Detection & segmentation of anatomical structures in retinal images

We are thrilled to announce that our talented final year students from the Machine Vision and Intelligent Systems Lab have swept the awards at the School of Electrical Engineering and Computer Sciences Open House 2023! The trio of projects developed by our students were recognized as the 1st, 2nd, and 3rd Best Industry Adjudged Projects. This is a phenomenal testament to their hard work, ingenuity, and innovative applications of machine learning in practical scenarios.

1st Best Adjudged Industry Project: Headcount of Sunflowers in a Sunflower Crop for Accurate Yield Estimation

Securing the first position is the project titled “Headcount of Sunflowers in a Sunflower Crop for Accurate Yield Estimation”. A unique blend of agriculture and AI, this project is the hard work of Muhammad Ali, Momin Anjum, and Amal Saqib, all from BSCS-9.

Their project successfully uses machine learning algorithms to accurately estimate the yield of a sunflower crop. This innovative approach could revolutionize traditional farming methods, aiding farmers in making data-driven decisions and planning for better crop management.

2nd Best Adjudged Industry Project: Multimodal Estimation of Wheat Phenology using Remote Sensing Imagery

The second spot was claimed by Asad Imtiaz Malik from BSCS-9 for his exceptional project, “Multimodal Estimation of Wheat Phenology using Remote Sensing Imagery”. This project harnessed the power of remote sensing and machine learning to estimate wheat phenology – the life cycle stages of wheat.

Asad’s project leverages cutting-edge technology to improve agricultural practices and productivity, thus taking a significant step towards a more sustainable future.

3rd Best Adjudged Industry Project: AI-enabled Quasi-real-time Water Quality Monitoring for Early Contamination Detection

The third place was awarded to Muhammad Usman Tahir and Jahangir Babar from BSCS-9, and Muhammad Kazim from BEE-11, for their project, “An AI-enabled quasi-real-time water quality monitoring for early contamination detection”.

Their project is an AI-enabled solution for monitoring water quality, aimed at providing early contamination detection. The system’s capacity to provide almost real-time results has the potential to significantly improve public health and environmental management.