Category: Aanya’s Status Reports

Work Accomplished:

• Went to Aldis to test out hypothetical workflow
• Collected additional Aldi product images from GitHub repositories and online sources to refine detection capabilities.
• Researched fine-tuning techniques to adapt YOLOv8 to Aldi-specific products, including augmentation strategies to improve model robustness.
• Began implementing an OpenCV preprocessing pipeline for contrast adjustment and text detection (OCR) to assist in product differentiation.

Progress Status:

I am making steady progress in adapting YOLOv8 for real-time grocery detection. While I have successfully set up the base model and tested inference speed, the next step is fine-tuning it with Aldi-specific images and integrating OCR-based product matching.

Next Weeks Goal:

• Implementing OCR-based product matching, testing label extraction on Aldi-specific items.
• Integrating detected objects with the product database, ensuring proper matching and categorization.

Work Accomplished:

This week, I focused on the initial research and setup phase of the computer vision pipeline for SmartCart.

• Started curating a dataset by sourcing existing grocery product images from GitHub repositories and other publicly available datasets.
• Investigated USFDA food data to map size-to-weight ratios for grocery items, which will be useful for estimating weights when barcode or packaging data is unavailable.
• Reviewed OCR-based text extraction methods for distinguishing visually similar products by identifying brand names and labels.

Progress Status:

I have laid the groundwork for the data acquisition and preprocessing steps necessary for real-time product recognition. The insights gained this week will guide dataset preparation and the initial implementation of YOLOv8.

Next Week’s Goal:

For next week, I plan to move into dataset preparation and initial model setup by:

• Finalizing a structured dataset of Aldi grocery products by combining GitHub-sourced images, USFDA data, and web-scraped product images.
• Implementing OpenCV preprocessing techniques for image enhancement and noise reduction.
• Setting up a baseline YOLOv8 model with an initial subset of grocery product images.
• Developing a basic pipeline to match detected objects with database records, using text recognition and visual similarity scoring.