Abstract: The present invention discloses the detection of faces in digital images. Rather than subjecting the entire image (1) to computationally intensive face detection analysis, the image is instead segmented into regions (2) each of which has a substantially homogeneous color. Only those regions (2) having a predominantly skin color are then subjected to the face detection analysis. Preferably the face detection analysis is independent of facial color.

Abstract: A method of browsing electronically-accessible resources using descriptions of the resources. These descriptions have descriptor components, which have attributes representative of at least two axes of access to the resources. These descriptions also have links to the corresponding resources. The method first reads the descriptions and displays a number of items (1608). Each one of these items are associated with a corresponding descriptor component of the read description that has an attribute. The method allows the browsing (1602,1603) of the descriptions and their corresponding electronically-accessible resources via the links using the displayed items.

Abstract: The present invention discloses the detection of faces in digital images. Rather than subjecting the entire image (1) to computationally intensive face detection analysis, the image is instead segmented into regions (2) each of which has a substantially homogeneous colour. Only those regions (2) having a predominantly skin colour are then subjected to the face detection analysis. Preferably the face detection analysis is independent of facial colour.

Abstract: A method (100) is disclosed for producing, using a multi-slot presentation skeleton (400), an image presentation from a set of source images (702). The method comprises establishing a duration of the presentation, an average slot duration, and based upon slot template rules, locations and properties of key slots in the skeleton (400). The method then generates (104) candidate groups of sub-image sets from the set of source images, and selects (106) sub-image sets from the candidate groups for the key slots. The method then fills (108) the non-key slots with sub-image sets from the candidate groups, and processes (110) the sub-image sets in the skeleton slots using effect and transition rules, to thereby form the image presentation.

Abstract: Digital image signal interpretation is the process of understanding the content of an image through the identification of significant objects or regions in the image and analysing their spatial arrangement. Traditionally the task of image interpretation required human analysis. This is expensive and time consuming, consequently considerable research has been directed towards constructing automated image interpretation systems. A method of interpreting a digital video signal is disclosed whereby the digital video signal has contextual data. The method comprising the steps of firstly, segmenting the digital video signal into one or more video segments, each segment having a corresponding portion of the contextual data. Secondly, analysing each video segment to provide a graph at one or more temporal instances in the respective video segment dependent upon the corresponding portion of the contextual data.

Abstract: A system is described including a media browser (101) for providing a user with a single user interface for browsing and searching different metadata collections over the Internet (102). A metadata server (212) is associated with each of the metadata collections. When the metadata server (212) receives a request, the metadata server (212) interprets the request and replies with a description that satisfies the request and according to a predetermined scheme. The description contains at least one link which represents a return link which represents a return request to the metadata server (212).

Abstract: A system is described in which a media browser (101), operating as a software application on a user terminal or preferably a server for a number of users, provides a user with a single user interface that facilitates browsing and searching different metadata collections over the Internet (102). A metadata server (212) is associated with each of the metadata collections. When the metadata server (212) receives a request from the media browser (101), the metadata server (212) interprets the request and replies with a description that satisfies the request and according to a predetermined scheme. The description contains at least one link which represents a return link which represents a return request to the metadata server (212).

Abstract: A method of arranging a plurality of images on a page includes the step of arranging the images on the page in accordance with a first predetermined layout pattern. The images are then rearranged in accordance with a “controlled overlapping” rule characterized by a predetermined cost function. Finally, the predetermined cost function is optimized to determine a final coordinate position for each image, thereby to generate a final layout pattern.

Abstract: A method and apparatus for annotating an image (407) is disclosed. The image (407) and a plurality of icons (403) are displayed such that each icon is associated with metadata. At least one of the icons is selected depending on at least one subject of the image (407) and the metadata associated with the selected icon is stored as an annotation of the subject of the image.

Abstract: A method of interpreting an image using a statistical or probabilistic interpretation model is disclosed. The image has associated therewith contextual information. The method comprises the following steps: providing the contextual information associated with the image for analysis; analyzing the additional contextual information to identify predetermined features relating to the image; and biasing the statistical or probabilistic interpretation model in accordance with the identified features.

Abstract: A method of extracting key frames from a video sequence, which video sequence comprises MPEG compressed video data having block motion vectors. The method initially partially decompresses (202) the MPEG compressed video data to obtain block motion vectors and converts (204) the block motion vectors to forward block motion vectors. The method then generates (206) global motion signals and generates (306) dominant global direction clusters. The method then selects (402, 404, 406) potential key frames of the video sequence using the generated dominant global direction clusters. The method lastly decompresses (408) the selected key frames to obtain the extracted key frames.