Image similarity search

While comparing two or more images, the first question that comes to our mind is what makes an image similar to another? We can say that one image is equal to another if all their pixels match. However, a small change in the light, angle, or rotation of the camera represents a big change in the numerical values of the pixels. Finding ways to define if two images are similar is the main concern of services such as Google Search by Image or TinEye, where the user uploads an image instead of providing keywords or descriptions as search criteria.

Humans have natural mechanisms to detect patterns and similarity. Comparing images at content or semantic level is a difficult problem and an active research field in computer vision, image processing, and pattern recognition. We can represent an image as a matrix (two-dimensional array), in which each position of the matrix represents the intensity or the color of the image. However, any change in the lighting, camera angle,...