| 摘要 |
Specification covers new algorithms, methods, and systems for artificial intelligence, soft computing, and deep learning/recognition, e.g., image recognition (e.g., for action, gesture, emotion, expression, biometrics, fingerprint, facial, OCR (text), background, relationship, position, pattern, and object), large number of images (“Big Data”) analytics, machine learning, training schemes, crowd-sourcing (using experts or humans), feature space, clustering, classification, similarity measures, optimization, search engine, ranking, question-answering system, soft (fuzzy or unsharp) boundaries/impreciseness/ambiguities/fuzziness in language, Natural Language Processing (NLP), Computing-with-Words (CWW), parsing, machine translation, sound and speech recognition, video search and analysis (e.g. tracking), image annotation, geometrical abstraction, image correction, semantic web, context analysis, data reliability (e.g., using Z-number (e.g., “About 45 minutes; Very sure”)), rules engine, control system, autonomous vehicle, self-diagnosis and self-repair robots, system diagnosis, medical diagnosis, biomedicine, data mining, event prediction, financial forecasting, economics, risk assessment, e-mail management, database management, indexing and join operation, memory management, and data compression. |
| 主权项 |
1. A method for analyzing or resolving ambiguities in image recognition for gesture, emotion, or expression recognition for a human, said method comprising:
an input device receiving a first image of a body or facial part of said human from a source; an analyzer module segmenting a first part of said first image and a second part of said first image; retrieving said first part of said first image and said second part of said first image; a reference database storing gestures, emotions, or expressions; said reference database referring to a rules engine for definitions of said gestures, emotions, or expressions; said rules engine defining said gestures, emotions, or expressions, based on relationships between parts of an image, for said body or facial part of said human; a processor determining Z-valuation for one or more parameters for one or more relationships between said first part of said first image and said second part of said first image; wherein said Z-valuation relates to reliability or confidence of data; said processor determining a first gesture, emotion, or expression, for said human, based on said Z-valuation and said one or more parameters for said one or more relationships between said first part of said first image and said second part of said first image, by comparing to said reference database, using said rules engine. |
