Image matching finds an image amongst a million others in less than a second
Our image matching technology is robust against several types of transformations, detecting not only the exact same image, but also modified versions of the original image and object matches
Fast, Robust, and Scalable Technology
LTU’s vision aims to enhance computer vision to provide with fast and accurate results.
Our visual intelligence aims to recognise retail products, decorated objects, pictures, books, textbooks, art paintings, and logos.
Image matching current version : sig. 72
1 query retrieval is under 1 second for 1 million image index on only 1 CPU core
Used with categorization and keywords, it enables innovative search functionality that adds a new dimension sites and stock photo portals making the user experience more relevant and engaging. Keywords can be assigned to each image in the collection. Keywords can then be used to restrict the query result to some specific categories.
LTU Engine can handle multiple types of image transformations to identify a match. Image transformations can be broadly divided into several groups:
- Geometric transformations: Includes scale changes, rotations, translations, flips and projective transformations.
- •Photometric transformations: Includes colour space conversions, gray level transformations, changes in hue, brightness and contrast.
- Filtering effects: Includes noise and smoothing.
- Structural transformations: Includes composite images, i.e. images that have been overlaid on top of each other, overlay of text, adding of borders and cropping.
- Recompression: Due to different compression algorithms (such as jpg) and different image encodings, information can get lost and artifacts may appear.
- Images derived from mobile
- Grayscale: Colour image converted to shades of gray.
- Brightness: Luminance settings correspond to the degree of luminance within each image pixel. For a distant observer, the word ‘luminance’ is substituted by the word ‘brightness’, which corresponds to the sparkling parts of an object or image.
- Contrast: The difference between the darkest and the brightest parts of an image.
- Colour change (Hue): Changes in colouration; hue is a complex colour obtained by a mix of basic colours – Red, Blue, Green.
Often images may be modified with a combination of the above transformations. However, the LTU image matching technology is robust even in those instances. The matching technology easily matched the above combination which includes Gray scale, blur, re-encoding, projective transformation and overlay composite transformations, Resizing of the original image, Arbitrary Rotations, Projective distortions, Photometric Transformations.
LTU Engine computes a visual signature for every image that describe its visual content in terms of colour, shape, texture and many higher order visual features and stores it in a reference database. These descriptors are also called image DNAs can be compared at extremely high speed with other image signatures from a database up to millions of images.
LTU has developed the most robust and scalable visual search technologies including image recognition, fine image matching, colour search and similarity search based on shape and texture. LTU Tech's algorithms process queries within a second, the best retrieval time available today.