Blur Detector

This function block evaluates whether an input image is blurred by analyzing its sharpness using frequency domain methods.

📥 Inputs

Input Image The image that you want to analyze for blur.

📤 Outputs

Is Blurred? This output returns a boolean value indicating whether the input image is classified as blurred (True) or not (False).

🕹️ Controls

Detection Threshold A slider used to set the threshold value for determining if the image is blurry. Adjusting this value will affect the sensitivity of the blur detection.

Current Blur Value A label that displays the current blur measurement calculated from the input image.

Info Text A helpful description of the detection logic, indicating that if the blur value is below the threshold, the image is considered blurred.

🎨 Features

Frequency Domain Analysis This block uses Fast Fourier Transform (FFT) to analyze the sharpness of the image, allowing for effective identification of blurriness.

Real-Time Feedback The current blur measurement is dynamically updated and displayed, providing immediate insight into the image's sharpness.

📝 Usage Instructions

1. Connect Input: Link an image you would like to assess for blurriness to the Input Image socket.

2. Set Threshold: Adjust the Detection Threshold slider to define how sensitive the blur detection should be. A lower threshold will be more sensitive.

3. Evaluate: Run the function block to analyze the input image. The output will indicate if the image is blurry based on the threshold setting.

📊 Evaluation

When executed, this function block calculates the blur value of the input image, comparing it against the specified threshold to determine whether the image is blurred.

💡 Tips and Tricks

Choosing an Appropriate Threshold

Experiment with different threshold values to find the most accurate sensitivity for your specific images. A lower threshold is better for detecting slight blur, while a higher threshold might work better for more distinct sharpness.

Testing with Various Images

Test the blur detector with images of various quality levels to see how it performs across different scenarios. This can help in fine-tuning the threshold for best results.

Combining with Other Blocks

Consider using this block in conjunction with the Show Image block to visualize the blur analysis along with your image.

Preprocessing Images

Before running the Blur Detector, you might want to apply preprocessing techniques such as Auto Contrast or Histogram Equalization to enhance image quality, making blur detection more effective.

🛠️ Troubleshooting

No Image Data Available

Ensure that the input connected to the block is indeed transmitting valid image data. Verify connections to ensure an image is being passed through.

Unexpected Results

If the output does not match your expectations, consider adjusting the detection threshold or ensure your input image is clear and not artificially blurred by preprocessing steps.