# Ep120 - Using computer vision to identify pollen for doubled haploid breeding

An episode of [Behind The Science Podcast](https://invisiblenetwork.ai/podcast/1753464681), 16 Apr 2026, 1 h 05 min.

Audio: https://anchor.fm/s/ee2ce360/podcast/play/118283628/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-3-11%2F421841101-44100-2-612661df4e517.mp3

In this episode, we talk with John Albert M. Caraan about his study on Sporesight — an AI-powered computer vision tool that can automatically identify pollen developmental stages in eggplant in real time. Knowing the exact developmental stage of pollen is critical in doubled haploid technology, where microspores at the right stage are cultured in vitro to rapidly produce purebred plant lines. 📚Reference: Caraan JAM, Bautista AM, Lamorin JBV, Madrid VRM. 2026. Sporesight: A real-time computer vision-driven inference tool for pollen development stage classification in eggplant. SciEnggJ. 19(Supplement):015–022. 🤝Behind The Science Podcast is presented to you by Marine & Earth Science Learning Hub, UP Resilience Institute, The Philippine Agricultural Scientist, The Philippine Journal of Fisheries, and SciEnggJ.

Shows are listed from Apple Podcasts' charts and directory, and Podcast Index where it is used. Every show and episode belongs to its publisher and plays from the publisher's own feed; this site hosts none of them.