Circle Detector

This function block is utilized to detect circular patterns within an input image. It employs the Hough Circle Transform technique to locate and outline circles within images effectively.

📥 Inputs

Image Any This input accepts any image data that may contain circular patterns for detection.

📤 Outputs

Result The output image showcasing the detected circles, marked for easy identification.

Positions The coordinates of the detected circles, allowing for further processing or analysis.

Number of Circles The total count of detected circles in the image.

Circles Detailed information about the detected circles in the format specified by the Circle type, which can include various attributes of the detected circles.

🕹️ Controls

dp A slider used to adjust the inverse ratio of the accumulator resolution to the image resolution used during circle detection.

Edge Detection A slider to set the higher threshold of the two passed to the Canny edge detector (the lower one is twice smaller).

Threshold This slider sets the center threshold for the circle detection method.

Min Distance A parameter that determines the minimum distance between the centers of detected circles.

Min Radius A slider to specify the minimum radius of circles to be detected, defined as a percentage of the input image's width.

Max Radius A slider to set the maximum radius of circles to detect, also defined as a percentage of the input image's width.

🎨 Features

Flexible Parameters Users can fine-tune several parameters to optimize circle detection for various kinds of input images.

Visual Feedback The resulting output image clearly marks the detected circles, offering real-time visual feedback on the detection process.

📝 Usage Instructions

1. Connect Input: Link your input image, which may contain circles, to the Image Any input.

2. Adjust Parameters: Use the sliders to set appropriate parameters to optimize circle detection according to the specific characteristics of your image.

3. Evaluate: Run the block to detect circles. The output will include an image with detected circles and relevant data about the positions and counts.

📊 Evaluation

On execution, this function block analyzes the input image and returns an output with the identified circles drawn on it along with their positions and counts.

💡 Tips and Tricks

Adjusting Edge Detection

If you are struggling to detect circles, try adjusting the Edge Detection parameter higher or lower based on the image clarity.

Testing Different Radius Values

Experiment with different values for Min Radius and Max Radius based on the expected sizes of circles in the input image for optimal results.

Using Preprocessing

You can use preprocessing techniques like Blur or Image Threshold blocks to enhance edges in the image, making it easier to detect circular patterns.

More Accurate Detection

Using a higher Min Distance value can help to reduce the detection of false positives by preventing overlapping detections.

🛠️ Troubleshooting

No Circles Detected

If no circles are detected, try adjusting the parameters, especially the Threshold and the Min Radius settings to find a suitable configuration based on your input image.

Soft or Blurred Circles

If circles appear soft or are not well-defined, consider applying a preprocessing method such as a Gaussian Blur to your input image before it reaches this block.