Problem: We need to recognise a plate or any other ID number on a vehicle. However it's hard to get it shadow free. What methods can be applied to remove shadows effectively? Am i right that there is now way to analyse a picture having shadow of a high contrast?
This problem has been addressed, at least with face recognition problem, and there are many approaches to choose from. Depending on the further processing some approach may be better for you than other, but I would recommend to see, for example, ECCV 2014 paper from Amara et al. "On the Effects of Illumination Normalization with LBP-Based Watchlist Screening". There you have eleven different approaches tested on faces.
Personally I have used only Retinex style methods and some basic filtering (but not on faces)...
http://www.google.fi/url?sa=t&rct=j&q=&esrc=s&source=web&cd=3&ved=0CDQQFjAC&url=http%3A%2F%2Fwww.etsmtl.ca%2FUnites-de-recherche%2FLIVIA%2FRecherche-et-innovation%2FPublications%2FPublications-2014%2FECCV_lbp_Workshop_2014.pdf&ei=NYEvVaaPLsGMsgHMooLgBw&usg=AFQjCNGtKsHTTTW10_CpAVoBulA8y-63YA&sig2=PBEo_S3Hs_YOGXi-ZtN3xg&bvm=bv.91071109,d.bGg&cad=rja
Dear Sami, thank you very for your help! I'm wondering whether object recognition method limits choice of shadow removing method? For example, what should i take in account if my object detection method is Viola-Jones?
You can check the work of Jose M. Álvarez on road detection. He extensively explored the issue of shadow detection and supression:
http://josemalvarez.net/
- Badges
- Science topic
- Similar topics
- Analytical Chemistry
- Extraction