報(bào)告題目:Geometric Priors: The bridge between natural images and biomedical \r
images
主講嘉賓:龔元浩 助理教授 深圳大學(xué)
邀請(qǐng)人:邱國平教授
時(shí)間:2018年 11月 22日(周 \r
四)下午4:00
地點(diǎn):深圳大學(xué)南校區(qū)基礎(chǔ)實(shí)驗(yàn)樓北座信息工程學(xué)院N710會(huì)議室
報(bào)告摘要:
Priors play fundamental \r
roles in various image processing and deep learning tasks. Geometric priors are \r
particularly interesting because of their intuitive explanation. Minimizing \r
these priors, however, is challenging. In this talk, I will show to model such \r
geometric priors and their related optimization algorithms. More specifically, I \r
will show how to use simple filters to minimize curvatures. These filters are \r
1000 or 10,000 faster than traditional methods.
嘉賓簡介:
龔元浩,深圳大學(xué)助理教授,2007年本科畢業(yè)于清華大學(xué),2015年博士畢業(yè)于瑞士蘇黎世聯(lián)邦理工學(xué)院,主要從事圖像處理、醫(yī)學(xué)圖像分析和計(jì)算機(jī)視覺方面的研究。