Image Retrieval Paradigm Research Articles

Application of Digital Images and Corresponding Image Retrieval Paradigm

We live in a world where digital images are constantly generated during our daily activities, whether private or business. They play an important role in our private life, showing important moments, people, places, or events and keeping their memory. Images are unavoidable in business, especially in digital marketing, web sales, social networks, medicine, security, and education. In general, images contribute to a better understanding of the message, increase the attractiveness of textual content, provide a better user experience, and can convey emotion quickly. The key advantage of the image is that very often, even a cursory glance at the image is enough to convey a message and arouse emotion and interest. But with the increase in digital image numbers, storage, organization, and retrieval problems arise. The paper describes the importance of images in different areas of application and different image retrieval paradigms that include text-based, content-based, and combined approaches. Also, the most popular image search tools and cloud storage services are compared and discussed. The conclusion comments on the applicability of existing approaches to image searches in different application domains and highlights the advantages and disadvantages of each of the approaches.

Random projection and hashing based privacy preserving for image retrieval paradigm using invariant and clustered feature

In recent years, exploration of local characteristics have been an effective feature extraction technique for managing multimedia repository for image retrieval. These class of approaches accelerate the image retrieval. However, with the increase of online intrusion, it is also essential to provide confidentiality for the private online data with effective functionality and significant retrieval accuracy. In this paper, we have solved the protuberant bottleneck problem of privacy-preserving in CBIR using random projection technique for feature encryption with effective retrieval. For this, we formulated highly discriminative interest points based features that are rotation and translation invariant and are constructed using k-means clustering and silhouette concept. Moreover, we have devised locally likely arrangement hashing technique that can incorporate fast, accurate, and secure matching over encrypted features. Based on the experiment, it substantially outperforms the recent state-of-the-art techniques in terms of retrieval accuracy and time overhead on various standard benchmarks, namely, Corel, Olivia, ALOI, and MPEG-7. The proposed method on average provided retrieval accuracy of 83.10%, 81.30%, 81.62%, 73.01% for Corel, Olivia, ALOI and MPEG-7 plaintexted feature, respectively while retrieval accuracy of 79.90% for Corel, 79.10% for Olivia, 79.97% for ALOI, and 67.34% for MPEG-7 using the encrypted feature.

Content-based medical image retrieval by spatial matching of visual words

Content-Based Image Retrieval (CBIR) systems have recently emerged as one of the most promising and best image retrieval paradigms. To pacify the semantic gap associated with CBIR systems, the Bag of Visual Words (BoVW) techniques are now increasingly used. However, existing BoVW techniques fail to capture the location information of visual words effectively. This paper proposes an unsupervised Content-Based Medical Image Retrieval (CBMIR) framework based on the spatial matching of the visual words. The proposed method efficiently computes the spatial similarity of visual words using a novel similarity measure called the Skip Similarity Index. Experiments on three large medical datasets reveal promising results. The location-based correlation of visual words assists in more accurate and efficient retrieval of anatomically diverse and multimodal medical images than the state-of-the-art CBMIR systems.

From Pixels to Semantic Spaces: Advances in Content-Based Image Retrieval

The paradigm for image retrieval has evolved from low-level image representations to semantic concept models to higher-level semantic inferences. UCSD's Statistical Visual Computing Laboratory has developed effective techniques for each paradigm that equate retrieval with classification and strive for minimum-probability-of-error optimality.

Mental image search by boolean composition of region categories

Existing content-based image retrieval paradigms almost never address the problem of starting the search, when the user has no starting example image but rather a mental image. We propose a new image retrieval system to allow the user to perform mental image search by formulating boolean composition of region categories. The query interface is a region photometric thesaurus which can be viewed as a visual summary of salient regions available in the database. It is generated from the unsupervised clustering of regions with similar visual content into categories. In this thesaurus, the user simply selects the types of regions which should and should not be present in the mental image (boolean composition). The natural use of inverted tables on the region category labels enables powerful boolean search and very fast retrieval in large image databases. The process of query and search of images relates to that of documents with Google. The indexing scheme is fully unsupervised and the query mode requires minimal user interaction (no example image to provide, no sketch to draw). We demonstrate the feasibility of such a framework to reach the user mental target image with two applications: a photo-agency scenario on Corel Photostock and a TV news scenario. Perspectives will be proposed for this simple and innovative framework, which should motivate further development in various research areas.

Visual image retrieval: seeking the alliance of concept-based and content-based paradigms

In the commercial use of picture collections, a heavy dependency continues to be exhibited on a concept-based image retrieval paradigm in which the query is verbalised by the client and resolved as a metadata text-matching operation. The practical and philosophical challenges posed by the indexing aspect of image metadata construction are significant and frequently expressed. Nevertheless, it has taken image digitisation to bring this particular information retrieval problem to prominence in the research agenda. Metamorphosed into a binary data structure, the digital image offers some enticing processing opportunities which content-based image retrieval techniques are exploiting with developing success. Drawing on studies of user need, this paper seeks to explain why a heavy dependency will continue to be placed on concept-based rather than content-based image retrieval techniques within archival image collections. In contrast, the promising nature of content-based techniques from the viewpoint of a growing clientele with less traditional visual information needs will also be considered. The paper concludes by offering the view that, while both concept-based and content-based approaches suffer from operational limitations, the further development of a hybrid image retrieval paradigm which combines the two approaches makes a potentially valuable contribution to the research agenda for visual image retrieval.

Visual image retrieval: seeking the alliance of concept-based and content-based paradigms

In the commercial use of picture collections, a heavy dependency continues to be exhibited on a concept-based image retrieval paradigm in which the query is verbalised by the client and resolved as a metadata text-matching operation. The practical and philosophical challenges posed by the indexing aspect of image metadata construction are significant and frequently expressed. Nevertheless, it has taken image digitisation to bring this particular information retrieval problem to prominence in the research agenda. Metamorphosed into a binary data structure, the digital image offers some enticing processing opportunities which content-based image retrieval techniques are exploiting with developing success. Drawing on studies of user need, this paper seeks to explain why a heavy dependency will continue to be placed on concept-based rather than content-based image retrieval techniques within archival image collections. In contrast, the promising nature of content-based techniques from the viewpoint of a growing clientele with less traditional visual information needs will also be considered. The paper concludes by offering the view that, while both concept-based and content-based approaches suffer from operational limitations, the further development of a hybrid image retrieval paradigm which combines the two approaches makes a potentially valuable contribution to the research agenda for visual image retrieval.