×
Portfolio
About Us Blog Events Contact us

Detecting the extent of screen damage in mobile phones,At Scale!

Create more accurate quotes for refurbished phones online with at home mobile screen cracks detection through AI.

Detecting The Extent Of Screen Damage In Mobile Phones

Overview

Blimp deployed a Convolutional Neural Network based visual recognition model on TensorFlow to automate the classification of screen damage on mobile phones. Hence, it was able to achieve screen damage classification of more than 200,000 devices at 90%+ accuracy.

Client

A leading name in the mobile phone refurbishment and replacement market.

Business Requirement

Wanted a way to automatically detect the extent of screen damage in devices.

Preferable Outcome

To eliminate the huge time and cost overheads of manual inspection and tagging of all the new inventory in the warehouses.

Reduce Manual Effort

Reduce

The automated approach reduces the manual effort required in visually inspecting mobile screens. Now, there is no need to hold the screen at different angles to capture the right light to manually visualize the cracks in the screens. The mobile screen cracks detection removes manual classification of the same according to a gradation scale published by the client. It also eliminated manual errors and provided a far more robust data capture mechanism for the client.

Cross-device Damage Detection

The model has been trained to detect and grade screen damage across various mobile phone models and screen types. Thereby providing efficiencies of scale and higher throughput from the assessment stations. The model also provides an automatic assessment of the extent of the screen damage as a function of the screen size and phone type.

Cross-device Damage Detection
Phone Make & Model Detection

Phone Make & Model Detection

The automated screen damage detection system was trained on multiple different brands of smart phones. Hence, as an adjunct information, the algorithm also identifies the Make and Model of the phone from its image. This helps in categorizing the device for further workflows and also in assessing the repair costs for the damage detected.

Our Solution

Here are the technologies we used to create the AI-powered mobile screen cracks detection tool.

Convolutional Neural Networks

A bespoke machine learning model based on Convolutional Neural Networks was deployed using TensorFlow and trained on 8000+ training images across 200+ cracked and normal devices.

Convolutional Neural Networks
Efficiencies Delivered

Efficiencies Delivered

The resultant TensorFlow model was deployed at three different warehouses for the customers for processing mobile phones; training is underway to detect cracked tablet screens next.

Deployment

The resultant TensorFlow model was deployed at three different warehouses for the customers for processing mobile phones; training is underway to detect cracked tablet screens next.

Deployment

Want To Develop Something Like This?

Let`s Talk

Experience
the Next-Level Potential of

Human and Machine Intelligence

mail

Hi! I am

Reach me at

Or call me at