"I'm a deep expert!"
Hi,
I am an engineer specializing on computer vision and machine learning applications. I have years of experience working on production-level computer vision based applications such as smart surveillance, object detection and tracking, semantic and instance segmentation, face recognition, person-reidentification, facial attribute detection, and various other applications.
I have a very broad knowledge from image processing algorithms to machine learning and deep learning techniques. I have a very good knowledge in python programming, openCV (both C++ and Python), and other libraries/tools neccesary such as tensorflow, keras, pytorch, etc. Moreover I am good with designing custom network layers, loss fucntions, etc depending on the requirements and also to optimize the models.
The problem seems to be regression based, and if sequence of images are involved in predictions, then a combination of CNN-LSTM can be used to determine the final quality score. I would like to know more information to come up with a better approach. The trained models will be able to be converted CoreML for iOs).
Regards,
Dilina