0
$\begingroup$

I'm new to Computer Vision and training a TensorFlow neural network using VGG16. The problem is quite simple:

I'm training in a custom dataset to detect and localize numbers in a 100x100 image. The numbers (0 to 9) can appear in all x and y within the 100x100 image size. The model works very well when a single object (number) appears.

enter image description here

However, when I have multiple objects in the image, the model can not handle the task.

enter image description here

The expected result is something like this:

enter image description here

How can I do it? The problem is in the model.predict() and how I pass the image, but I don't have a clue of what to do now.

$\endgroup$

1 Answer 1

0
$\begingroup$

I found the solution to the problem.

The VGG was not made to detect and localize multiple objects at once. We can do some workaround to make it work like I described earlier, but it's just too complicated and very computationally expensive.

So I decided to move on and use R-CNN and YOLO for multiple object detection and localization. This models are designed for this.

I hope this helps anyone who has the same problem as me.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.