Human face expression data collection method and device

Abstract

An embodiment of the invention discloses a human face expression data collection method and device. The method comprises the following steps: collecting at least one human face data; obtaining at least one reference expression information of target human face data, and obtaining probability of target expression information corresponding to the target human face data being each kind of reference expression information in the at least one kind of reference expression information, wherein the target human face data is any human face data in the at least one human face data; and determining the expression information, the probability of which is the largest, as the target expression information of the target human face data, and carrying out association storage on the target human face data and the target expression information to finish establishment of a human face expression database. The human face expression data collection method and device can overcome the problems of clumsiness and non-intelligence when the human face expression data is collected in a conventional mode, and can finish classification and acquisition work of the human face data automatically through existing tools.

Description

technical field [0001] The invention relates to the communication field, in particular to a method and device for collecting facial expression data. Background technique [0002] With the continuous development of artificial intelligence technology, facial expression recognition technology is also constantly making breakthroughs. Facial expression recognition is widely used. Human behavior can be analyzed through facial expression recognition. For example, shoppers’ preferences for goods can be learned through their facial expressions, and then the location of goods in shopping malls can be placed in a targeted manner so that products Big sales, etc., or, through expression recognition to prevent drowsiness, etc. Facial expression recognition is based on the application of expression data for model training. Therefore, it is of great significance to establish a facial expression database. The traditional facial expression data collection methods are divided into the follow...

AI Technical Summary

Problems solved by technology

[0003] Calling volunteers to gather time-consuming and labor-intensive collection requires the cooperation of personnel, and most of the collected pictures are in the form of picture-in-the-lab (background changes, lighting changes, etc. are very simple). For picture-in-the-wild (background , scale, lighting changes, etc.) expression data cannot be recognized well; purchasing a database is expensive, and no matter which collection method is used, it is all manual collection, which lacks intelligence and efficiency

Images