Databases
StackOverflow2013
Postsdbo
POComparing SIFT features stored in a mysql database
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POComparing SIFT features stored in a mysql database
    primarykey
    data
    text
    <p>I'm currently extending an image library used to categorize images and i want to find duplicate images, transformed images, and images that contain or are contained in other images.<br> I have tested the SIFT implementation from OpenCV and it works very well but would be rather slow for multiple images. Too speed it up I thought I could extract the features and save them in a database as a lot of other image related meta data is already being held there. </p> <p><strong>What would be the fastest way to compare the features of a new images to the features in the database?</strong><br> Usually comparison is done calculating the euclidean distance using kd-trees, FLANN, or with the <a href="http://userweb.cs.utexas.edu/~grauman/research/projects/pmk/pmk_projectpage.htm" rel="noreferrer">Pyramid Match Kernel</a> that I found in another thread here on SO, but haven't looked much into yet.</p> <p>Since I don't know of a way to save and search a kd-tree in a database efficiently, I'm currently only seeing three options:<br> * Let MySQL calculate the euclidean distance to every feature in the database, although I'm sure that that will take an unreasonable time for more than a few images.<br> * Load the entire dataset into memory at the beginning and build the kd-tree(s). This would probably be fast, but very memory intensive. Plus all the data would need to be transferred from the database.<br> * Saving the generated trees into the database and loading all of them, would be the fastest method but also generate high amounts of traffic as with new images the kd-trees would have to be rebuilt and send to the server.</p> <p>I'm using the SIFT implementation of OpenCV, but I'm not dead set on it. If there is a feature extractor more suitable for this task (and roughly equally robust) I'm glad if someone could suggest one.</p>
    singulars
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. PTQuestion
    1. This table or related slice is empty.
    1. USDarcara
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PO
      singulars
      1. PTAnswer
    2. PO
      singulars
      1. PTAnswer
    3. PO
      singulars
      1. PTAnswer
    1. VO
      singulars
      1. POComparing SIFT features stored in a mysql database
      1. This table or related slice is empty.
      1. VTUpMod
    2. VO
      singulars
      1. POComparing SIFT features stored in a mysql database
      1. USjblocksom
      1. VTFavorite
    3. VO
      singulars
      1. POComparing SIFT features stored in a mysql database
      1. This table or related slice is empty.
      1. VTUpMod
    1. COOpenCV already includes a SURF implementation as well as Kd-Trees for matching (no need for SIFT any more). And: This is not directly related to your question, but you might want to consider matching histograms (or other, global features) first. This way you could possibly reduce the amount of image-pairs to compare with slow high-dimensional features drastically by eliminating all candidates with very different histograms beforehand.
      singulars
      1. POComparing SIFT features stored in a mysql database
      1. USzerm
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload