Abstract: A method of privacy oriented insight generation, the method includes (a) receiving by a volatile cache memory unit, during an occurrence of an event that is defined by one or more programmable rules, face-recognition based indicators that indicate that one or more persons were captured by one or more cameras during the occurrence of the event, the one or more cameras are associated with the event and, wherein each person of the one or more persons has a unique face-recognition based indicator that lacks personally identifiable information regarding the person; (b) processing the face-recognition based indicators based on the one or more programmable rules to provide an insight related decision; wherein the processing ends during the event or immediately after a completion of the event; and (c) deleting the face-recognition based indicators from the volatile cache memory unit upon a completion of the processing.
Abstract: Computerized systems, and method and computer readable media. The method may include receiving, by a neural network, input face visual information; wherein the neural network comprises multiple convolutional layers, an embedding layer and one or more conversion layers; generating, by the embedding layer, a face recognition (FR) feature vector that comprises multiple FR feature elements; applying a soft function on the multiple FR feature elements, by the one or more conversion layers, to provide a converted FR feature vector that comprises multiple converted FR feature elements that are non-binary; and generating a binary representation of the face recognition features based on the converted FR feature vector.