Image intelligent mode recognition and searching method

Abstract

The invention puts forward an image intelligent mode identification search method. The method can establish an image sample training set database and combine with basic text search engine technology and basic image content inquiry technology, so that a network creeper can perform Internet image search and URL information resolution, so as to catch the image URL and relevant information into a local primary database; perform such pre-processes as preliminary filtration, decompression and image pre-classification and etc for the images; then, calculate color characteristics, grain characteristics and shape characteristics of the extraction images, so as to gain corresponding characteristic vector sets; combine with the image URL information before saving the images into the image basic database and establishing an index for the images; perform characteristic vector similarity calculation for images in the image basic databases and sample training sets, and then, save the classified images into an image classification database; accept key words or image description that are input by the user, create the index vector, perform similarity calculation with the image characteristic vectors in the image classification database, and then, return the index results to the user.

Description

technical field [0001] The invention belongs to the field of computer image pattern recognition, especially for still images dynamically generated by Internet search engines, and proposes a search method for association analysis in combination with image annotation text features and image self-measurement values. Background technique [0002] Image pattern recognition refers to the research on the design of automatic processing system for pattern recognition of image data. An important field of application of pattern recognition is the detection of certain types of text or images and the control of operating processes. A schema (also called an object, case, or sample) is a "physical" description of an object, usually a signal, image, or simply a table of values. Features are metrics, attributes, or primitives derived from schemas that are useful for classification. For example, in image recognition, a 256×256 grayscale image can obtain 65536 image metric values ​​(light in...

AI Technical Summary

Problems solved by technology

There are two problems with this method: one is that this method requires more manual participation, and as the number of images increases, this method is difficult to implement; the second problem is that the amount of information contained in images is huge, Different people have different understandings of the same image, which leads to no uniform standard for image annotation, so the retrieval results cannot well meet the needs of users

However, since these features do not represent the real semantic information of the image, content-based retrieval results are often unsatisfactory, and sometimes irrelevant advertisement banners, icons, background images, and buttons are also retrieved

Images