Develop Computer Vision SDK for Mobile Apps
Budget: $250 – $750 USD
We have plan to develop mobile applications that one of it’s functionality is processing image real time. We needs capable individuals/teams that have excellent experience in image processing, object detection, ai optical character recognition, computer vision and develop SDK in mobile apps, so we can use it in our existing mobile application (based on kotlin/flutter). Solid background in open CV, Python, and AI OCR technologies (ie Tesseract) is a must.
The overall flow is like this:
1. User open the image processing modules.
2. Application will need access to user’s camera.
3. When user point the camera at specific object (ie road name), the ai ocr will translate it to ASCII characters (computer friendly characters).
4. The system will query to database based on OCR result, and return the response to the apps so that users can view the response.
5. The process must be done in real time (preferable) so that when user point the camera at another object different response will be generated.
6. User can take picture (with response above), insert additional information and geotagging the picture and send to backend.
The overall flow is like this:
1. User open the image processing modules.
2. Application will need access to user’s camera.
3. When user point the camera at specific object (ie road name), the ai ocr will translate it to ASCII characters (computer friendly characters).
4. The system will query to database based on OCR result, and return the response to the apps so that users can view the response.
5. The process must be done in real time (preferable) so that when user point the camera at another object different response will be generated.
6. User can take picture (with response above), insert additional information and geotagging the picture and send to backend.