STDF to Wafer Bin Map utility written in Python

Python utilities for loading, plotting, and editing wafer defect maps known as KLA Reference Files (KLARFs)

a kibana plugin to visualize the wafer map

This project aims to process 2D images of semiconductor silicon wafers to identify any defects on the wafers as well as their corresponding locations.

산학협력프로젝트: 머신러닝 기반 Wafer Map Defect Pattern Identification

Wafer map defect pattern classification with Multi-Input Neural Network using Convolutioal and Handcrafted Features

SPECTROview : A Tool for Spectroscopic Data Processing and Visualization.

Mask-aware wafer defect classification using a DenseNet-based CNN with explicit geometry masking and Grad-CAM explainability.

Interactive wafer map visualization and yield analysis for semiconductor test data. Rendering, spatial statistics, failure clustering, lot-level trends, and reticle analysis — pure ES modules, no dependencies.

Utility script for generating wafer-level measurement point layouts with configurable patterns and edge exclusion, designed for semiconductor process development and production workflows.

Utility script for visualization of wafer properties from measurement data, intended for wafer evaluation in process development and production workflows.

Research-driven wafer defect classification framework combining classical ML and CNN-based approaches, with experimental analysis of few-shot learning under severe class imbalance and limited data regimes.

Utility script for visualization of wafer properties from measurement data, intended for wafer evaluation in process development and production workflows.

Automatic scratch detection in semiconductor wafer maps using engineered spatial features and XGBoost.

Semiconductor DMI yield intelligence platform for class-imbalanced defect detection, wafer-map simulation, and chamber traceback

Wafer Map Defect Classification using Deep Convolutional Neural Networks (CNN) with TensorFlow/Keras on the WM-811K dataset.

ResNet-18 wafer defect classifier trained on WM-811K — focal loss, CBAM attention, TTA, and Grad-CAM++ explainability. Macro-F1 0.916 on the 9-class labeled subset.