A Cognitive-Based Approach to Image Understanding

Abstract

The present invention relates to a cognition-based image understanding method, the method comprising: a step of establishing a high-cognition neural network training model, associating a picture data set to be classified with a picture label data set, and according to the result of the association Reclassify the inside of the image data set to be classified, and perform deep convolutional neural network training on the reclassified data set to obtain a neural network training model with a high degree of recognition; the image understanding step is to pass the image to be understood through a high degree of recognition The neural network training model to get the label corresponding to the picture. Compared with the prior art, the present invention has the advantages of high understanding accuracy, being more in line with actual conditions, effectively shortening the image understanding time, and the like.

Description

technical field [0001] The invention relates to the field of image semantic understanding, in particular to a cognition-based image understanding method. Background technique [0002] With the development of computer vision and natural language, more and more research and applications combine the two, use algorithmic models to understand the semantic content of pictures, and express the content in natural language. In the process of image understanding, deep convolutional neural networks are usually used to extract the visual features of pictures. A common method is to continue training and parameter fine-tuning on the trained classification task pre-training model. However, the category division method as the training target plays a vital role in the feature learning of the neural network. Different from traditional classification tasks, it is not necessary to accurately classify all objects in the picture in the content understanding of pictures, but it is necessary to l...

AI Technical Summary

Problems solved by technology

[0004] First, the types of objects in the data set are randomly selected, which is not suitable for feature learning of image understanding tasks

[0005] Second, the classification in the data set is too fine, and some category labels are beyond the cognitive ability of ordinary humans

[0006] Third, the training samples of some classes in the dataset are not representative

[0007] Fourth, although for pure visual tasks, the deep convolutional neural network pre-training model can improve the training performance to a certain extent, but it does not consider the impact of human cognitive ability on visual understanding

Images