Content-based Image Retrieval Research Research Articles

An Efficient Video Frames Retrieval System Using Speeded Up Robust Features Based Bag of Visual Words

Most studies in content-based image retrieval (CBIR) systems use database images of multiple classes. There is a lack of an automatic video frame retrieval system based on the query image. Low-level features i.e., the shape and colors of most of the objects are almost the same e.g., the sun and an orange are both round and red in color. Features such as speeded up robust features (SURF) used in most of the content-based video retrieval (CBVR) & CBIR research work are non-invariant features which may affect the overall accuracy of the CBIR system. The use of a simple and weak classifier or matching technique may also affect the accuracy of the CBIR system on high scale. The unavailability of datasets for content-based video frames retrieval is also a research gap to be explored in this paper.

Query-Based Image Retrieval using SVM

Now a day’s image plays an important role to extract the information about the object in various industries. Many traditional methods have been employed to retrieve images. It interactively determines the user’s query by asking the user whether the image is relevant or not. In this information tech age, graphics have become a major portion of information processing. In the Image registration processing, the image plays an important part to extract the information regarding the item in a variety of fields including in tourism, medical and geological, weather systems calling. There are lots of Approaches individuals who are used to recover images. It interactively determines an individual's query by requesting the users whether the image will be relevant (similar) or maybe not. In content-based image retrieval (CBIR) system, effective company of this image database used to improve the functioning of the procedure. The research of content-based image retrieval (CBIR) technique has become a significant research topic. Being an individual, we've Studied and done investigation of various features in this manner or in mixes. We found that image Registration processing (IRP) is the key area in above mentioned industries. Various research papers through color feature and texture feature extraction were studied and concluded that point cloud data structure is best for image registration process using Iterative Closest Point (ICP) algorithm.

A dynamic wrapper‐based feature selection for improved precision in content‐based image retrieval

SummaryThe content‐based image retrieval (CBIR) has been applied in the image processing as well as pattern recognition. A challenging task in the CBIR research has been through the feature extraction for decreasing any semantic gap that is an active research topic. Here, in this work, there is a texture feature that is extracted from an image, making use of a technique of curvelet transform. This curvelet is selected for a sparse representation that is quite critical for the estimation of images, which have been de‐noised with some inversed problems. The wrapping‐based curvelet transform will be even more robust as well as faster in the time of computation than the Ridge Transform. A technique of feature selection will be brought for selecting the optimal features. The correlation‐based feature selection (CFS) method has been adapted for improving the accuracy of the CBIR systems. The non‐deterministic polynomial (NP)–hard problems may be solved using the chemical reaction optimization (CRO) that has been motivated using the technique of chemical reaction. The benefits of proposed method is a necessity for marginal human intrusion for the purpose of retrieving the images needed from its database. The proposed mechanism has been again assessed depending on the Coral Database, and a performance study is ended using precision, f measure, and recall.

A robust CBIR framework in between bags of visual words and phrases models for specific image datasets

One objective of the Content Based Image Retrieval research field is to propose new methodologies and tools to manage the increasing number of images available. Linked to a specific context of small expert datasets without prior knowledge, our research work focuses on improving the discriminative power of the image representation while keeping the same efficiency for retrieval. Based on the well-known bag of visual words model, we propose three different methodologies inspired by the visual phrase model effectiveness and a compression technique which ensures the same effectiveness for retrieval than the BoVW model. Our experimental results study the performance of our proposals on different well known benchmark datasets and show its good performance compared to other recent approaches.

Image retrieval method based on metric learning for convolutional neural network

At present, the research of content-based image retrieval (CBIR) focuses on learning effective feature for the representations of origin images and similarity measures. The retrieval accuracy and efficiency are crucial to a CBIR. With the rise of deep learning, convolutional network is applied in the domain of image retrieval and achieved remarkable results, but the image visual feature extraction of convolutional neural network exist high dimension problems, this problem makes the image retrieval and speed ineffective. This paper uses the metric learning for the image visual features extracted from the convolutional neural network, decreased the feature redundancy, improved the retrieval performance. The work in this paper is also a necessary part for further implementation of feature hashing to the approximate-nearest-neighbor (ANN) retrieval method.

A Survey on Content-based Image Retrieval

The widespread of smart devices along with the exponential growth of virtual societies yield big digital image databases. These databases can be counter-productive if they are not coupled with efficient Content-Based Image Retrieval (CBIR) tools. The last decade has witnessed the introduction of promising CBIR systems and promoted applications in various fields. In this article, a survey on state of the art content based image retrieval including empirical and theoretical work is proposed. This work also includes publications that cover research aspects relevant to CBIR area. Namely, unsupervised and supervised learning and fusion techniques along with low-level image visual descriptors have been reported. Moreover, challenges and applications that emerged to support CBIR research have been discussed in this work.

Content Based Image Retrieval

With the passing years, many advanced technologies have come into existence for efficientimage retrieval. Research in content-based image retrieval (CBIR) in the past has been focused on image processing, low-level feature extraction. The accuracy of retrieval has subsequently increased with the use of low level features such as color, texture, shape etc. But still image retrieval using low level features has been restricted to a specific efficiency. Extensive experiments on CBIR systems demonstrate that low-level image features cannot always describe high-level concepts in the users mind. Because, using low level features only does not include human perception. If human intervention is allowed in the image retrievalsystem the efficiency boosts up. Therefore, in this research my aim is to reduce the Gap between the low level and high level features because the CBIR systems should provide Maximum support in bridging the semantic gap between low-level visual features and the Richness of human semantics. Keywords- CPW, CST, FR4, LAN, WiMAX

3D image retrieval based on differential geometry and co-occurrence matrix

3D image retrieval approach is a challenging problem in the research of content-based image retrieval. In this paper, a novel retrieval approach combined differential geometry and co-occurrence matrix is presented. Firstly, Gaussian curvature and mean curvature are utilized to represent the inherent characteristic of spatial surface, and then we use co-occurrence matrix to store the shape information of 3D images. Secondly, normalization process is applied to the co-occurrence matrix and the invariants independence of the translation, scaling, and rotation transforms are proved. In comparison with the recent methods, experiments indicate a lower computation complexity and a better retrieval rate to 3D images with slight different shape characteristic.

CBIR SYSTEM USING COLOR HISTOGRAM AND WAVELET TRANSFORM FOR BLOOD CELLS IMAGES

The research in Content-based image retrieval is developing rapidly. It benefits many other fields, in particular the medical field as the need of having a better way of managing andretrieving digital images has increased.The aim of the thesis is to investigate performance of descriptors of blood cell image retrieval. In this process traditional wavelet based and global color histogram is investigated. The prototype system allows user to search by providing a query image and selecting one of four implemented methods. Research goal is enhancing current content-based image retrieval techniques. Results were obtained by experimenting to this proposed method is able to perform clinically relevant queries on image databases without user supervision.

Secure Image Retrieval Based on Visual Content and Watermarking Protocol

As an interesting application on cloud computing, content-based image retrieval (CBIR) has attracted a lot of attention, but the focus of previous research work was mainly on improving the retrieval performance rather than addressing security issues such as copyrights and user privacy. With an increase of security attacks in the computer networks, these security issues become critical for CBIR systems. In this paper, we propose a novel two-party watermarking protocol that can resolve the issues regarding user rights and privacy. Unlike the previously published protocols, our protocol does not require the existence of a trusted party. It exhibits three useful features: security against partial watermark removal, security in watermark verification and non-repudiation. In addition, we report an empirical research of CBIR with the security mechanism. The experimental results show that the proposed protocol is practicable and the retrieval performance will not be affected by watermarking query images.

Bridging the Feature Gaps for Retrieval of Multi-Dimensional Images

Content-based image retrieval (CBIR) refers to the use of visual features for images retrieval, and has become an attractive approach to managing biomedical image achieves. However, existing CBIR systems are typically designed for 2D single-modality imaging, and are restricted when multi-dimensional images are considered. With the advances in imaging scanners, image complexity and magnitude have rapidly expanded in both the temporal (time) and spatial (space) dimensions, i.e., dynamic PET provides physiological functions of the human body acquired in 3D volumes over multiple time sequences, and dual-modality imaging scanners that sequentially acquires co-aligned functional (PET) and anatomical (CT) images. This manuscript summarizes research in CBIR of multi-dimensional biomedical images with focuses on the feature extraction and retrieval techniques that utilize the information available in the image’s multidimensional data spaces. Applications of multi-dimensional CBIR will be exemplified with our ongoing studies with 4D dynamic PET and dual-modal PET/CT images.

Ontology of Gaps in Content-Based Image Retrieval

Content-based image retrieval (CBIR) is a promising technology to enrich the core functionality of picture archiving and communication systems (PACS). CBIR has a potential for making a strong impact in diagnostics, research, and education. Research as reported in the scientific literature, however, has not made significant inroads as medical CBIR applications incorporated into routine clinical medicine or medical research. The cause is often attributed (without supporting analysis) to the inability of these applications in overcoming the "semantic gap." The semantic gap divides the high-level scene understanding and interpretation available with human cognitive capabilities from the low-level pixel analysis of computers, based on mathematical processing and artificial intelligence methods. In this paper, we suggest a more systematic and comprehensive view of the concept of "gaps" in medical CBIR research. In particular, we define an ontology of 14 gaps that addresses the image content and features, as well as system performance and usability. In addition to these gaps, we identify seven system characteristics that impact CBIR applicability and performance. The framework we have created can be used a posteriori to compare medical CBIR systems and approaches for specific biomedical image domains and goals and a priori during the design phase of a medical CBIR application, as the systematic analysis of gaps provides detailed insight in system comparison and helps to direct future research.

Mining user hidden semantics from image content for image retrieval

The problem confronted in the content-based image retrieval research is the semantic gap between the low-level feature representing and high-level semantics in the images. This paper describes a way to bridge such gap: by learning the similar images given from the user, the system extracts the similar region pairs and classifies those similar region pairs either as object or non-object semantics, and either as object-relation or non-object-relation semantics automatically, which are obtained from comparing the distances and spatial relationships in the similar region pairs by themselves. The system also extracts interesting parts of the features from the similar region pair and then adjusts each interesting feature and region pair weight dynamically. Using those objects and object-relation semantics as well as the dynamic weights adjustment from the similar images, the semantics of those similar images can be mined and used for searching the similar images. The experiments show that the proposed system can retrieve the similar images well and efficient.

A multi-agent platform for content-based image retrieval

Efficient and possibly intelligent image retrieval is an important task, often required in many fields of human activity. While traditional database indexing techniques exhibit a remarkable performance in textual information retrieval current research in content-based image retrieval is focused on developing novel techniques that are biologically motivated and efficient. It is well known that humans have a remarkable ability to process visual information and to handle the volume and complexity of such information quite efficiently. In this paper, we present a content-based image retrieval platform that is based on a multi-agent architecture. Each agent is responsible for assessing the similarity of the query image to each candidate image contained in a collection based on a specific primitive feature and a corresponding similarity criterion. The outputs of various agents are integrated using one of several voting schemes supported by the system. The system's performance has been evaluated using various collections of images, as well as images obtained in specific application domains such as medical imaging. The initial evaluation has yielded very promising results.

Capture local information in shape representation

Research in content-based image retrieval has been around for over a decade. While the research community has successfully exploited content features such as color and texture, finding an effective shape representation and measure remains a challenging task. The shape feature is particularly crucial for the success of content-based systems as it carries meaningful semantics of the objects of interest and fits more naturally into humans' perception of similarity. In this paper, we present our approach to use the shape feature for image retrieval. First, we introduce an effective image decomposition method called Crawling Window (CW) to distinguish the outline of each object in the image. Second, to represent each individual shape, we propose a novel representation model called component Distance Distribution Function and its measure. Traditionally, an object is represented by a set of points on the shape's contour. Our idea is to first compute the distance between each point and the center of the object. The distance values for all points form a signal, which we call Distance Distribution Function (DDF). Each DDF is then divided into component DDFs (cDDF) by taking local signal information into account. Finally, a transformation technique is employed to generate the feature vector for each cDDF. All vectors from the cDDFs in circular order construct the final shape representation. The model is invariant to position, scaling, rotation and starting point. The similarity measure model based on the new representation is also introduced. Our extensive experiments show that our models are more effective than the existing representation model, both in the shape and the image level.