vehicle to see, recognize and comprehend any text available on the roads. Also known as Scene Text Recognition, this helps Vehicles read Traffic Signs, Road Signs, for example, STOP, Speed Limits, etc. and provide intelligent inputs to the driver or the vehicle to take appropriate action.

Traffic & Transportation

The Image shows a Black Sedan, halting at a checkpoint, where KritiKal's License Plate Recognition System has automatically recognized its Number Plate or License Plate and Digitized the data, to record it for further use. KritiKal's License Plate OCR based on KritiKal's robust OCR Engine, is their ANPR Technology, which allows License Plates of Vehicles to be Recognized and logged digitally. This can be applied for Security Purposes in any facility like a Mall, an Industrial Setup, Apartment/Residential Setups, Public Spaces like Airports, Stadiums, or even Offices. KritiKal offers the License Plate Recognition as a combined package in their proprietary product - KLiPR, which can help City Authorities catch Traffic Offenders, by capturing the License Plate, through CCTV Cameras and can help Security and Parking Operations Automation at Establishments, with a screenshot of the driver, License Plate Data as well as scanning for suspicious attachments under the vehicle.

License Plate Recognition

KritiKal is a leader in Vision Systems & Vision based Technology. One strong application of the same, comes out in making Container & Port Logistics more efficient, by capturing Container Details either through images or Video, using intelligent overlaid algorithms. This can be integrated with the Gate, where the trucks come in to the premises, by capturing the Container Details from a moving container, or even with stationary containers stocked in the yard.

Container Number Identification

The Image shows a Manufacturing Unit, an Engineer working on a Silver Sedan, propped up on a hydraulic lift, with its hood open. The image is linked with KritiKal's OCR Technology, which helps capture and log important data during the manufacturing, production or assembly processes, such as the Vehicle's Chassis Number, the Vehicle Identification Number, etc. which are printed or inscribed on the Vehicle's Surface, helping the Quality Control Process.

Vehicle Surface Text Recognition

This image shows brown packaged cardboard boxes, with product details in a sticker on each box. These boxes are travelling over black conveyor belts, inside an industrial setup. KritiKal's OCR Technology, is shown here, automatically capturing Product ID & Quality Inspection details from the Packages, as they move on the Conveyor Belt, using Algorithms, intelligently overlaid on the footage captured of this production unit, through strategically placed Cameras.

Industrial
Inspection

An image of a desk with papers showing analytics & data. KritiKal's Document OCR Technology, is shown digitizing this text, to make it available as text, instead of as an image.

Document Digitization

FEATURES

KritiKal’s Robust OCR Engine helps you increase efficiency across various domains.  Here are the features that make it the best in the Industry:

  • Robust across different font types, sizes, symbols
  • Ability to segment and recognize characters, words, text lines, paragraphs and full pages
  • Ability to split and recognize glued characters, as well as to glue and recognize broken characters
  • Hi-performance OCR engine, with pre-processing and de-skewing and normalization techniques 

Upto 100% accuracy is achievable when the print and image quality is good. With drop in image quality, the accuracy drops gracefully, and can be better than or close to what human beings can read.

200 to 600 Characters Per Second (CPS)is readily achievable depending on the CPU speed. 

Color, gray scale or bi-tonal images with a 200 DPI or greater resolution can be used as input. Custom solutions have been built around OCR on videos, integrating frames with varying text resolution (and motion blur). 

The output includes ASCII or UNICODE character strings, and confidence values (for decision/data fusion). We have also combined character level output to interpret word or higher level data.

The OCR Engine supports Linux and Windows based platforms. Custom embedded platform implementations have also been made, optimized for memory and run-time.

Close Menu