Image Processing

Face Recognition

• Deep Learning
  • Introduction to Convolutional Neural Network
    • What CNN see? https://youtu.be/Zanrd7IzZLM
  • Image Classification
    • Cat vs Dog Classifier: https://www.tensorflow.org/tutorials/images/transfer_learning
    • Multiclass Classification: https://www.tensorflow.org/tutorials/images/transfer_learning_with_hub
  • Data Augmentation
    • Random Rotation: https://www.tensorflow.org/tutorials/images/data_augmentation
  • Object Detection
    • YOLOv5: https://youtu.be/GRtgLlwxpc4
    • SSD MobileNet V2: https://youtu.be/yqkISICHH-U
  • Image Segmentation
    • PyTorch & U-Net: https://youtu.be/IHq1t7NxS8k
    • Modified U-Net with MobileNetV2: https://youtu.be/hWN1Xqu8aRE
    • Aerial Semantic Segmentation: https://youtu.be/jvZm8REF2KY
    • Segmentation Model PyTorch: https://github.com/qubvel/segmentation_models.pytorch
    • Segmentation Model Keras: https://github.com/divamgupta/image-segmentation-keras
  • OCR
    • Intro to OCR: https://youtu.be/ZVKaWPW9oQY
    • KTP OCR: https://github.com/hanifizzudinrahman/KTP-ID-Card-with-OCR-to-JSON-File-by-Template-Images-V1
  • Human Keypoint Detection
    • MediaPipe: https://google.github.io/mediapipe/solutions/pose
    • Holistic Keypoint Detection: https://google.github.io/mediapipe/solutions/holistic.html
  • AutoEncoders
    • Intro: https://www.tensorflow.org/tutorials/generative/autoencoder
    • VAE: https://www.tensorflow.org/tutorials/generative/cvae
  • Deep Dream
    • Inceptionism: https://www.tensorflow.org/tutorials/generative/deepdream
  • GAN
    • CycleGAN: https://www.tensorflow.org/tutorials/generative/cyclegan
    • GAN Notebooks: https://github.com/kartikgill/TF2-Keras-GAN-Notebooks
  • Neural Style Transfer
    • Fast Style Transfer: https://www.tensorflow.org/tutorials/generative/style_transfer
    • Using MobileNetV2 TFLite: https://www.tensorflow.org/lite/examples/style_transfer/overview
  • Human Activity Recognition
    • SlowFast
    • Detectron2 + LSTM
  • Tranformers
    • Vision Transformers: https://huggingface.co/docs/transformers/model_doc/vit
    • Fine Tuning the CIFAR-10: https://github.com/NielsRogge/Transformers-Tutorials/blob/master/VisionTransformer/Fine_tuning_the_Vision_Transformer_on_CIFAR_10_with_the_🤗_Trainer.ipynb
• Projects:
  • MNIST Handwritten Digit
  • Classification:
    • Binary:
      • Cat vs Dog
      • Paper vs Plastic
    • Multi-class:
      • Fashion MNIST
      • Rock Paper Scissors
  • Object Detection:
    • YOLOv5
    • SSD MobileNet V2
    • COCO
    • Custom Dataset
  • Segmentation:
    • Self-driving car segmentation
  • OCR:
    • e-KTP
    • BPJS
    • Document
  • Human Keypoint Detection:
    • Pose Detection
  • GAN:
    • Art generation
  • AutoEncoders:
    • Colorization
    • Style Transfer
  • Transformers:
    • Vision Transformers: https://huggingface.co/docs/transformers/model_doc/vit