Attribute learning and interactive feedback in android platform based online image recognition and retrieval method

Abstract

The invention discloses an attribute learning and interactive feedback in android platform based online image recognition and retrieval method. The recognition part comprises the following steps: obtaining an image and extracting features of the image through an android phone; sending the features to a server; giving feedback from the server the attributes of the image; giving feedback to a user on the categories corresponding to the attribute combinations of the image for the user to confirm whether to add a to-be-recognized image into the training image database with corresponding attributes or not to enhance the recognition performance of the system. The retrieval part comprises the following steps: After the user describes the attribute list of the image to be retrieved by the mobile phone, the system presents the image corresponding to the category with the attribute combination in the image library to the user in a sorting manner for the user to choose from. Based on the choice of the user, the parameters of an attribute classifier are adjusted. The system communicates the underlying features of the image with the semantic representation of the user through the attribute medium, which has good application effect in the retrieval of relevant images through semantic description. And at the same time, high robustness can also be achieved.

Description

technical field

[0001] The invention relates to the technical field of pattern recognition, in particular to an image recognition method based on attribute learning. Background technique

[0002] Image recognition is an important application of pattern recognition, and image processing and recognition technology began in the middle of the 20th century. In 1964, the US Jet Propulsion Laboratory (JPL) used computers to process a large number of moon photos sent back by the spacecraft to obtain clear and realistic images. This is an important milestone in the development of image processing technology and promoted the birth of this discipline.

[0003] Current smartphone devices are still subject to some hardware limitations, such as low processing rate, small operating memory, limited system space, short standby time, etc., and common image recognition technologies often require a large amount of calculation and storage space , has high requirements on the operating hardware ...

Images