Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Yet still no mention of the Fast Hough Transform. Not the randomized approximate one, but fast as in FFT, n²log n fast. We've been using it a lot in, e.g. the automatic vehicle classifier [0, 1]. It has been recently contributed to OpenCV [2] by my colleagues.

The title of the paper (by my company's CTO) "Hough Transform: Underestimated Tool In The Computer Vision Field" [3] still holds true. It describes the FHT algorithm rather well.

[0] http://visillect.com/en/avc

[1] pdf http://www.scs-europe.net/dlib/2015/ecms2015acceptedpapers/0...

[2] http://docs.opencv.org/3.1.0/d9/d29/namespacecv_1_1ximgproc....

[3] https://www.researchgate.net/publication/228573007_Hough_Tra...




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: