Talk:Histogram of oriented gradients

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia

The paper by Dalal and Triggs must be cited in the introduction, not just somewhere below! — Preceding unsigned comment added by 80.156.43.137 (talk) 09:29, 9 December 2013 (UTC)[reply]

Introductory comment[edit]

This article is rather inaccessible to beginners. I would have done the changes myself, but I came to this article precisely because I was not sure I understand HOG features. For one, it doesn't say, in simple words, a HOG descriptor is so-and-so, and this is how they can be computed. The rest of the theory and motivation behind the HOG descriptor is quite useful, but without a concise description of what they are, this page sort of misses its purpose.

Muxdevil (talk) 05:05, 22 November 2010 (UTC)[reply]

Orientation binning gradient image selection criteria for counting[edit]

As a matter of practical detail the computation of a histogram is easy--counting of things in range oriented bins, however, the text in the article does not say how the n histogram cells in 180 or 360 degrees have their gradient image points selected or found for counting?

  • For what range of distances surrounding the given gradient image pixel are considered for selection?
  • Do the counts get truncated as soon as a gradient image pixel is considered blank / background / too near to zero, etc.
  • In the human detection system referred to, are these 9 directions for selection points the 8 surrounding pixel gradient values & the pixel itself, or more?
  • Are the gradients selections compared to a given threshold prior to being counted (or not) into a bin?

The finding or selection criteria should be spelled out more clearly so that a reader does not have to guess how it is done or read & understand the scholarly paper(s) written on this topic.

Could some knowledgeable person please revise the text so as to clarify it in this regard? Oldspammer (talk) 20:42, 16 February 2012 (UTC)[reply]

External links modified[edit]

Hello fellow Wikipedians,

I have just modified one external link on Histogram of oriented gradients. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 18 January 2022).

  • If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
  • If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 11:55, 4 November 2017 (UTC)[reply]

Needs an Example Image[edit]

there are no explanatory images in the article, which is about image processing. 135.180.116.182 (talk) 00:00, 11 February 2024 (UTC)[reply]