0

I am trying to find options for detecting objects in image. Couple of options I found while researching are openCV and catchroom sdk.

Are there any other options that you have used or know of that works well? My use case is to detect all objects in an image and save them as separate images (with transparent background) ie. it should be able to detect boundaries as well.

It would be great if this can work on device ios/android sdk. If not, I can use some api/service.

Please advise.

user3264361
  • 37
  • 3
  • This is quite broad for this site. It depends on what you want to do/need. Also, what have you tried so far, what technique are you going for (e.g Machine learning, feature descriptors, etc). You should choose one, try to do it and come back if something fails. – api55 Jul 18 '17 at 07:32
  • I know its broad, and may be stackoverflow is not the right place for this question. But, I have no idea about image processing/object detection. That's why I was hoping to may be at-least get some pointers. – user3264361 Jul 18 '17 at 15:42
  • A good start would be to read some of the tons of OpenCV books out there. – SSteve Jul 18 '17 at 17:37
  • I'd suggest you searching for 'caffe' which are both are open source machine learning techniques to understand images. https://www.tensorflow.org/tutorials/image_recognition – Mayer Spitz Jul 27 '17 at 03:15
  • If you're looking for a starting point to integrate TensorFlow, you can also have a look at this [guide and open-source example](https://v-play.net/cross-platform-development/machine-learning-add-image-classification-for-ios-and-android-with-qt-and-tensorflow). – GDevT Sep 05 '18 at 14:15

0 Answers0