Kaggle Carvana Image Masking Challenge Solution with Keras

In this neural network project, we are going to develop an algorithm that will automatically identify the boundaries of the car images which will help to remove the photo studio background.


Each project comes with 2-5 hours of micro-videos explaining the solution.

Code & Dataset

Get access to 50+ solved projects with iPython notebooks and datasets.

Project Experience

Add project experience to your Linkedin/Github profiles.

What will you learn

  • Understanding the problem statement

  • What is image masking

  • Importing the dataset

  • Initializing necessary libraries and understanding its use

  • Installing Tensorflow and Keras framework

  • Fetching masked and non-masked images and visualizing them

  • Performing Data augmentation for increasing the dataset

  • Colour transformation and Random Channel shift

  • Changing color scheme, Brightness, and Saturation

  • Drawing boxes around desired images

  • Visualizing the difference using plots

  • Performing Fast run image encoding on provided masked data

  • Training the Neural Networks

  • Running the Trained neural networks and fetching masked images as output

  • Using RLE to measure the accuracy of the model

  • Saving the final output

Project Description

About the Carvana Image Masking Challenge Neural Network Project:

As with any big purchase, full information and transparency are key. While most everyone describes buying a used car is frustrating, it’s just as annoying to sell one, especially online. Shoppers want to know everything about the car but they must rely on often blurry pictures and little information, keeping used car sales a largely inefficient, local industry.

Carvana, a successful online used car startup, has seen an opportunity to build long term trust with consumers and streamline the online buying process.

An interesting part of their innovation is a custom rotating photo studio that automatically captures and processes 16 standard images of each vehicle in their inventory. While Carvana takes high-quality photos, bright reflections, and cars with similar colors as the background cause automation errors, which requires a skilled photo editor to change.‚Äč


To develop an algorithm that automatically removes the photo studio background. This will allow
Carvana to superimpose cars on a variety of backgrounds. You’ll be analyzing a dataset of photos,
covering different vehicles with a wide variety of year, make, and model combinations.


Similar Projects

Big Data Project Deep Learning with Keras in R to Predict Customer Churn
In this deep learning project, we will predict customer churn using Artificial Neural Networks and learn how to model an ANN in R with the keras deep learning package.
Big Data Project MNIST Dataset : Digit Recognizer Data Science Project
In this data science project, we are going to work on video recognization data and a robust level of image recognization MNIST data.
Big Data Project Time Series Forecasting with LSTM Neural Network Python
Deep Learning Project- Learn to apply deep learning paradigm to forecast univariate time series data.
Big Data Project German Credit Dataset Analysis to Classify Loan Applications
In this data science project, you will work with German credit dataset using classification techniques like Decision Tree, Neural Networks etc to classify loan applications using R.

Curriculum For This Mini Project

01h 39m
02h 30m