0

I'm planing to make android app the need of it is to recognize building in the city . I need help in choose the most important unique features in the buildings ,such that the size of the features stay small as it will not be a practical application if the size of the database become large , is running the application offline possible or i should send the features to remote server for processing the similarity between the pictures ?

Abo gaseem
  • 5
  • 5

1 Answers1

1

Actually, you could choose some simple but effective features(building logo, the foreground of the building) for recognizing offline.

In order to make the result more accuracy, you cound send the GPS information back to the server.

Do not only recognize the building by analyzing the picture, sometimes ,you can get more information from the Android.

Good luck.

cyh24
  • 266
  • 1
  • 3
  • 13
  • not all building have logo also they are in different shape and size thanks for reply . – Abo gaseem Sep 30 '14 at 21:41
  • If people wanna take a picture of the building, they must choose some conspicuous features(door, sharpe...).These have the same effect. – cyh24 Oct 02 '14 at 06:56
  • yes that's the logic . do you know SURF algorithm? or you used it before? – Abo gaseem Oct 02 '14 at 18:39
  • yes, I used SURF and SIFT algorithm before. I also used them to recognize the buildings. SIFT is more accuracy but slow, SURF is a better choise I think. GOOD LUCK. – cyh24 Oct 03 '14 at 06:41
  • thank you man i read document about SURF & SIFT for recognize building from one pic only they have >80% success , so you encourage me for use it on the android platform for recognizing the building with the GPS to increase so comparing method ? thanks for reply – Abo gaseem Oct 03 '14 at 12:19
  • You could have a try, but if your data is huge, maybe both these method are useless. I suggest you to use ImageNet if your data is huge. – cyh24 Oct 05 '14 at 05:59