Navya Bhardwaj

Undergraduate Research in the Neighborhoods

The goal of Navya’s research was to test Hugging face image segmentation algorithms against images in the SEE-Insight Team’s dataset of images. To accomplish this, Navya performed web scraping on the hugging face website and attained a list of all models (230 at the time). She then used the high-performance computer at MSU to process them against 9 images and get fitness values. These values indicate how close the newly segmented image is, as compared to ground truth. Navya found that there was some hope in the models posted on hugging face; although, a problem in their dataset hindered Navya and her research teammates from saying that for sure. Advancements in technology have led to the widespread use of image data in research across many scientific disciplines such as self-driving vehicles and plant biology. However, manual processing and retrieval of specific information from image data can be time-consuming and burdensome for researchers. Automating this process would save researchers’ time and effort.  

Learn more about this and other research in the Neighborhood Engagement Centers.