.png)
Letting Data Speak!
Case Study
AI-Powered Tyre Dimension Extraction System
About the Client
The e-commerce platform of one of the world’s largest tire manufacturers.
Challenge
The client faced difficulties in assisting online customers who wanted to purchase new tires but were unsure of their vehicle's tire dimensions. This uncertainty led to reduced conversion rates and potential customer dissatisfaction. The challenge was to develop an automated system that could accurately extract tire dimensions from images, simplifying the purchasing process for customers and increasing sales for the e-retailer.
Key Results
Increased e-commerce conversion rates by 25% for tire purchases.
Reduced customer support inquiries related to tire sizing by 80%.
Improved customer satisfaction scores significantly for the tire purchasing process.
Solution
JashDS developed a sophisticated computer vision system to extract tire dimensions from images:
Implemented an instance segmentation model (YoloV8) for zone detection, identifying areas containing tire dimensions, model, brand, and DOT information.
Developed a cropping and orientation correction algorithm to prepare detected zones for further processing.
Utilized an object detection model for character recognition within the cropped images.
Created a post-processing system with pattern checks to verify the accuracy of extracted tire dimensions.
Designed custom augmentation techniques based on model explanations to improve detection accuracy.
Implemented parallelization of zone processing to enhance system efficiency.
Developed a zone correction mechanism using pattern matching to further improve accuracy.
Utilized Azure ML pipeline to track experiment results and manage the machine learning workflow.
Technologies Used
YoloV8
Mask R-CNN
RTMDet
Azure Machine Learning
Computer Vision
Optical Character Recognition (OCR)
Instance Segmentation
Object Detection
Other Case Study Items
AI Model for Retail Shelf Monitoring
JashDS revolutionized retail shelf management for a major grocery chain by developing an AI-powered real-time monitoring system. The solution utilized advanced computer vision techniques and deep learning models to detect out-of-stock and misplaced products, significantly improving inventory accuracy and enhancing the customer shopping experience while reducing manual labor costs.
AI-Driven Candidate Screening Revolution
JashDS revolutionized a company's hiring process by developing a GenAI-powered candidate screener that reduced time-to-hire by 50% and improved hiring outcomes. The solution leverages advanced language models to conduct dynamic, role-specific interviews, automatically generating and adapting questions based on job descriptions and candidate responses.
AI-Powered Resume-Job Matching Engine
JashDS developed an AI-powered resume-job matching engine for a leading Indian job portal, processing over 1M resumes and 50k job descriptions. The solution employed BERT embeddings and HNSW algorithms to create personalized job recommendations for candidates and streamline resume screening for recruiters, significantly enhancing the job search and recruitment processes.