Image recognition method, image presentation time adjustment method and equipment

Abstract

The embodiment of the invention provides an image recognition method, an image presentation time adjustment method and equipment. The image recognition method comprises the steps that a presentation time sequence corresponding to an image sequence is set, the image sequence comprises N images, the presentation time sequence comprises at least two unequal presentation times, the difference betweenany two presentation times in the at least two unequal presentation times is k * delta, and k is a positive integer and delta is a preset time period value; the image sequence is processed by using acomputer vision algorithm to obtain a computer vision signal corresponding to each image in the image sequence; a feedback signal of each image in the corresponding image sequence generated when the observation object watches the image sequence displayed according to the presentation time sequence is generated; and for each image in the image sequence, the corresponding computer vision signal andthe corresponding feedback signal are fused to obtain a target identification signal of each image in the image sequence. By implementing the embodiment of the invention, the omission factor of imagerecognition can be reduced.

Description

technical field [0001] Embodiments of the present invention relate to the field of information technology, and in particular, to an image recognition method, an image presentation time adjustment method, and equipment. Background technique [0002] In the current information age, when people share rich information resources, the problem of "information overload" or even "information explosion" often occurs. How to efficiently screen out the information you need most from the massive information resources is an important issue with the advent of the information age. In the image field, image recognition is one of the most concerned problems at present. Image recognition can be achieved using computer vision algorithms. Computer vision algorithms can be traditional image detection algorithms or deep learning algorithms based on artificial neural networks. The traditional image detection algorithm is to extract image features from the image area, and classify the image accor...

AI Technical Summary

Problems solved by technology

[0003] Both the traditional target detection algorithm and the deep learning algorithm based on the worker neural network have the following disadvantages: First, it may be difficult to obtain a certain type of training data, resulting in an unbalanced distribution of training samples

At present, the time interval between images in the RSVP-based image sequence is determined based on experience or experiments. However, due to the fatigue of the human brain and the limited attention resources of the human brain, the missed detection rate of brain-computer collaborative image recognition is still high. , resulting in low efficiency of brain-computer collaborative image recognition

Images