Abstract: Systems, methods, and software for operating an image processing system are provided herein. In a first example, a method of operating an image processing system is provided. The method includes identifying object pixels associated with an object of interest in a scene, identifying additional pixels to associate with the object of interest, and performing an operation based on a depth of the object in the scene on target pixels comprised of the object pixels and the additional pixels to change a quality of the object of interest.

Abstract: Systems, methods, and software for operating an image processing system are provided herein. In a first example, a method of operating an image processing system is provided. The method includes identifying object pixels associated with an object of interest in a scene, identifying additional pixels to associate with the object of interest, and performing an operation based on a depth of the object in the scene on target pixels comprised of the object pixels and the additional pixels to change a quality of the object of interest.

Abstract: When using Web intelligence (“Webint”) to collect information regarding a target social network user, one of the most valuable pieces of information is the target user's List-Of-Friends (LOF). In some cases, however, the LOF of the target user is not accessible in his profile. Herein are described methods and systems for identifying the LOF of a target user. An analysis system crawls the profiles of social network users, other than the target user, and reconstructs the LOF of the target user from the crawled profiles.

Abstract: A computer-implemented method for text processing includes processing at least one body of text including semantic elements. Syntactic roles of the respective semantic elements are recognized, and the body of text is segmented into individual semantic constructs. At least one selected semantic element is removed from the semantic constructs, so as to produce respective nuclear semantic constructs. Occurrence frequencies of the respective nuclear semantic constructs are computed. An action is invoked with respect to one or more of the nuclear semantic constructs whose occurrence frequencies meet a predefined condition.

Abstract: Systems and methods of automated ontology development include a corpus of communication data. The corpus of communication data includes communication data from a plurality of interactions and is processed. A plurality of terms are extracted from the corpus. Each term of the plurality is a plurality of words that identify a single concept within the corpus. An ontology is automatedly generated from the extracted terms.

Abstract: Method of automated anomaly detection includes obtaining a corpus of interaction data. Regular interaction data is identified from the corpus of interaction data with a processor. New interaction data is received. The processor compares the new interaction data to the identified regular interaction data The processor identities anomalies in the new interaction data.

Abstract: Methods and systems for tracking mobile communication terminals based on their identifiers. The disclosed techniques identify cellular terminals and Wireless Local Area Network (WLAN) terminals that are likely to be carried by the same individual, or cellular and WLAN identifiers that belong to the same multi-mode terminal. A correlation system is connected to a cellular network and to a WLAN. The system receives location coordinates of cellular identifiers used by mobile terminals in the cellular network, and location coordinates of WLAN identifiers used by mobile terminals in the WLAN. Based on the location coordinates, the system is able to construct routes that are traversed by the terminals having the various cellular and WLAN identifiers. The system attempts to find correlations in time and space between the routes.

Abstract: Methods and systems for locating occurrences of a search pattern in a body of text. A processor searches the text for one or more occurrences of a pattern. Both the text and the pattern comprise symbols of some alphabet. In preparation for the search, the processor defines a respective bit-map for each alphabet symbol. Using the bit-maps, the processor carries out a highly efficient process of searching the text for occurrences of the pattern. The processor then scans the pattern backwards using the bit-maps, symbol by symbol, attempting to match the symbols of the pattern to the corresponding symbols of the text. If a match is not found, the processor calculates the size of the jump to the next position in the text based on the accumulated results of the evaluations up to the current position.

Abstract: Methods and systems for keyword spotting, i.e., for identifying textual phrases of interest in input data. In the embodiments described herein, the input data comprises communication packets exchanged in a communication network. The disclosed keyword spotting techniques can be used, for example, in applications such as Data Leakage Prevention (DLP), Intrusion Detection Systems (IDS) or Intrusion Prevention Systems (IPS), and spam e-mail detection. A keyword spotting system holds a dictionary of textual phrases for searching input data. In a communication analytics system, for example, the dictionary defines textual phrases to be located in communication packets—such as e-mail addresses or Uniform Resource Locators (URLs).

Abstract: Methods and systems for locating Mobile Stations (MSs) that are served by a Wireless communication Network (WLN) in a given geographical area. The MSs typically communicate with other parties, or connect to the Internet, through the WLN, wherein Base Transceiver Stations (BTSs) serve as the WLN front ends from the MSs perspective. A Stimulating Apparatus (SA) monitors control messages that the BTSs in the area of the SA broadcast to MSs. The SA analyzes the control messages that it receives, selects one transmitting BTS and creates a modified version of the control messages that it has received from the selected BTS. The SA then broadcasts the modified messages on behalf of the selected BTS by using its frequency channel. The discrepant transmission parameters are designed to stimulate any MS that receives them to induce a network event from which the MS location may be estimated.

Abstract: Methods and systems for managing the actions that are applied to packet flows by packet processing systems. A packet processing system maintains a flow table, i.e., a list of active flows and respective actions to be applied to the flows. The system classifies each incoming packet into a respective flow, and processes the packet in accordance with the action that is specified for this flow in the flow table. Typically, the system deletes a packet flow from the flow table when it becomes inactive, e.g., when no packets belonging to the flow arrive within a certain time-out period.

Abstract: Methods and systems for monitoring, analyzing and acting upon voice calls in communication networks. An identification system receives monitored voice calls that are conducted in a communication network. Some of the monitored voice calls may be conducted by target individuals who are predefined as suspects. In order to maintain user privacy, the system selects and retains only voice calls that are suspected of being conducted by predefined targets. The techniques disclosed herein are particularly advantageous in scenarios where the network identifiers of the terminal used by the target are not known, or where the target uses public communication devices. In accordance with the disclosure, content-based identifiers such as speaker recognition or keyword matching are used.

Abstract: People are counted in a segment of video with a video processing system that is configured with a first set of parameters. This produces a first output. Based on this first output, a second set of parameters is chosen. People are then counted in the segment of video using the second set of parameters. This produces a second output. People are counted with a video played forward. People are counted with a video played backwards. The results of these two counts are reconciled to produce a more accurate people count.

Abstract: Methods and systems for malware detection techniques, which detect malware by identifying the Command and Control (C&C) communication between the malware and the remote host, and distinguish between communication transactions that carry C&C communication and transactions of innocent traffic. The fine-granularity features are examined, which are present in the transactions and are indicative of whether the transactions are exchanged with malware. A feature comprises an aggregated statistical property of one or more features of the transactions, such as average, sum median or variance, or of any suitable function or transformation of the features.

Abstract: Systems and methods of detecting irregular events include the extraction of values for measure in each of a plurality of notifications. The extracted values are stored in a measures database and a distribution is calculated for the values of each of the measures. The extracted values are compared to the calculated distributions to determine if an irregular event has occurred. An irregularity alert is produced if an irregular event has occurred.

Abstract: Systems and methods search video data for objects that satisfy a general object description. A database is populated with identified objects and object characteristics detected in video data with at least one identifier that specifies video image data. At least one search parameter is received that presents a general object description. The database is queried based upon the received at least one search parameter. At least one identifier is returned from the database based upon the at least one search parameter.

Abstract: A video monitoring system and method comprises a first camera at a first camera location configured to video record a first monitored area, wherein a georeference location of the first monitored area is known, and a virtual 3D model of the monitored zone that includes the first camera location and the first monitored area, wherein the virtual 3D model is georeferenced to a physical location. The system further comprises a processor configured to receive the video recording of the first monitored area and to overlay the video recording of the first monitored area onto a part of the virtual 3D model that corresponds to the georeference location of the first monitored area. A display is also connected to the processor and configured to display the virtual 3D model of the monitored zone overlaid with the video recording of the first monitored area.

Abstract: A method of monitoring the amount of time spent in a specified area by an individual comprises employing a first camera to automatically create one or more entrance images, each entrance image containing a face of an entering individual that passes a first location, and storing each entrance image in a database along with a corresponding entrance time that the entering individual passed the entrance location. A second camera is also employed to automatically create an exit image of a face of an exiting individual that passes a second location, and the exit image is recorded along with the corresponding exit time that the exiting individual passed the exit location. The exit image is then compared to the entrance images in the database to identify a matching entrance image containing the same face as the exit image. A stay time is then determined for the exiting individual by determining the difference between the entrance time corresponding to the matching entrance image and the exit time.

Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.

Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.