Image retrieval

About: Image retrieval is a research topic. Over the lifetime, 28169 publications have been published within this topic receiving 651988 citations.

Multi-feature fusion image retrieval method

Abstract: The invention discloses a multi-feature fusion image retrieval method The method comprises the steps of firstly, inputting an image I to be retrieved; secondly, constructing a color feature vector and a SIFT feature vector of the image I; thirdly, training the image in a query image library to obtain a color feature dictionary and a SIFI feature dictionary, and using a visual word for representing the image in the image library; fourthly, using the visual word for representing the image I, calling a candidate image set Q from the query image library according to the visual word, and calculating a similarity value score (Q,I); fifthly, selecting a local area Si with the visual saliency in the image I and repeatedly executing the step three and the step four to obtain a candidate image set K, and calculating a similarity value score (K,I); sixthly, using an overlapped image set of the two candidate fusion sets as D, fusing score (D,I) and score (D,I), and calculating a final similarity value score (D,I); seventhly, using the image with the highest final similarity value as a retrieval result of the image I to be retrieved The multi-feature fusion image retrieval method has the advantages of lowering image noise and improving the retrieval accuracy

Secure and efficient image retrieval through invariant features selection in insecure cloud environments

Abstract: Advances in computer vision technologies lead to a renewed focus on content-based image retrieval (CBIR) in computer multimedia content analysis applications. CBIR is a technique for image retrieval using automatically derived features. As the size of image repositories grew, supported by increased cloud storage adoption, security concern around trust in cloud service provider (CSP) witnessed a resurgence of interest in user privacy. Hence, unlike in traditional CBIR, cloud-based image retrieval is based on the encrypted feature vector. This may reduce the overall retrieval performance of the system. Consequently, mechanisms are needed to protect the feature vector and the actual images during transmission. Second, to provide image content security, images are often encrypted by users before uploading to the cloud. This article addresses the challenges of retrieving images securely from an untrusted cloud environment. Images are represented in terms of their local invariant features to form an image feature vector. Later, an asymmetric scalar-product-preserving encryption (ASPE) is applied to secure the feature vector. Then, images are encrypted before they are uploaded to a cloud server. The proposed method has been tested on various Corel image datasets and the medical image repository. Performance evaluation shows that the proposed method outperforms its best secure CBIR systems in the literature.

Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval

Abstract: Scene text instances found in natural images carry explicit semantic information that can provide important cues to solve a wide array of computer vision problems. In this paper, we focus on leveraging multi-modal content in the form of visual and textual cues to tackle the task of fine-grained image classification and retrieval. First, we obtain the text instances from images by employing a text reading system. Then, we combine textual features with salient image regions to exploit the complementary information carried by the two sources. Specifically, we employ a Graph Convolutional Network to perform multi-modal reasoning and obtain relationship-enhanced features by learning a common semantic space between salient objects and text found in an image. By obtaining an enhanced set of visual and textual features, the proposed model greatly outperforms previous state-of-the-art in two different tasks, fine-grained classification and image retrieval in the Con-Text[23] and Drink Bottle[4] datasets.

Methods for automatic and assisted image annotation

Abstract: Personal memories composed of digital pictures are very popular at the moment. To retrieve these media items annotation is required. During the last years, several approaches have been proposed in order to overcome the image annotation problem. This paper presents our proposals to address this problem. Automatic and semi-automatic learning methods for semantic concepts are presented. The automatic method is based on semantic concepts estimated using visual content, context metadata and audio information. The semi-automatic method is based on results provided by a computer game. The paper describes our proposals and presents their evaluations.

Evaluation strategies for automatic linguistic indexing of pictures

Abstract: With the rapid technological advances in machine learning and data mining, it is now possible to train computers with hundreds of semantic concepts for the purpose of annotating images automatically using keywords and textual descriptions. We have developed a system, the automatic linguistic indexing of pictures (ALIP) system, using a 2-D multiresolution hidden Markov model. The evaluation of such approaches opens up challenges and interesting research questions. The goals of linguistic indexing are often different from those of other fields including image retrieval, image classification, and computer vision. In many application domains, computer programs that can provide semantically relevant keyword annotations are desired, even if the predicted annotations are different from those of the gold standard. In this paper, we discuss evaluation strategies for automatic linguistic indexing of pictures. We provide both objective and subjective evaluation methods. Finally, we report experimental results using our ALIP system.