Scribd
Upload
7 views10 pages

Mid Eval

Uploaded by

mlbyad.273
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
7 views10 pages

Mid Eval

Uploaded by

mlbyad.273
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Application Development

and
Hardware-Software Integration
Mid Evaluation : BTech. Project

Presented by:
Aaditya Deshpande (210003027)
Devansh Gupta(210003028)

Indian Institute of Technology Indore


S U P E RV I S O R
DR . ANKUR MIGLANI
A S S O C I AT E P R O F E S S O R
M E C H A N I C A L E N G I N E E R I N G D E PA RT M E N T

1
Introduction
• Rice Adulteration

• Classification of Damages

• Leveraging Machine Learning

• Accessibility to the common man

Fig 1: Classes of damages in rice grain

2
Objectives

• To create an end-to-end Android application that can host


the trained ML model for the classification of rice as
Basmati or Non-Basmati.

• To integrate the grain-pro software into the existing


machine to classify the damage in the rice grain. Fig 2: GrainPro software

3
Methodology
• Classify rice as Basmati and Non-Basmati based on parameters provided by FSSAI.

• Milled Basmati Rice should have


1. Length > 6.61mm

2. Breadth < 2.00mm

3. Aspect Ratio (Length/Breadth) >= 3.5

• Android Studio and Kotlin.

• Zero cloud / third-party dependency.

• ML model in the Android application package.

4
Current Progress
• Android application development is completed.

Fig 3: Initial landing view to select Fig 4: Output displayed Fig 5: Processed image saved
the grid image to the device
5
Future Work
• Software integration for the Classification of damage.

Fig 6: Classification and inferencing with GrainPro Fig 7: Summary of the Inferences

6
Future Work
• Development of Closed Loop system.

Raspberry pi-
camera system

Random sample of
Grain Pro Software
Single rice grain

Dispensing the
Arduino-motor
grain into the right
Fig 8: Random grain sampler and dispenser system
compartment

Fig 9: Proposed closed loop system

7
Timeline

October 2024 November 2024


August 2024 September 2024 Publishing android
Building a closed loop
Analysis of existing model ML model preparation and application on Google
system, integrating
and cloud based web- android application Play Store
GrainPro Software with
application development Analysis of Grain Pro
Hardware.
Software

8
References
1. https://amitdhavale.pythonanywhere.com/
2. https://github.com/ultralytics/ultralytics/tree/main
3. https://www.sciencedirect.com/science/article/pii/S0168169922001284
4. https://ai.google.dev/edge/litert/android
5. https://github.com/gupta-devansh/Grainpro-Android

9
THANK YOU!

10

You might also like