Image Similarity Detection (pHash Algorithm)

An online image similarity detection tool based on the pHash algorithm commonly used across major platforms. Supports batch comparison analysis to quickly identify duplicate and similar images.

Bug report

Browser execution mode: Your data is processed in your browser and is not uploaded to the server.

Speed and Stability: Processing speed depends on your device and browser. For large batch work, the desktop version may be more stable.

Loading tool, please wait...

If the online tool fails to load or run, try the desktop tool.https://tools.yikeaigc.com/

Tool Usage

Return to old version

1Select original image

Upload an original image as the baseline. Supports JPG, PNG, BMP, GIF, and more.

2Select comparison images

Select one or more images to compare with the original. Images are not uploaded; all processing is done locally on your device.

3Similarity settings

Hamming distance threshold

Distance ≤5: nearly identical, 5-10: similar, >10: not similar

Hash precision

Higher precision provides more accurate results

Show details

Instructions

Software Usage Instructions

1. Select the Original Image

Click the "Select Original Image" button to upload an image to use as the reference standard. JPG, PNG, GIF, BMP, and WebP formats are supported.

2. Select Comparison Images

Click the "Select Comparison Images" button to choose one or more images for comparison detection.

3. Set the Hamming Distance Threshold

Adjust the Hamming distance threshold (0-15). A smaller distance indicates greater similarity:

Distance = 0: Exactly the same
Distance ≤ 5: Very similar
Distance > 10: Not similar

4. Adjust Hash Precision

Set the number of hash bits. The higher the number of bits, the more accurate the detection:

8x8: Fast detection
16x16: Standard precision
32x32: Ultra-high precision

5. Start Detection

Click the "Start Detection" button, and the tool will calculate the Hamming distance between the original image and each comparison image.

6. View Results

After detection is complete, the results are sorted in ascending order by Hamming distance, with the most similar images listed first. You can view detailed comparison information and statistics.

7. Export Report

Click "Export Report" to save the detection results as a CSV file for further analysis.

FAQ

Hamming distance is the number of positions at which two strings of equal length have different characters. In image similarity detection, it represents the number of differing bits between the hash values of two images. The smaller the distance, the more similar the images. Compared with percentages, Hamming distance provides a more precise and standardized way to assess similarity.

Adjust it based on your detection needs:
Strict mode (threshold ≤ 3): Detects only nearly identical images
Standard mode (threshold = 5): Detects images with high similarity
Lenient mode (threshold ≥ 8): Detects images that may be related

The higher the number of hash bits, the more accurate the detection, but the slower the speed:
8x8: Fast detection, suitable for large-scale processing
16x16: Balances accuracy and speed; recommended
32x32: Highest accuracy, suitable for detailed comparisons

No. This tool runs entirely locally. All image processing is completed on your device, and no images are uploaded to the server, ensuring your privacy and security.

The pHash algorithm is based on perceptual features of images, so the following situations may occur:
• The main color tones and structure of the images are similar
• The hash precision is set too low
• The Hamming distance threshold is set too high
We recommend increasing the hash precision or lowering the threshold to reduce false positives.

Common image formats are supported: JPG/JPEG, PNG, GIF, BMP, WebP. We recommend using JPG or PNG for the best detection results.

The exported CSV report includes:
• Original and comparison image file names
• Hamming distance value
• Similarity percentage
• Hash length and threshold settings
• File size information

Image Similarity Detection (pHash Algorithm)

Loading tool, please wait...

Tool Usage

Detection results

Total images

0

Comparison images

0

Similar images

0

Average Hamming distance

0

Comparison results