Image retrieval method based on object detection

Abstract

The invention discloses an image retrieval method based on object detection. The method is used for solving the problem that multiple objects in an image are not retrieved respectively during image retrieval. According to the implementation process of the method, object detection is performed on an image in an image database, and one or more objects in the image are detected; SIFT features and MSER features of the detected objects are extracted and combined to generate feature bundles; a K mean value and a k-d tree are adopted to make the feature bundles into visual words; visual word indexes of the objects in the image database are established through reverse indexing, and an image feature library is generated; and an object detection method is used to make objects in a query image into visual words, similarity compassion is performed on the visual words of the query image and the visual words of the image feature library, and the image with the highest score is output to serve as an image retrieval result. Through the method, the objects in the image can be retrieved respectively, background interference and image semantic gaps are reduced, and accuracy, retrieval speed and efficiency are improved; and the method is used for image retrieval on a specific object in the image, including a person.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, and mainly relates to image retrieval, in particular to an image retrieval method based on object detection, which can be used for Internet image data retrieval. Background technique [0002] With the advent of the information society and the popularization of computer applications, people are more and more exposed to a large amount of information, among which multimedia information is the most widely accessible information resource. It exists in various forms and grows at an explosive rate as technology advances. Especially in recent years, the application and development of the Internet has further promoted the rapid growth of the data volume of multimedia information. In the face of massive data, people are often at a loss. The rapid growth of information makes people's demand for multimedia information retrieval increase rapidly, so image retrieval technology has become one...

AI Technical Summary

Problems solved by technology

Text-based image retrieval uses keywords to annotate images. When users perform image retrieval, they mainly search for tags in matching images, but it has many disadvantages: the text keywords describing images are manually added, and the subjective consciousness is too large. large; the text description cannot express the rich meaning of the image at all, and it is difficult to accurately retrieve the images in the database only in the form of keywords; So much effort to label each image with text, the cost is too high

The disadvantage of this method is that the image segmentation is not accurate enough. The extracted features are low-level features such as color features and texture features. The features are extracted and retrieved for the entire image, and there is no single object retrieval in the image.

The disadvantage of this method is that it only considers the color and spatial information of the object for retrieval. When the number of images is large, too many features are extracted, and the retrieval of a single object in the image is not considered.

When the query image is input, feature extraction and retrieval are performed on the entire image or the main part of the image, and multiple objects in the image are not considered to be detected and features are extracted and retrieved separately. The method is not flexible and accurate enough.

Images