Ask Your Question

Flower Detection

asked 2013-08-05 12:20:28 -0500

updated 2013-08-05 12:21:22 -0500


I'm developing a flower detector and would be glad if anyone has some ideas I could try.

Current directions I was thinking of:

  1. Training Viola & Jones
  2. HOG + SVM
  3. Object by parts - I tried and haven't got good results.

Any other directions you can suggest?

Thanks in advance, Gil.

edit retag flag offensive close merge delete


I think you hitted the most frequent used techniques for object detection: You could look into class specific randomn forests which is sortlike svm.

StevenPuttemans gravatar imageStevenPuttemans ( 2013-08-05 12:34:20 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2013-08-06 01:27:03 -0500

Siegfried gravatar image

Hi, as StevenPuttemans already answered, contains your list the most frequent used techniques. But you should also take a look at the Bag-of-Words approach. It is widely used for image classification and object categorization. There exist a project at Visual Geometry Group from Andrew Zisserman with the goal to recognize the species of flowers using bag-of-words. On the project website you can find publications, a dataset and test your own images by uploading the image file.

edit flag offensive delete link more


Thanks for your answer.

What about LBP+SVM? Is it a better choice then HOG+SVM?


GilLevi gravatar imageGilLevi ( 2013-08-06 02:52:59 -0500 )edit

And regarding Bag-of-words, I'm more interested in detection, not recognition. Is BOW a good approach also for detection?

GilLevi gravatar imageGilLevi ( 2013-08-06 03:04:35 -0500 )edit

Hi, LBP+SVM is also a possible technique. On the PASCAL VOC'06 object detection challenge the results of LBP+SVM and HOG+SVM are similar (see for example:

Siegfried gravatar imageSiegfried ( 2013-08-06 03:13:30 -0500 )edit

I am not an expert in BOW but I guess that the bag-of-words approach is less suitable to detect object (flowers) in an image. BOW computes and counts features in the whole image and compares them with a model. No spatial relation of the features is stored. So you have no information where the features which best match the flower-model are located in the image. As a conclusion i think that if you already have a hypothesis (region-of-interest) and you want to know if it is a flower you can use BOW. But for detecting the ROI of the flower in the image BOW is not suitable. In the cited project ( they use Grabcut to segment the flowers from the background and use then BOW for classification.

Siegfried gravatar imageSiegfried ( 2013-08-06 03:38:04 -0500 )edit

Just a side-note: localization is typically important for an instance classification via BoW. It can be easily achieved by using a spatial pyramid, i.e. a form of grid and compute in each grid a BoW-descriptor which are in the end concatenated to one descriptor. See also .

Guanta gravatar imageGuanta ( 2013-08-06 08:40:59 -0500 )edit

Thank you all for your answers.

My first attempt is taking each patch in the image, re sizing it to 400X400 pixels, then dividing it into 4 100X100 patches and extracting rotation invariant uniform LBP codes. These are fed to a previously trained SVM.

Current results are far from satisfactory, but I'm working on tuning the SVM to get better performance.

Any comment on what I've done so far?


GilLevi gravatar imageGilLevi ( 2013-08-06 11:32:43 -0500 )edit

BoW can be extended to constellation models using spartial relation and voting for center of the oject.

mrgloom gravatar imagemrgloom ( 2013-08-14 07:02:04 -0500 )edit

Question Tools



Asked: 2013-08-05 12:20:28 -0500

Seen: 2,255 times

Last updated: Aug 06 '13