Abstract: A lighting normalisation method, apparatus and computer program product are disclosed. First, lighting parameters are estimated (110) optimally based on a shading model. After applying segmentation (120), each generated region is assigned are liability based on the stochastic model of that object. This reliability is used to distinguish (130) shadow from object detail. Regions are then further split and merged (140) according to these reliabilities. Finally, the lighting parameters of these regions are calculated and the object is reconstructed (150) to a normalised lighting condition. This technique can be used for an object recognition system, i.e., face recognition applications, as well as for image enhancement, image retrieval, machine vision and related regions.

Abstract: A steganographic method is disclosed to embed an invisible watermark into an image. It can be used for copyright protection, content authentication or content annotation. The technique is mainly based on K-L transform. Firstly a block and cluster step 106 and cluster selection step 108 are performed to enhance the optimization of K-L transform 110 for a given image. Then a watermark is embedded 114 into the selected eigen-clusters. ECC (Error Correction Code) can be employed to reduce the embedded code error rate. The proposed method is characterized by robustness despite the degradation or modification on the watermarked content. Furthermore, the method can be extended to video, audio or other multimedia especially for multimedia databases in which the stored multimedia are categorized by their contents or classes.

Abstract: A method, an apparatus and a computer program product for adaptive, content-based watermark embedding of a digital audio signal (100) are disclosed. Corresponding watermark extracting techniques are also disclosed. Watermark information (102) is encrypted (120) using an audio digest signal, i.e. a watermark key (108). To optimally balance inaudibility and robustness when embedding and extracting watermarks (450), the original audio signal (100) is divided into fixed-length frames (1100, 1120, 1130) in the time domain. Echoes (S′[n], S″[n]) are embedded in the original audio signal (100) to represent the watermark (450). The watermark (450) is generated by delaying and scaling the original audio signal (100) and embedding it in the audio signal (100). An embedding scheme (104) is designed for each frame (1100, 1120, 1130) according to its properties in the frequency domain.

Abstract: A computing system provides a mobile computing environment of settings, accessible programs and accessible files for a user. The computing system is connectable to remote storage and has a local computing environment of settings, accessible programs and accessible files, an operating system, and a local storage. The computing system also includes an application program and a process manager for invoking the application program. The process manager allocates the& execution location of the application program when the application program is invoked, being an intermediary between the application program and the operating system.

Abstract: Conventional approaches or communications systems for data communications in an asymmetric network connection are disclosed. These approaches or systems relate to the problems posed by the difference in bandwidth between the downstream and upstream channels in the asymmetric network connection. In accordance with the invention, a method, a computer product and a communications system in relation to data communications in an asymmetric network connection are disclosed. The data communications is in accordance with a communications protocol wherein a receiver transmits acknowledgement packets for acknowledging data packets transmitted by a sender. The invention includes the step of measuring the interval between the transmission of data from one of the receiver and sender and the reception of a response thereto by the one of the receiver and sender.

Abstract: A method, an apparatus and a computer program product for indexing and retrieving image data using visual keywords (108) is disclosed. Visual keywords (108) are prototypical, visual tokens (104) and are extracted from samples of visual documents (100) in a visual-content domain via supervised and/or unsupervised learning processes. An image or a video-shot key frame is described and indexed by a signature (112) that registers the spatial distribution of the visual keywords (108) present in its visual content. Visual documents (100) are retrieved for a sample query (120) by comparing the similarities between the signature (112) of the query (120) and those of visual documents (100) in the database. The signatures (112) of visual documents (100) are generated based on spatial distributions of the visual keywords (108). Singular-value decomposition (114) is applied to the signatures (112) to obtain a coded description (116).

Abstract: A wireless carrier sense multiple access/collision detection (CSMA/CD) communication system (1) is disclosed which includes a repeater station (R; 10) and a plurality of terminal stations (E, F, G; 30). A wireless uplink communication channel (Fu) provides for one-way communications between each terminal station and the repeater station and a wireless downlink communication channel (Fd) provides for one-way communications between the repeater station and each of the terminal station. The uplink and downlink communication channels operate at different transmission wavelengths. A bit pattern (18) received by the repeater station via the uplink channel is retransmitted via the downlink channel.

Abstract: An apparatus for use in simulated image guided surgery comprises a positional transducer, clamping means located proximate to the transducer, and a processor. The transducer is responsive to a thin flexible member that can be manipulated by a user, and produces signals representative of displacement and rotation of the thin flexible member. The clamping means responds to a controlling signal to apply a predetermined variable clamping force to the flexible member. The processor receives these displacement and rotation signals, and is programmed to plot the path of the flexible member therefrom as it is manipulated by the user. Additionally, the processor produces the controlling signal to the clamping means in response to the instantaneous position along the path. The processor may be coupled to a display device for displaying an image of the instantaneous position of the flexible wire therealong, or other information. The invention also includes a related method for the simulation of image guided surgery.

Abstract: Emerging patterns (EPs) are itemsets having supports that change significantly from one dataset to another. A classifier, CAEP, is disclosed using the following main ideas based on EPs: (i) Each EP can sharply differentiate the class membership of a (possibly small) fraction of instances containing the EP, due to the big difference between the EP's supports in the opposing classes; the differentiating power of the EP is defined in terms of the EP's supports and ratio, on instances containing the EP. (ii) For each instance t, by aggregating (124) the differentiating power of a fixed, automatically selected set of EPs, a score is obtained for each class (126). The scores for all classes are normalized (144) and the largest score determines t's class (146). CAEP is suitable for many applications, even those with large volumes of high dimensional data. CAEP does not depend on dimension reduction on data and is usually equally accurate on all classes even if their populations are unbalanced.

Abstract: A method of processing speech representative of ideograms for speech communication using an asynchronous communication channel (21) is disclosed. The method includes the step of processing speech units of a speech and data indicative of the speech units. Each speech unit is representative of an ideogram or a plurality of semantically related ideograms (500-508). The data indicative of the speech units is discretely communicable on the asynchronous communication channel (21). By communicating the data indicative of the speech units, a substantially low data transmission rate and intelligible speech communication is achieved.

Abstract: A method, an apparatus, a computer program product and a system for voice annotating and retrieving digital media content are disclosed. An annotation module (420) post annotates digital media data (410), including audio, image and/or video data, with speech. A word lattice (222) can be created from speech annotation (210) dependent upon acoustic and/or linguistic knowledge. An indexing module (430) then indexes the speech-annotated data (422). The word lattice (222) is reverse indexed (230), and content addressing (240) is applied to produce the indexed data (432, 242). A speech query (474) can be generated as input to a retrieval module (480) for retrieving a segment of the indexed digital media data (432). The speech query (474, 310) is converted into a word lattice (322), and a shortlist (344) is produced from it (322) by confidence filtering (330). The shortlist (344) is input to a lattice search engine (350) to search the indexed content (342) to obtain the search result (352).

Abstract: A computer-implemented method of generating a user personalized filter for processing files is disclosed, the method comprising the steps of:

Abstract: A method, an apparatus, and a computer program product for organizing and searching catalogs based on compacting a hierarchical structure (150, 500) into related arrays (210, 310, 410, 610; and 220, 320, 420, 620) are disclosed. This involves the steps of: storing indices (1-9) according to categories and subcategories in an array of indices (310), storing the keys (S54-S48) according to the categories and subcategories in an array (320) of keys, and linking each index of the array (310) of indices with one or more corresponding keys of the array (320) of keys corresponding to the category or subcategory associated with the index. The indices of a category or subcategory are stored contiguously in the array (310). Each index has one or more pointers recording the interrelationship of the indices. The keys of a given index are also stored contiguously with keys of any indices at the same corresponding category or subcategory level.

Abstract: A method and system for recognizing the characters on surfaces where alphanumeric identification code (“ID” for short) may be present such as a license plate. The present system is particularly adapted for situations where visual distortions can occur, and utilizes a highly robust method for recognizing the characters of an ID. Multiple character recovery schemes are applied to account for a variety of conditions to ensure high accuracy in identifying the ID. Accuracy is greatly enhanced by taking a comprehensive approach where multiple criteria are taken into consideration before any conclusions are drawn. Special considerations are given to recognizing the ID as a whole and not just the individual characters.

Abstract: A system (100, 200) for tokenization and named entity recognition of ideographic language is disclosed. In the system, a word lattice is generated for a string of ideographic characters using finite state grammars (150) and a system lexicon (240). Segmented text is generated by determining word boundaries in the string of ideographic characters using the word lattice dependent upon a contextual language model (152A) and one or more entity language models (152B). One or more named entities is recognized in the string of ideographic characters using the word lattice dependent upon the contextual language model (152A) and the one or more entity language models (152B). The contextual language model (152A) and the one or more entity language models (152B) are each class-based language models. The lexicon (240) includes single ideographic characters, words, and predetermined features of the characters and words.

Abstract: A computationally efficient method for trusted and dynamic dissemination of digital objects. Related digital objects of various types are grouped, based on their usage and functionality, by an information provider into distribution packages. Trustworthiness of objects contained in a distribution package are certified by a trusted certification authority in the form of a certificate which consists of a body and the certification authority's signature on the body based on a public-key digital signature scheme. The body further consists of the name of the information provider; name of the distribution package; and type, safety checking flag, and digest of each and every object. It is used by end users to verify the trust criteria of any individual or any subset of objects specified by the package.