Autism early-stage screening system based on smile normal form and audio and video behavior analysis

Abstract

The invention discloses an autism early-stage screening system based on smile normal form and audio and video behavior analysis, and the system comprises: a data collection module which is used for collecting audio and video data in the whole test process; a preprocessing module which is used for synchronously aligning the acquired audios and videos and marking the time and types of different comma stimulations in sections; a feature extraction module which is used for carrying out frame-by-frame analysis on the preprocessed data to obtain various features; a training classification module which is used for training a classifier for features extracted from the paragraph video data and training an autism risk coefficient prediction classifier model in the whole normal form; and a predictionmodule which is used for grading the extracted features by paragraphs by using a classifier model and grading the whole paradigm. The system is used for early screening of autism, so that a screeningtest is more standardized and structured, and test evaluation is more accurate and easier to read and explain.

Description

technical field [0001] The present invention relates to the fields of speech processing and image processing, in particular to an early screening system for autism based on social and shared smile paradigms and audio-video behavior analysis, which collects audio-video data and subjects when evaluators induce smiles Response image data were induced and analyzed to evaluate a system for predicting autism spectrum disorder. Background technique [0002] Autism spectrum disorder (ASD) has been paid more and more attention by the society. In China, the number of autistic children aged 0 to 14 is between 3 million and 5 million. The current evaluation methods for autism mainly focus on three aspects: language communication barriers, social communication barriers, and repetitive stereotyped behaviors. An effective and accurate assessment of ASD requires clinically experienced medical professionals to observe children and conduct experiments together. [0003] In the experiment, ...

AI Technical Summary

Problems solved by technology

However, the existing computer screening system mainly induces smiles by playing videos. This method not only restricts children from wearing devices or sitting on fixed devices and cannot move freely, but also is difficult to simulate real life, especially difficult to simulate the interaction with people in real social scenes. social communication

Images