Image target identification method and device

Abstract

The embodiment of the invention provides an image target identification method and device. The method comprises the following steps that: obtaining an image to be identified; inputting the image to beidentified into a preset three-dimensional classification model; extracting the three-dimensional image characteristics of the image to be identified by the three-dimensional classification model, according to the three-dimensional image characteristics, generating a three-dimensional probability spatial graph of the image to be identified, identifying a target object in the image to be identified according to a pre-stored relationship between each target object and the three-dimensional probability spatial graph, and outputting the target object as an identification result; and obtaining theidentification result output by the three-dimensional classification model. By use of the embodiment of the invention, image target identification accuracy can be improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method and device for recognizing image objects. Background technique [0002] With the wide application of image recognition technology, the requirements for image target recognition accuracy are getting higher and higher, especially for application scenarios such as license plate recognition and traffic sign recognition. [0003] At present, the widely used image target recognition method is the image target recognition method based on the preset classification model, wherein the preset classification module includes a convolutional neural network (Convolutional Neural Network, CNN) model and a cascaded classifier; the following Taking the process of recognizing the license plate as an example, the target recognition process of the image is explained in detail: [0004] First, obtain the image to be recognized that contains the target license plate; [0005] Then,...

AI Technical Summary

Problems solved by technology

[0008] Since the cascade classifier is composed of a series of classifiers connected in series, the lower-level classifier continues to perform classification processing on the basis of the processing results of the upper-level classifier; it can be seen that in the above-mentioned image recognition method, after obtaining the After the two-dimensional image features are obtained, the classification results need to be processed by multi-level classification. The processing process is relatively complicated, and various errors are prone to occur, thus affecting the recognition accuracy of image targets.

Images