# m0dulo/pattern_recognition architecture

> Architecture diagram of the GitHub repository m0dulo/pattern_recognition, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-07-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/m0dulo/pattern_recognition
- Repository: https://github.com/m0dulo/pattern_recognition

## Overview

##### Project type and purpose
- This is a research-style, command‐line pipeline for surface-defect image analysis.
- It loads BMP images, extracts texture features using GLCM in MATLAB, then classifies them via (a) a MATLAB K-nearest‐neighbor script and (b) a PyTorch-based multilayer perceptron.

##### File structure
- dataset/ – raw image data (patches & scratches).
- features/ – CSVs holding extracted features (PCA, rescaling parameters).
- src/ –
– MATLAB scripts (.m) for feature extraction (get_glgm.m, glgm_norm.m, rescaling.m, write.m, load_all_features.m, main.m)
– MATLAB classification (knn.m + run_knn.bat) using config_knn.json
– Python classification (classification.py + run_mlp.bat) using config_mlp.json and PyTorch
– Utility scripts & configs (config_*.json)
- README, LICENSE, .gitignore – project metadata

##### Summarize README insights
- Core pipeline:
1. GLCM texture feature extraction
2. Classification via KNN & MLP (PyTorch)
- References for algorithms and optimizer (Adam)

##### Main components & interactions
A. Data Storage
– dataset/patches & dataset/scratches (input BMP files)
B. Feature Extraction Module (MATLAB)
– main.m calls get_features.m
– get_glgm.m computes co-occurrence matrix features
– glgm_norm.m normalizes them, rescaling.m applies scaling
– write.m & load_all_features.m aggregate results into features/*.csv
C. Configuration
– config_knn.json: KNN hyperparameters
– config_mlp.json: MLP architecture, learning rate, optimizer settings
D. Classification Module
1. MATLAB KNN branch
- knn.m reads features CSV + config_knn.json → predicts labels
- run_knn.bat launches MATLAB script
2. Python MLP branch
- classification.py (PyTorch) loads features CSV + config_mlp.json → trains/tests model
- run_mlp.bat launches Python script
E. External Dependencies
– MATLAB runtime/toolboxes
– Python interpreter + PyTorch

##### Architectural patterns & principles
- Pipeline pattern: clear, linear stages (ingest → extract → classify)
- Modularity: separate folders & scripts for each stage
- Config-driven: JSON files control algorithm parameters
- Dual-environment execution: MATLAB for extraction & KNN; Python/PyTorch for MLP

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Data Storage
    subgraph "Data Storage" 
        direction TB
        DataPatches["dataset/patches\n(BMP)"]:::datastore
        DataScratches["dataset/scratches\n(BMP)"]:::datastore
    end

    %% Feature Extraction Module
    subgraph "Feature Extraction Module (MATLAB)" 
        direction TB
        MainM["main.m"]:::processing
        GetFeaturesM["get_features.m"]:::processing
        GetGLGM["get_glgm.m"]:::processing
        GLGMNorm["glgm_norm.m"]:::processing
        RescalingM["rescaling.m"]:::processing
        WriteM["write.m"]:::processing
        LoadAll["load_all_features.m"]:::processing
    end

    %% Features Output
    subgraph "Features Output (CSV)" 
        direction TB
        PCA_CSV["features/pca.csv"]:::datastore
        Rescaling_CSV["features/rescaling.csv"]:::datastore
    end

    %% Configuration
    subgraph "Configuration Files" 
        direction TB
        ConfigKNN["config_knn.json"]:::config
        ConfigMLP["config_mlp.json"]:::config
    end

    %% Classification Module
    subgraph "Classification Module" 
        direction TB

        subgraph "MATLAB KNN Branch"
            direction TB
            KNNM["knn.m"]:::processing
            RunKNN["run_knn.bat"]:::processing
        end

        subgraph "Python MLP Branch (PyTorch)"
            direction TB
            MLPPy["classification.py"]:::processing
            RunMLP["run_mlp.bat"]:::processing
        end
    end

    %% Connections
    DataPatches -->|"BMP"| MainM
    DataScratches -->|"BMP"| MainM

    MainM --> GetFeaturesM
    GetFeaturesM --> GetGLGM
    GetGLGM --> GLGMNorm
    GLGMNorm --> RescalingM
    RescalingM --> WriteM
    WriteM --> LoadAll
    LoadAll -->|"CSV"| PCA_CSV
    LoadAll -->|"CSV"| Rescaling_CSV

    PCA_CSV -->|"CSV"| KNNM
    ConfigKNN -->|"JSON"| KNNM
    KNNM --> RunKNN

    PCA_CSV -->|"CSV"| MLPPy
    Rescaling_CSV -->|"CSV"| MLPPy
    ConfigMLP -->|"JSON"| MLPPy
    MLPPy --> RunMLP

    %% Click Events
    click DataPatches "https://github.com/m0dulo/pattern_recognition/tree/master/dataset/patches"
    click DataScratches "https://github.com/m0dulo/pattern_recognition/tree/master/dataset/scratches"
    click MainM "https://github.com/m0dulo/pattern_recognition/blob/master/src/main.m"
    click GetFeaturesM "https://github.com/m0dulo/pattern_recognition/blob/master/src/get_features.m"
    click GetGLGM "https://github.com/m0dulo/pattern_recognition/blob/master/src/get_glgm.m"
    click GLGMNorm "https://github.com/m0dulo/pattern_recognition/blob/master/src/glgm_norm.m"
    click RescalingM "https://github.com/m0dulo/pattern_recognition/blob/master/src/rescaling.m"
    click WriteM "https://github.com/m0dulo/pattern_recognition/blob/master/src/write.m"
    click LoadAll "https://github.com/m0dulo/pattern_recognition/blob/master/src/load_all_features.m"
    click PCA_CSV "https://github.com/m0dulo/pattern_recognition/blob/master/features/pca.csv"
    click Rescaling_CSV "https://github.com/m0dulo/pattern_recognition/blob/master/features/rescaling.csv"
    click ConfigKNN "https://github.com/m0dulo/pattern_recognition/blob/master/src/config_knn.json"
    click ConfigMLP "https://github.com/m0dulo/pattern_recognition/blob/master/src/config_mlp.json"
    click KNNM "https://github.com/m0dulo/pattern_recognition/blob/master/src/knn.m"
    click RunKNN "https://github.com/m0dulo/pattern_recognition/blob/master/src/run_knn.bat"
    click MLPPy "https://github.com/m0dulo/pattern_recognition/blob/master/src/classfication.py"
    click RunMLP "https://github.com/m0dulo/pattern_recognition/blob/master/src/run_mlp.bat"

    %% Styles
    classDef datastore fill:#bbf,stroke:#88a
    classDef processing fill:#bfb,stroke:#4a6
    classDef config fill:#fb8,stroke:#fa3

    %% Legend
    subgraph Legend
        direction TB
        L1["Blue = Data Store"]:::datastore
        L2["Green = Processing Module"]:::processing
        L3["Orange = Config File"]:::config
    end
```
