The challenge
An Agro business giant with over 7,500 warehouses and working in agricultural commodities in India and Myanmar was facing issues with the time and accuracy in determining the quality of commodities.
They had to resort to MATT-based testing to accurately assess the quality of the commodity. The quality testing was impractical in dimly lit warehouses. The quality checking process in their laboratories would take around three days to generate a quality report creating a bottleneck in the process.
Three main challenges that the agro-business was facing were
- Turnaround time
- Quality of work
- Fidelity
They needed an AI-based mobile app that could help anyone who wanted to assess the quality of agricultural commodities faster, accurately, and easily.
Our solution
We developed a quality-checking application that used computer vision and AI/ML algorithms to detect and classify the grains and categorize them based on various parameters such as the percentage of defects.
The algorithms were trained with on-field data sets to ensure high accuracy.
The app uses images of the grains of the required sample size, detects the grain type, and checks the quality of each grain with the predefined quality sets. The images will be analyzed partially on the phone and on the cloud (AWS).
Quality standards: The user can create quality standards for different commodities and variants and add the required quality parameters.
Report generation: Once the AI/ML algorithm detects and classifies grains, the report can be generated as PDF, or any format required.
The app was integrated with their database and middleware so that they can manage the information easily.
The main highlights of the app are
Minimal operational skills
The app is designed to ensure user-friendliness and can be used by anyone, anywhere even with a minimal understanding of technology.
Responsive design and compatibility
The application is OS agnostic and can run on any mobile phone. The RAM, memory, and camera quality should not affect the quality check process.
Minimal environment requirements
The app is built to work with minimum requirements like internet, lighting, and additional accessories.
Local language support
The app supports vernacular languages so that it can be used from anywhere.
Offline functionality
The app can function offline by using the images saved on it for classification.
Universal Testing
The app can test the quality of various types of grains such as chana, wheat, and maize.
Business and personal user support
The application is publicly available through a subscription-based model and farmers or business users can subscribe to do quality checking.
Roles and privileges
The multi-user application supports personal and business users for quality checking.
Outcomes
The QC app helped reduce the time and cost associated with quality checking of the grains. The QC app also allows them to conduct regular quality checks of the grains stored in the warehouses, identify quality deterioration, and take timely measures to prevent it.
- Reduced the turnaround time for testing from 3 days to 3 seconds.
- Lowered the cost involved with quality checking.
- Farmers can sell their crops directly to buyers with an instant quality certificate.
- 90% accuracy of quality assessment compared to the lab quality data.
- Improved transparency of the quality checking process.
Tech Stack
Reach out to our team
Schedule a conversation with our technology experts
Share your requirement with us and our team will contact you within one business day to schedule a personalized consultation.
Once you connect with our technology leaders, they will evaluate your specific business case and share a proof of concept with estimates of costs, the effort required in terms of technologies and developers, and the timeline for the process.