Abstract: A method for finding and digitally evaluating illegal image material is provided, wherein a data memory is searched for image material. Image material that is found is classified as potentially illegal image material or as legal image material by means of a classification method on the basis of an image content that is presented. The image material graded as potentially illegal has the age of the persons shown determined, and potentially illegal image material which shows at least one person whose ascertained age is below a prescribed age is graded as illegal image material. Biometric features of the persons shown in the illegal image material are detected and are compared with at least one database which contains biometric features. In the illegal image material, at least one further feature which it contains is detected and is compared with at least one appropriate database.

Abstract: A method for supervising a chat connection between at least two terminals is provided. The method includes verification of first conditions, including a camera at each terminal is operated, video streams of each camera are live streams, and/or each video stream contains images of a live person. The connection is allowed if all of the first conditions are met and if one second condition is met. A second condition can include one first subset of the persons is identified as belonging to one defined restricted group and an identity of a second subset of the persons is determined at least on the basis of facial and/or body features and the identified second person is classified as an allowed exception. The method also includes a pre-defined reaction if any of the first conditions and/or all of the second conditions are not met.

Abstract: The invention relates to a method for the training of a classifier based on weakly labeled images and for the binary classification of an image. The training of the classifier comprises the steps of automatically and iteratively determining initial regions of interest for a training set and further on refining said regions of interest and adapting the classifier onto the refined regions of interest by a classifier refinement procedure. Further on, for a query image with unknown classification, an initial region of interest is determined and refined as to maximize the probability value derived at the output of said classifier. The query image is automatically assigned a negative classification label if said probability value is lower than or equal to a predetermined first threshold. The query image is automatically assigned a positive classification label if said probability value is greater than a predetermined second threshold.

Abstract: A method for supervising a chat connection between at least two terminals is provided. The method includes verification of first conditions, including a camera at each terminal is operated, video streams of each camera are live streams, and/or each video stream contains images of a live person. The connection is allowed if all of the first conditions are met and if one second condition is met. A second condition can include one first subset of the persons is identified as belonging to one defined restricted group and an identity of a second subset of the persons is determined at least on the basis of facial and/or body features and the identified second person is classified as an allowed exception. The method also includes a pre-defined reaction if any of the first conditions and/or all of the second conditions are not met.

Abstract: A method for finding and digitally evaluating illegal image material is provided, wherein a data memory is searched for image material. Image material that is found is classified as potentially illegal image material or as legal image material by means of a classification method on the basis of an image content that is presented. The image material graded as potentially illegal has the age of the persons shown determined, and potentially illegal image material which shows at least one person whose ascertained age is below a prescribed age is graded as illegal image material. Biometric features of the persons shown in the illegal image material are detected and are compared with at least one database which contains biometric features. In the illegal image material, at least one further feature which it contains is detected and is compared with at least one appropriate database.

Abstract: A method for recognizing content in an image sequence is provided, the method includes the steps of: detecting at least one face appearing in at least one frame of an image sequence under test; recognizing characteristic features of the at least one face; comparing the characteristic features to known features of characters stored in a database, thereby deciding whether the face represents a known character; detecting and recognizing at least one additional feature in at least one frame of the image sequence under test and at least one relation between the appearance of the known character and the at least one additional feature; and comparing the at least one relation to metadata comprising known relations stored in the database each one assigned to a particular known image sequence, thereby recognizing if the image sequence under test at least partially equals one of the known image sequences.