A Method for Fast Retrieval of Massive Images

Abstract

The invention presents a new quick searching method for mass images, which comprises the following steps: 1, transforming images of red, green and blue (RGB) colored spaces to a hue, saturation and value (HSV) colored space; 2, extracting HSV color histogram information of every small block respectively by blocking the image spaces; 3, obtaining the index characteristics of the images by using a hashing algorithm; and 4, searching the returned similar image sets by using the hashing index characteristics; blocking the color histogram characteristics by using an original HSV colored space; rearranging the similar image sets returned by the index characteristics generated on the basis of hashing by adopting a street distance as the function of a similarity measurement between the images. The test shows that the algorithm provided in the invention can exactly process millions of image data in real time in comparison to the algorithm in the past; the method can be used in the search of the content-based images on internet, on-line electronic shopping website, and other scenes.

Description

technical field [0001] The invention relates to the fields of image retrieval based on content and electronic shopping websites, in particular to a method for fast retrieval of massive pictures. Background technique [0002] At present, with the popularity of electronic products such as cameras, mobile phones, and video cameras, we can take pictures of our favorite scenery, animals, food, and so on anytime and anywhere. As of January 2010, Facebook claims that the number of pictures on its website has exceeded 25 billion. Facing such a large number of picture resources, how to quickly and accurately find the pictures we are interested in is already a problem we must solve. It is against this background that the present invention extracts the color histogram information of the HSV color space block from the picture, because it takes into account the spatial distribution information of the color, and has better discrimination than the traditional color histogram feature , can...

AI Technical Summary

Problems solved by technology

[0003] The traditional text-based image retrieval method has inherent defects: because the pictures need to be manually labeled, it brings a heavy workload, and because of the rich information in the pictures, it is often difficult for the labeling personnel to fully understand the information displayed in the pictures. On the other hand, due to human subjectivity, different people may have completely different understandings and points of interest for a picture, so the marked information may be completely different

The other is a random method, the representative one is the locality sensitive hashing method (Locality Sensitive Hashing), but because this method needs to maintain multiple hash indexes to ensure that similar feature vectors are mapped to the same hash bucket , which requires the use of a large amount of memory space, facing a large amount of data, this method is also inappropriate

Images