Abstract: The invention relates to a method for recognizing faces in digital images consisting in providing for a knowledge base which contains face images and is hierarchical into several classes each of which comprises different images of the same person. The invention relates to pre-processing said knowledge base in such a way that a minimization of variance in each class and a maximization of variance between different classes are simultaneously obtainable, thereby making it possible to form a vectorial base comprising the discriminant component of said knowledge base. The comparison of a recognizable face with a pre-processed reference face such as the knowledge base and an eventual reconstruction of a recognized face are also disclosed.

Abstract: A method, apparatus or software are disclosed for verifying a parameter value against a predetermined threshold function in which a sequence of reference values is retrieved, each reference value being associated with a respective sampling point N, said reference values representing a threshold function at said respective sampling points N; a profile type is associated with said threshold function, said profile type being arranged, when combined with said sequence of reference values, to provide an approximation to said threshold function for a region of said threshold function between said reference values; a parameter value is received for verification against said threshold function, said parameter value being associated with a discrete time P; said sequence of reference values is combined with said profile type to provide an approximation of said threshold function; and said parameter value is verified against said approximation of said threshold function.

Abstract: A waste comminuting device includes a comminuting housing (1), a rotor (2) provided with a plurality of protruding peripheral knives, stationary counterblades supported by the comminuting housing, the minimal distance separating each knife from each associated counterblade, during the passage of the knife opposite the counterblade, being equal to an operating clearance, called the cutting size. For each knife (3, 4, 5, 6) and for at least one direction of rotation of the rotor, at least two non-aligned counterblades (7 and 11, 8 and 12, 9 and 13, 10 and 14) associated with the knife are adapted so that the distance separating the leading edge (45) of the knife and the leading edge (48, 56) of a counterblade at the moment when the leading edge of the knife opposes the leading edge of the counterblade, is different from one counterblade (7-10) to another (11-14).

Abstract: A method identifying faces from facial images called query images, associated with at least one person, including a learning phase using learning images and a recognition phase used to identify the faces appearing in query images. The learning phase includes filtering the images, applied on the basis of a group of at least two learning facial images associated with the at least one person, enabling selection of at least one learning image representing the face to be identified. The recognition phase uses only the learning images selected during the learning phase. Filtering is performed using at least one of the thresholds belonging to the group including: a maximum distance taking at least account of the membership of the vectors in a cloud constituted by the vectors; and a maximum distance between the vectors and vectors rebuilt after projection of the vectors on a space associated with said cloud of vectors.

Abstract: A system is provided for locating at least two points of interest in an object image. One such system uses an artificial neural network and has a layered architecture having: an input layer, which receives the object image; at least one intermediate layer, known as the first intermediate layer, consisting of a plurality of neurons that can be used to generate at least two saliency maps, which are each associated with a different pre-defined point of interest in the object image; and at least one output layer, which contains the aforementioned saliency maps. The maps include a plurality of neurons, which are each connected to all of the neurons in the first intermediate layer. The points of interest are located in the object image by the position of a unique global maximum on each of the saliency maps.

Abstract: The invention relates to a method for recognizing faces in digital images consisting in providing for a knowledge base which contains face images and is hierarchical into several classes each of which comprises different images of the same person. The invention relates to pre-processing said knowledge base in such a way that a minimization of variance in each class and a maximization of variance between different classes are simultaneously obtainable, thereby making it possible to form a vectorial base comprising the discriminant component of said knowledge base. The comparison of a recognizable face with a pre-processed reference face such as the knowledge base and an eventual reconstruction of a recognized face are also disclosed.

Abstract: A method, apparatus or software are disclosed for verifying a parameter value against a predetermined threshold function in which a sequence of reference values is retrieved, each reference value being associated with a respective sampling point N, said reference values representing a threshold function at said respective sampling points N; a profile type is associated with said threshold function, said profile type being arranged, when combined with said sequence of reference values, to provide an approximation to said threshold function for a region of said threshold function between said reference values; a parameter value is received for verification against said threshold function, said parameter value being associated with a discrete time P; said sequence of reference values is combined with said profile type to provide an approximation of said threshold function; and said parameter value is verified against said approximation of said threshold function.