CASE STUDY

Computer Vision Model Automates Explicit Content Detection & Reduces Image Processing Time by 99%

Expertise Delivered

Backend
Data Science
QA

Industry

Automotive

Our client,

Being an INC5000 honoree, McQueen Autocorp is a leading US-based used car selling company with a buyer network spread across the entire United States.

McQueen Autocorp offers a nationwide modern car selling service, facilitating sellers with an instant offer for their car(s) using price prediction algorithms and real-time bids from an extensive network of licensed buyers. With 600,000 vehicles sold annually, McQueen Autocorp has seen a 300% increase in reve-nue over the course of 3 years.

Disclaimer - The name McQueen Autocorp is a placeholder as there is an NDA signed between both parties.

Challenge

  • Our client is a used car selling company; car sellers need to upload their car details and images on the platform to sell their cars.
  • Users would upload close to ~120,000 images/month on the client’s platform to sell off their cars.
  • Some of these uploaded images would contain racy/adult content instead of relevant vehicle images.
  • Manual approval of these massive volumes of images daily involved a team of 15 human agents and a lot of time.
  • Such excessive levels of manual processing gave way to serious time sinks and errors in approved images.
  • This led to poor customer experience and tarnished brand image.

Solution

The Maruti Techlabs team studied the client’s process and ideated a solution to improve the expensive, time-consuming, and error-prone process.

Our AI team worked towards building a custom Computer Vision model to design a binary image classification model. The model worked in two steps:

Step 1 - Detect car images and flag the rest 

  • The model was trained with thousands of different car images from the client’s data-base.
  • After training the model, it would classify the image into two categories - car and non-car. 
  • The model would identify the images of cars/vehicles, flag the rest and notify the team via Slack notifications.
  • Once the image of the car was identified, the model also performed obstacle detection to detect if any other unidentified object was blocking the car’s appearance.
  • The model further performed image tagging and classified images into those of cars and blocked vehicle numbers.

Step 2 - Verify car models against the details provided 

  • After identifying the car images, we went a step further and trained the model to verify if the car model and make in the picture matched the car model and make mentioned by the user in the form.
  • For this, we included the car make and model recognition dataset to train the Computer Vision model.
  • The model would verify the car model in the image against that mentioned in the form based on the training. If the model did not find both to be a match, it would be flagged, and the team would be notified of the same via a Slack notification.

The Computer Vision model automated two steps of the verification process. We used ~1500 images for training the model. With training datasets, the model could classify pictures with an accuracy of 85% at the time of deploying in production. 

Human assistance is required for those instances where the model has a confidence score of less than 80%. For this, we integrated the CV model with Slack, where the team is notified of images falling under the confidence threshold. The team then reviews and classifies the images accordingly.

This human intervention in specific instances is treated as a feedback loop, where the model records the feedback and uses it to learn and improve its performance over time.

With supervised learning and model upgrades, the model's accuracy has now increased to 90% in the course of 6 months.

Achieve unmatched speed and precision in image processing.




Phone

Don't take our word for it, take theirs!

Technology Stack

CV Model for Image Recognition and Flagging - Automotive.png

reduction in processing time

saved annually

hours saved per month

Our Development Process

We follow Agile, Lean, & DevOps best practices to create a superior prototype that brings your users’ ideas to fruition through collaboration & rapid execution. Our top priority is quick reaction time & accessibility.

We really want to be your extended team, so apart from the regular meetings, you can be sure that each of our team members is one phone call, email, or message away.

Our Development Process.png
Our Process
Acquiring Image Datasets
The first step we carry out is the analysis of business goals and creation of a database of images extracted from multiple sources. Structured, relevant, and quality data is prepared to serve as a guideline for future comparison.
Labeling Datasets
After structuring the image datasets, we label the images to make the database more search-friendly. Filtering similar patterns and making object comparisons become more efficient with this method. We use variables like color, contour, intensity, and size to create labels and organize the data.
Processing the Data
We then test the labeled dataset against training data by processing it through meticulous quality checks. We run a series of automated processes to enhance the images like adding or removing pixels, removing noise, sorting misclassified data, and so on.
Data Augmentation
To improve the training data, we modify the images with a variety of techniques like flipping (horizontally or vertically), cropping, blurring, zooming, and compression. This way, we train the model for more accurate image recognition results.
Understanding the Image
In the final stage, we ensure that the model is able to correctly interpret and categorize the object identified. The software is now adequately trained to recognize images from new input sources. With the iterative process, we ensure that the model continues to enhance its capabilities over time.
Acquiring Image Datasets
The first step we carry out is the analysis of business goals and creation of a database of images extracted from multiple sources. Structured, relevant, and quality data is prepared to serve as a guideline for future comparison.
Labeling Datasets
After structuring the image datasets, we label the images to make the database more search-friendly. Filtering similar patterns and making object comparisons become more efficient with this method. We use variables like color, contour, intensity, and size to create labels and organize the data.
Processing the Data
We then test the labeled dataset against training data by processing it through meticulous quality checks. We run a series of automated processes to enhance the images like adding or removing pixels, removing noise, sorting misclassified data, and so on.
Data Augmentation
To improve the training data, we modify the images with a variety of techniques like flipping (horizontally or vertically), cropping, blurring, zooming, and compression. This way, we train the model for more accurate image recognition results.
Understanding the Image
In the final stage, we ensure that the model is able to correctly interpret and categorize the object identified. The software is now adequately trained to recognize images from new input sources. With the iterative process, we ensure that the model continues to enhance its capabilities over time.

More social proof incase you're still on the fence

Our Clients Review
Our Happy Clients
Review Everything
Why choose Maruti Techlabs?
14+ years experience
Start as quickly as week
Recurring cost of training and benefits - $0
Risk of failure? Next to none. 4.8/5 NPS on Clutch
Certified PMs & delivery teams
Rapid deployment & on-time delivery of projects
Complete transparency
Robust communication across shared channels
Agile & lean startup methodology
Experience across 16 industries

Years of Experience

Professionals

Projects Delivered

NPS on Clutch

Services
  • Software Product Development
  • Artificial Intelligence
  • Data Engineering
  • DevOps
  • UI/UX
  • Product Strategy
Case Study
  • DelightfulHomes (Product Development)
  • Sage Data (Product Development)
  • PhotoStat (Computer Vision)
  • UKHealth (Chatbot)
  • A20 Motors (Data Analytics)
  • Acme Corporation (Product Development)
Technologies
  • React
  • Python
  • Nodejs
  • Staff Augmentation
  • IT Outsourcing
Company
  • About Us
  • WotNot
  • Careers
  • Blog
  • Contact Us
  • Privacy Policy
mtechlogo.svg
Our Offices

USA 
5900 Balcones Dr Suite 100 
Austin, TX 78731, USA

India
302, Regency Plaza,Nr. Anandnagar Crossroads,
Satellite, Ahmedabad, Gujarat- 380015

clutch_review
goodfirms_review
Social
Social
Social
Social
©2024 Maruti TechLabs Pvt Ltd . All rights reserved.

  • Software Product Development
  • Artificial Intelligence
  • Data Engineering
  • DevOps
  • UI/UX
  • Product Strategy

  • DelightfulHomes (Product Development)
  • Sage Data (Product Development)
  • PhotoStat (Computer Vision)
  • UKHealth (Chatbot)
  • A20 Motors (Data Analytics)
  • Acme Corporation (Product Development)

  • React
  • Python
  • Nodejs
  • Staff Augmentation
  • IT Outsourcing

  • About Us
  • WotNot
  • Careers
  • Blog
  • Contact Us
  • Privacy Policy

USA 
5900 Balcones Dr Suite 100 
Austin, TX 78731, USA

India
302, Regency Plaza,Nr. Anandnagar Crossroads,
Satellite, Ahmedabad, Gujarat- 380015

©2024 Maruti TechLabs Pvt Ltd . All rights reserved.