Industrials - Automatic classification of cars by their model
Industrials
A client requested to automate the labeling of car models in social media photos using a deep convolutional neural network, speeding up the process and freeing up employee time for more valuable tasks.
The solution developed by synvert with Keras and Tensorflow, integrates with business processes via a REST web service and achieves near-human accuracy in identifying around 200 car types.
Initial situation
European Emission Laws requires advertisers to label the car model in any photo shared on social media.
The client would like a way to automate the labelling of car models when they are copied from personal accounts to the company account for advertising purposes.
Architecture
The project has been developed using Keras with a Tensorflow backend.
It is run as notebooks on Databricks, managed via Azure Machine Learning, and exposed for business process integration as a REST web service.
An inference program hosted on AWS Sagemaker can be queried with an image url, and will return the label and associated probability.
Generated benefits
The client is able to automate the process of labelling cars, which frees up the company’s employees’ time for more valuable tasks.
Cars can be classified much faster than with a human labeler (a few milliseconds, compared to 1+ minutes for humans).
Services accomplished by synvert
synvert has trained a deep convolutional neural network to identify car types.
It can identify roughly 200 different types of cars with near-human level accuracy (85%).
Industrials
Vehicle Data Store
Industrials
SoftwareFactory at a leading automotive software company
Consumer Goods & Retail
DevX Impact at a HR-Tech Company
Consumer Goods & Retail
Driving International Expansion for a Leading Online Car Seller
Industrials
Accelerating Cloud-Native Development for a Car Manufacturer
Communications, Media & Telecom
Retail Commission Diagnostics Anomaly Detection
Energy & Resources
Setting up a Reliable and Powerful Platform
Communications, Media & Telecom
Prediction of customer probability to churn
Industrials
Early Detection of Mechanical Issues
Industrials
NLP in Automotive Reporting
Communications, Media & Telecom
Operational Data Lake
Consumer Goods & Retail
Real-Time Marketing
Industrials
Automatic classification of cars by their model
Public Sector
Dieseltech Program
Communications, Media & Telecom
Data Reconciliation
Industrials
Centralized Data Warehouse
Industrials
Data as a Service – BI & Big Data CC
Communications, Media & Telecom
Operational Work/Support in Data Warehousing
Industrials
Erosion Detection with Computer Vision
Communications, Media & Telecom
Development and Implementation of a Fully Automated MLOps Platform
Consumer Goods & Retail
Prediction and Allocation Optimization for stationary Channels
Communications, Media & Telecom
Building a Near Real-Time Recommendation System
Consumer Goods & Retail
Migration AWS data platform to Google Cloud
Communications, Media & Telecom
Design and Development of a Google Cloud-Based Data Platform
Consumer Goods & Retail
Refactoring, shift and new development of Data Services in Google Cloud
Establishment of a Master Data Management Foundation
Industrials
Central Data Lake
Replacement of a complex IBM Datastage structure
CRM analytics and lead management
Standardization of evaluation processes
Development of an ERP data hub
Establishment and further development of a DWH
Development of a group-wide BI platform
Establishment of a new sales reporting system
Source data migration with automation of the source data connection
Cloud self-service BI for data-driven corporate management
Development of various ML use cases with AWS
Replacement of an in-house software development
Company-wide data integration
Implementation of real-time data links
Consumer Goods & Retail
