Hey,
I am interested in working on this project, as I have worked with object detection and segmentation,using Opencv and python. The basic idea is to use pretrained deep learning models,to segment out the most common objects (can train our own model if required) and then image processing to aggregate the pixels space without objects, to generate a final count.
The sample image shows images of bottles , but I would like to know if the object is generic or only restricted to bottles.
A little bit more about myself, if required:
I was a Research Assistant at Robotics Research Centre at International Institute of Information Technology, Hyderabad, for a term of 3 years, (May 2012 - April 2015) and have been a independent researcher/freelancer ever since. Prior to that, I worked in Soliton Technologies - Texas Instruments team, as an Electronic Software engineer / Labview programmer.
During my term as a Research Assistant, I had the opportunity to attend courses in :
1. Image Processing,
2. Computer Vision,
3. Machine Learning and Optimization
4. Natural Language PRocessing (NLP)
I hope to strike a professional relationship with you and proceed to experience the zest and enthusiasm in working on the project to completion.
Thanks,
LN