Image recognition method and apparatus

Abstract

The present invention provides an image recognition method and apparatus. The method comprises the following steps that: pre-collected image samples are adopted to train a prediction image set for predicting image categories, wherein the image samples include the images of a complete target object, the images of a part of the target object and images not containing the target object, and the image categories include a target image category containing the target object and a non-target image category not containing the target object; the prediction image set is utilized to perform image category recognition on a current image so as to obtain an image category prediction result; and whether the current image belongs to the target image category or the non-target image category is judged according to the image category prediction result. With the image recognition method and apparatus provided by the embodiment of the present invention adopted, the accuracy of image recognition can be improved.

Description

technical field [0001] The present invention relates to the field of image recognition, in particular to an image recognition method and an image recognition device. Background technique [0002] In the current image recognition technology, it mainly recognizes the overall characteristics of an object with a complete and regular posture in the image. For example, if there is a full frontal human body in the image, it can be identified that the image contains a person image. [0003] However, in practical applications, the human body in the image may not be complete. For example, the human body in some images is partially blocked by the scenery or still life, and only the side or part of the limbs of the human body can be seen; Incomplete or irregularly posed, it is not possible to recognize the presence of a human subject in the image. In the recognition of other objects such as animals and still life, there is also the problem that incomplete and irregular objects cannot...

AI Technical Summary

Problems solved by technology

[0003] However, in practical applications, the human body in the image may not be complete

For example, the human body in some images is partially blocked by the scenery or still life, and only the side or part of the limbs of the human body can be seen; Incomplete or irregular poses that do not recognize the presence of human subjects in the image

In the recognition of other objects such as animals and still life, there is also the problem of inability to classify and recognize incomplete and irregular objects.

[0004] Therefore, the current image recognition method has the problem of low recognition accuracy.

Images