IndustryMobil Bangladesh Ltd.Work period · 2026Operator-assisted inspection

Mobil Bottle & Label Inspection

Operator-facing visual QA application for product identification, label integrity checks, batch inspection, OCR watermark analysis, configurable markers, and genuine-versus-counterfeit review.

Mobil Bottle & Label Inspection project workflow and system architecture
Project workflow and system architecture overview. Open full-size diagram

Workflow at a glance

  1. Provide product images

    Use an operator-facing inspection interface.

  2. Inspect product and label

    Evaluate product appearance and label regions.

  3. Check image evidence

    Review OCR and configured quality cues.

  4. Operator review

    Record inspection results for assessment.

Project facts & reported results

Streamlit
Interface

Implementation fact

Product + label + OCR checks
Inspection

Implementation fact

Batch review + logs
Workflow

Implementation fact

Project Overview

Problem Statement

Packaging QA requires consistent checks across products and batches while preserving inspection evidence and allowing operators to review uncertain cases.

Approach & Methodology

Built a Streamlit inspection interface for product identification and label review. Image-processing checks, OCR watermark cues, and configurable markers support operator comparison across individual or batch images.

Outcome & Scope

Delivered a Streamlit workflow that combines object detection, classical image processing, OCR, batch upload, and inspection logs.

Technical Challenges & Solutions

1

Variable label appearance

Lighting, positioning, and packaging differences affect comparison.

Solution

Combine configurable markers, geometric checks, and OCR cues with operator review.

2

Making results inspectable

A classification alone does not explain a label issue.

Solution

Present the relevant image evidence and retain inspection logs.

System Architecture

Operator-assisted visual inspection rather than a claimed line-speed benchmark.

Key Components:

Inspection interface

Accept product images and operator settings.

Product analysis

Identify product and label regions.

Quality cues

Evaluate configured image-processing and OCR checks.

Review and logging

Present evidence for operator assessment and record results.

Key Features & Capabilities

Operator-facing product inspection

Single-image and batch review

Product identification and label-region checks

OCR watermark and geometric quality cues

Configurable inspection markers and review logs

Current Scope & Limitations

No production-line throughput or automated authenticity guarantee is claimed.

Inspection settings and image conditions require product-specific evaluation.

Technologies & Tools

Python
Streamlit
YOLO11
OpenCV
Tesseract