Abstract: A method for detecting differences between two digital images includes the steps of: transforming the images by resizing the images in order to get identical image sizes, by aligning pixels of the images and by normalizing colors of the images; determining plural binary masks from the pixels of the transformed images, each binary mask being composed of one element per couple of pixels of the transformed images having same coordinates; determining plural energy functions, each energy function being the sum of a first term representative of transformed images and of one binary mask and of a second term which is only dependent on said one binary mask; minimizing the energy function over other plural energy functions; and selecting the binary mask corresponding to the minimized energy function.

Abstract: The present invention concerns a method for deriving from an arbitrary local image descriptor a descriptor that is invariant under arbitrary mirror symmetries. For a point of interest, pi, for which the descriptor is to be determined a direction, ODi is determined. The local patch from which the descriptor is to be extracted is mirrored along ODi if a “smaller than” relation does not hold a feature extracted from the left half of the local image patch, in regard of ODi, compared to the right half of the local image patch. Thereby, the local patch is brought into a normalized intrinsic orientation. Thereafter, the descriptor is extracted. Examples include a mirror symmetry invariant version of Lowe's SIFT.

Abstract: A method for generating representations of visual characteristics of images is presented. The method includes receiving search criteria. The criteria include images to be searched, query images and expected result sets, and a retrieval metric. The method identifies objects within each image and selectively generates a representation of visual characteristics of each image using descriptors from an inventory of descriptors in accordance with the retrieval metric. The method compares the representations of the query image to representations of the images to be searched and determines a search result. The search result is compared to the expected result. If the results do not match, the generating, comparing and determining steps are re-executed with reselected descriptors based on the search result and the retrieval metric. The re-execution continues in a trial-and-error approach until acceptable search results are achieved. When achieved, the method encodes the process for generating the representations.

Abstract: A system and method is presented for identifying a plurality of products within a collection of product images in an online shopping environment. The method includes providing the collection of images representing products offered for sale; receiving an input search criteria from a prospective customer. The criteria include at least one of a query color. The method also includes identifying and extracting colors within the collection of images based on a presence of significant colors in an image; and comparing and matching the query color to the identified and extracted significant colors. The method continues by determining, within a predetermined range of accuracy, products from within the collection of images having the matched query color; and presenting the determined products to the prospective customer. In one embodiment, the presentation is provided by means for a graphical user interface.

Abstract: The present invention pertains to a method and a system for identifying a specific image within a flow of images. The system calculates a reference index of the specific image, and current indexes of the current images of said flow. The index has the form of an ordered and finite set of values encoding the content of the current image. The system also compares the reference index with the current index of the current image of the monitored flow. It is thus possible to detect a specific image within a flow with great precision and extremely fast while being robust during major photometric alterations.

Abstract: A process for presenting information in a multimedia file from a query implemented by a user on an open computer network including a multiplicity of computer terminals enabling transmission of graphical data displayed in multimedia files, the process including selecting at least one image comprising an object to be retrieved, adaptively analyzing a global image to isolate a zone of interest comprising a graphical element which is an object of a query and calculating a set of visual signatures for each object, comparing visual signatures of extracted objects and images contained in the multimedia files to find similar objects stored in the multimedia files, and constructing a file including a set of responses resulting from the comparison.