ga★
Garvit AroraPORTFOLIO 2026 — AI & SOFTWARE

DEEPSAFE

Computer Vision / Deep Learning — Deepfake Detection Research Prototype

BRIEF

Synthetic facial media requires structured preprocessing pipelines that can isolate facial regions consistently before feeding frames into convolutional classification architectures.

ENGINEERING IDEA★

Build a modular Python pipeline combining OpenCV face localization and cropping with a TensorFlow CNN training architecture, paired with an interactive Streamlit prototype interface.

TOOLS USED

Python · OpenCV · TensorFlow · Streamlit · NumPy

PROJECT TYPE

*Computer Vision / Deep Learning
*Research Prototype (Training Pipeline + Demo UI)
01 // SYSTEM ARCHITECTURE & VISUAL SCHEMATIC
PROTOTYPE // OPENCV FACE EXTRACTION + TENSORFLOW CNNSTATUS: RESEARCH PROTOTYPE
OPENCV ROI EXTRACTION // ABSTRACT MESH01 // TRAINING & PREPROCESSING PIPELINE• OpenCV Face Bounding Box & Crop• NumPy Normalization & Tensor Resizing• TensorFlow CNN Feature Extraction Code02 // STREAMLIT DEMONSTRATION INTERFACE• Interactive Media Upload & Inspection UI• NOTE: Demo UI generates simulated predictions• Documented honestly as a research prototype
02 // 4-STAGE WORKFLOW PROGRESSION
STAGE 01

Media Ingestion & Frame Decoding

Load input imagery and convert color spaces into normalized NumPy arrays.

STAGE 02

OpenCV Face Localization & Cropping

Detect facial bounding boxes, extract aligned face regions, and resize tensors for CNN input.

STAGE 03

TensorFlow CNN Training Pipeline

Convolutional feature extraction layers and binary classification head coded in TensorFlow.

STAGE 04

Streamlit Demonstration Interface

Interactive prototype UI illustrating the user flow (currently operating with simulated demonstration predictions).

03 // IMPLEMENTATION, OUTCOMES & KEY LEARNINGS
IMPLEMENTATION DETAILS
  • ★Programmed OpenCV face-detection and image-preprocessing routines to isolate facial crops from raw input images.
  • ★Authored TensorFlow convolutional neural network architecture and training pipeline scripts for real-versus-synthetic classification experiments.
  • ★Built a Streamlit interactive prototype interface to demonstrate the end-to-end inspection workflow.
  • ★Documented the current engineering state transparently: separating the implemented training/preprocessing code from the Streamlit demonstration layer's simulated predictions.
VERIFIED OUTCOMES
  • ✓Established a working computer vision preprocessing and CNN training codebase in Python, OpenCV, and TensorFlow.
  • ✓Created an interactive Streamlit demonstration interface for presenting the deepfake inspection workflow concept.
REFLECTIONS & NEXT STEPS
  • →Bridging the gap between offline CNN training scripts and production inference requires serializing validated model checkpoints and benchmarking generalization across unseen compression artifacts.
  • →Next engineering milestone is replacing the Streamlit demo's simulated prediction step with live inference against a validated model checkpoint.