Leading IT Company envisioned to automate data processing from blueprints for Electrical Engineers
Trantor helped us create a solution that is by far one of the most reliable image and text processing tools on the market. Our customers are thrilled with the ease of use and cost reduction that this tool provides. Kudos to the Trantor team for their innovative approach to custom development
Business problem
The client wanted to create a solution for electrical engineers, enabling them to derive meaningful data from electrical blueprints to enable informed decision-making on costs.
The client through its innovative solution wanted to equip electrical engineers with meta-information on their blue-prints at the click of a button. Existing solutions were limited to giving data using OCR tools. Such solutions gave
Limited Use: Error-prone data – output data was dependent on the quality of input data; and was therefore not reliable
In-efficient process – OCR tools only provided Image capture and not data capture. Data still had to be typed in using manual, error-prone methods
By itself, typed-in data with image capture couldn’t provide any actionable information to the engineers.
Solution delivered
The team, after understanding the client’s process, architected a solution that would use Computer Vision and Machine learning to extract data. This data was further processed to provide actionable information.
The team determined the steps required in providing actionable information from blueprints. Trantor chose Python as the software language. Keeping the blueprint in mind, they chose Computer vision and Machine learning in the backend to convert blueprints into Images and images to data. This data was further processed into structure format by using predefined rule sets.
Blueprints were converted into Images for Computer vision and Machine Learning(ML). The processing flow was tailored to the characteristics of the source material Using Computer Vision, the regions where detected in which the relevant data was present. Machine learning was used for data extraction from detected regions.
The processing flow was tailored to the characteristics of the source material
Using Computer Vision, the regions where detected in which the relevant data was present.
Machine learning was used for data extraction from detected regions.
Results
30% improvement in bottom-line due to informed decision-making
60% reduction in operational cost
95% of data accuracy
Python
ROR
Open CV
Machine Learning (KERAS)
Tesseract APIs
Industry: IT Services
