CNN-Based Object Classification

Overview

Convolutional Neural Network models that classify objects and digits into predefined categories and sub-categories. The trained models were further fine-tuned for additional object classes, producing strong cross-domain performance. Outcome: Reusable CNN classifiers that can be fine-tuned to new object classes with minimal data and effort.

Architecture & Pipeline

flowchart LR
    n0["
Image Dataset
Labeled samples
"] n1["
Preprocessing
Augmentation · normalize
"] n2["
CNN + DNN
TensorFlow
"] n3["
Fine-tune for New Classes
Transfer learning
"] n4["
Predicted Class
Hierarchical output
"] n0 --> n1 n1 --> n2 n2 --> n3 n3 --> n4 classDef step0 fill:#f1f5f9,stroke:#64748b,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step1 fill:#ecfeff,stroke:#06b6d4,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step2 fill:#f0fdfa,stroke:#0d9488,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step3 fill:#ecfdf5,stroke:#10b981,color:#1e293b,stroke-width:2px,rx:10,ry:10; classDef step4 fill:#fffbeb,stroke:#f59e0b,color:#1e293b,stroke-width:2px,rx:10,ry:10; class n0 step0; class n1 step1; class n2 step2; class n3 step3; class n4 step4;

End-to-end flow derived from this project's scope and tech stack. Tap View Fullscreen for a larger view, or scroll horizontally on small screens.

Key Features

  • CNN and DNN architectures for hierarchical classification
  • Fine-tuning workflow for new object categories
  • Validated accuracy across predefined classes
  • Tech Stack:** Python, TensorFlow