| 摘要 |
Here, we introduce Z-webs, including Z-factors and Z-nodes, for the understanding of relationships between objects, subjects, abstract ideas, concepts, or the like, including face, car, images, people, emotions, mood, text, natural language, voice, music, video, locations, formulas, facts, historical data, landmarks, personalities, ownership, family, friends, love, happiness, social behavior, voting behavior, and the like, to be used for many applications in our life, including on the search engine, analytics, Big Data processing, natural language processing, economy forecasting, face recognition, dealing with reliability and certainty, medical diagnosis, pattern recognition, object recognition, biometrics, security analysis, risk analysis, fraud detection, satellite image analysis, machine generated data analysis, machine learning, training samples, extracting data or patterns (from the video, images, and the like), editing video or images, and the like. Z-factors include reliability factor, confidence factor, expertise factor, bias factor, and the like, which is associated with each Z-node in the Z-web. |
| 主权项 |
1. A method for recognition of faces from a still image or video frame, said method comprising:
receiving a still image or video frame through an input interface; preprocessing said still image or video frame; recognizing a first class of image for said still image or video frame; if said first class of image for said still image or video frame comprises face or human, then sending said still image or video frame to a face recognizer module; said face recognizer module accessing a first basis function from a first library of basis functions, stored in a first basis function storage, corresponding to a first component of face; said face recognizer module accessing a second basis function from a second library of basis functions, stored in a second basis function storage, corresponding to a second component of face; a computing processor applying said first basis function across said still image or video frame to detect said first component of face; said computing processor applying said second basis function across said still image or video frame to detect said second component of face; said computing processor accessing a relationship between said first component of face and said second component of face; assigning a first node and a second node on a relational web to represent said first component of face and said second component of face, respectively; assigning a first branch connecting said first node and said second node on said relational web to represent said relationship between said first component of face and said second component of face; assigning a first Z-factor, a second Z-factor, and a third Z-factor to said first node, said second node, and said first branch, respectively; wherein Z-factor is a mathematical set of factors comprising one or more of reliability factor, confidence factor, truth factor, expertise factor, bias factor, knowledge factor, usefulness factor, and relevance factor; said computing processor analyzing said first Z-factor, said second Z-factor, and said third Z-factor for said first node, said second node, and said first branch; said computing processor detecting one or more faces in said still image or video frame, with a fourth Z-factor, based on said analysis step; said computing processor comparing said detected one or more faces with said fourth Z-factor against a library of faces, each with its own said Z-factor, stored in a first face storage; if said detected one or more faces match or correspond to a first face in said library of faces, then outputting identity or identification number of said first face, as identification for said detected one or more faces from said still image or video frame, along with a fifth Z-factor corresponding to said matching or correspondence to said first face. |
