In this tutorial, we are going to learn how to use deep learning to remove background from images with TensorFlow. In short, we’ll use DeepLabV3+, a semantic segmentation based model to extract the background and foreground mask from the image. We are going to use these masks to extract the background from the image and leave the foreground intact.

Image background removal is a popular task in the computer vision community. It is used to alter the background in images for a better user experience. For example, while clicking a selfie, you can blur the background (bokeh) using the portrait effect of the camera. This portrait effect is generated by extracting the background from the original image.

Here, we are going to use semantic segmentation algorithms for segmenting the background from images and applying it to alter the background. For this task, we are going to use the DeepLabV3+ architecture, which is trained on human image segmentation.

To learn about the training of DeepLabV3+ on Human Image Segmentation, check the links:

Watch the video for a better explanation of the process of “Remove Photo Background using Deep Learning in Python.”

The entire process of background removal:

In the beginning, we import all the required classes, functions other stuff.

Next, we define height and width as global parameters.

Here, we define a function name create_dir. This function would help in creating a folder or a directory.

Next, we are going to seed the environment to make sure that things are reproducible. While training the DeepLabV3+ model, we have used the same seed.

Now, we are going to create an empty directory called remove_bg. This directory is used to store the processed images.

Here, we load the trained DeepLabV3+ model using the TensorFlow functions.

As we have loaded the trained model, we are going to take a look at the model summary.

Now, we select all the images, whose background needs to be removed.

Next, we are going to loop over all the images and try to extract the name from the image path.

Here, we read the image as an RGB using the OpenCV.

In the above code, we do the following:

The processed original image is now fed to the DeepLabV3+ model as input, which predicts the binary mask.

In the above code, we perform the following:

The above image is used as an input, resized and passed to the trained DeepLabV3+ model. Now, we are going to take a look at them:

In the above code:

In this tutorial, we have learned to remove background from human images using a semantic segmentation model known as DeepLabV3+.

If you have any questions or queries. Contact me:

IDIOT DEVELOPER – https://www.youtube.com/c/IdiotDeveloper/?sub_confirmation=1