Skip to main content

Image Similarity

Description​

Image similarity is a tool that allows the user to see how similar two images are. It is useful for finding duplicate images or images that are very similar to each other.

Settings​

Mode​

Image similarity mode, here are the options:

Absolute Difference (ABS):​

Calculates the absolute difference between corresponding pixel values of two images. This method is simple and fast, but it is sensitive to noise and slight variations in images. It does not consider the human visual system's perception, and a high ABS value does not necessarily mean that the images look different to the human eye.

Structural Similarity Index Measure (SSIM):​

SSIM is a perception-based model that considers image degradation as perceived change in structural information, while also incorporating important perceptual phenomena, including both luminance masking and contrast masking terms. It is a full-reference metric, meaning it requires an initial uncompressed or distortion-free image as a reference. SSIM values range from -1 to 1, where 1 indicates perfect similarity, 0 indicates no similarity, and -1 indicates perfect.

Peak Signal-to-Noise Ratio (PSNR):​

PSNR is a widely used metric for measuring the quality of lossy image and video compression. It is derived from the mean squared error (MSE) and is defined in logarithmic scale to account for the wide dynamic range of pixel values. PSNR values are typically between 30 and 50 for video compression, with higher values indicating better quality. However, PSNR may not always be consistent with human eye perception, which is why SSIM was developed as an alternative.

Gray value threshold​

The gray value threshold is used to convert the image to grayscale. The default value is 0, which means that the image is not converted to grayscale.

Reference Image (Server)​

The reference image is the image that is used to detect the object in the scene. Path within server to the reference image file.

Reference Image​

The reference image is the images that is used to detect the object in the scene. Path within server to the reference image file. Image within the UI computer to the reference image file.

Display Results​

Overlay Results​

Whether to draw the results on top of the image frame.