COMPUTER VISION / IMAGE PROCESSING

Automated Coin Detection

Translating physical currency into structured visual data.

A computer vision project built with OpenCV to detect circular coin objects from images using preprocessing, edge-based analysis, morphological operations and geometric detection.

OPENCV PYTHON NUMPY TKINTER
VISION_LAB / COIN_DETECTION 2024
Coin detection result
ENGINE OpenCV
LANGUAGE Python
NUMERICAL LIBRARY NumPy
INTERFACE Tkinter
01 / OVERVIEW

Detecting shape through image structure.

The project explores how classical computer vision can convert an image containing physical coins into machine-readable information.

Instead of relying on a trained deep learning model, the system uses a deterministic image-processing pipeline. Noise is reduced, object boundaries are emphasized, and circular geometry is analyzed to identify candidate coins.

CORE IDEA Clean the image first, then detect geometry from clearer visual boundaries.
02 / IMAGE PROCESSING PIPELINE

From raw pixels to detected coins.

The system uses a multi-stage processing pipeline to progressively reduce visual noise and improve the quality of circular object detection.

01

Input Image

The source image is loaded and prepared for preprocessing.

→
02

Gaussian Blur

Reduces image noise and smooths small visual irregularities.

→
03

Adaptive Threshold

Separates foreground objects under varying local lighting conditions.

→
04

Morphology

Erosion and dilation improve object boundaries and remove small artifacts.

→
05

Circle Detection

Circular candidates are identified using geometry-based detection.

03 / DETECTION PREVIEW

Visualizing the detected objects.

Once candidate circles are detected, the system marks them directly on the image. This makes the output easier to inspect and helps evaluate whether the preprocessing pipeline isolated the intended coin boundaries.

EDGE ANALYSIS CIRCULAR GEOMETRY OBJECT COUNTING
Detected coins visualized on the source image s
04 / FEATURES

Built around practical image-processing behavior.

A

Adaptive Analysis

Adaptive thresholding allows the preprocessing stage to respond to local brightness differences, helping separate coins from the surrounding background.

B

Shape-Based Detection

The system focuses on circular geometry rather than semantic recognition, making it a classical computer vision solution.

C

Morphological Cleanup

Erosion and dilation are used to refine binary masks, reduce small artifacts and strengthen useful contours.

D

Placement Guidance

The interface guides users toward clearer coin placement, helping reduce detection errors caused by overlap or poor object positioning.

05 / APPROACH

Why classical computer vision?

01
Interpretable pipeline

Every transformation can be inspected, making it easier to understand why a detection succeeds or fails.

02
No training dataset required

The system relies on image structure and geometry rather than model training.

03
Lightweight experimentation

Thresholds and preprocessing parameters can be adjusted rapidly to study the effect on detection results.

06 / STACK

Technology used.

PYTHON OPENCV NUMPY TKINTER IMAGE PROCESSING EDGE DETECTION MORPHOLOGICAL OPERATIONS
COMPUTER VISION LAB

From physical objects to structured visual information.

This project became an early exploration of how deterministic image-processing techniques can transform raw visual input into usable data.