Machine Learning Image Classification Project

Machine Learning project 03

Machine Learning Image Classification Project

Last updated: 4 September 2026

Build and evaluate a complete image classification workflow with reproducible Python code, explicit metrics, and honest limitations.

Explore Machine Learning training in VizagView all project ideas

Machine Learning workflow

1. Data: Scikit-learn’s built-in handwritten digits: 1,797 labelled 8×8 grayscale images represented as 64 pixel features.
2. Preprocessing: A stratified train/test split preserves digit proportions and StandardScaler is fitted within the pipeline.
3. Model: KNeighborsClassifier predicts a digit from the five closest training samples in scaled feature space.
4. Evaluation: Holdout accuracy plus per-class precision, recall, and F1 scores.

Complete Python code

Save the code as ml_image_classification.py. The random state and data handling are included so the result can be reproduced and reviewed.

"""Classify 8x8 handwritten digit images with k-nearest neighbours."""

from __future__ import annotations

from sklearn.datasets import load_digits
from sklearn.metrics import accuracy_score, classification_report
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier


def train_model(random_state: int = 42):
    digits = load_digits()
    x_train, x_test, y_train, y_test = train_test_split(
        digits.data,
        digits.target,
        test_size=0.25,
        random_state=random_state,
        stratify=digits.target,
    )
    model = make_pipeline(StandardScaler(), KNeighborsClassifier(n_neighbors=5))
    model.fit(x_train, y_train)
    predictions = model.predict(x_test)
    return model, x_test, y_test, predictions


def main() -> None:
    model, x_test, y_test, predictions = train_model()
    print("Handwritten Image Classification with KNN")
    print(f"Holdout accuracy: {accuracy_score(y_test, predictions):.3f}\n")
    print(classification_report(y_test, predictions, zero_division=0))
    sample = 0
    print(f"Example prediction: {model.predict(x_test[[sample]])[0]}; actual: {y_test[sample]}")
    print("The built-in images are 8x8 grayscale teaching samples, not arbitrary photos.")


if __name__ == "__main__":
    main()

How the pipeline works

A stratified train/test split preserves digit proportions and StandardScaler is fitted within the pipeline.

KNeighborsClassifier predicts a digit from the five closest training samples in scaled feature space. Holdout accuracy plus per-class precision, recall, and F1 scores.

Run the project

1. Create and activate a virtual environment.
2. Install the dependencies with python -m pip install scikit-learn.
3. Run python ml_image_classification.py.
4. Review every printed metric together with the limitation below; a single score never proves deployment readiness.

How to interpret the evaluation

Classification projects report class-aware metrics so majority classes do not hide weak performance. Regression projects report errors in target units and include R-squared or a simple baseline where appropriate. Always verify the split strategy matches how new data will arrive.

Ways to extend the project

Tune the neighbour count, display mistakes with Matplotlib, try PCA, compare SVC, or create a careful preprocessing step for a user-drawn 8×8 digit.

Continue learning Machine Learning

Try the next project, return to the Softenant project library, or explore the Machine Learning course in Vizag for guided data preparation, model evaluation, and portfolio feedback.