A framework for grid-based image retrieval

The traditional privacy-preserving image retrieval schemes not only bring large computational and communication overhead but also cannot well protect the image and query privacy in multi-user scenarios. To solve the above problems, we first propose a basic privacy-preserving content-based image retrieval (CBIR) framework which significantly reduces storage and communication overhead compared with the previous works. Furthermore, we design a new efficient key conversion protocol to support unshared key multi-owner multi-user image retrieval without losing search precision. Moreover, our framework supports unbounded attributes and can trace malicious users according to leaked secret keys, which significantly improve the usability of multi-source data sharing. Strict security analysis shows that the user privacy and outsourced data security can be guaranteed during the image retrieval process, and the performance analysis using real-world dataset shows that the proposed image retrieval framework is efficient and feasible for practical applications.

Feature extraction and similarity measure are two basic key issues in image retrieval. Combining the advantages of SNN in image recognition and selective attention for image retrieval, a novel visual keywords-driven image retrieval approach based on these properties has been proposed. By using a predefined set of visual keywords as prototype patterns stored with the SNN and then measuring the degree of similiarity of the stored images to the visual keywords, we show that such a visual keyword driven SNN can provide the framework for image indexing or retrieval which is scalable, robust and efficient for web-based search.

Most current content-based image retrieval systems are still incapable of providing users with their desired results. The major difficulty lies in the gap between low-level image features and high-level image semantics. To address the problem, this study reports a framework for effective image retrieval by employing a novel idea of memory learning. It forms a knowledge memory model to store the semantic information by simply accumulating user-provided interactions. A learning strategy is then applied to predict the semantic relationships among images according to the memorized knowledge. Image queries are finally performed based on a seamless combination of low-level features and learned semantics. One important advantage of our framework is its ability to efficiently annotate images and also propagate the keyword annotation from the labeled images to unlabeled images. The presented algorithm has been integrated into a practical image retrieval system. Experiments on a collection of 10,000 general-purpose images demonstrate the effectiveness of the proposed framework.

The image retrieval of industrial parts aims at ranking parts of different classes based on the similarity of the content, so as to solve the common problems of informatization management in industrial production and improve production efficiency. Generally speaking, the images are ranked by comparing the similarity between the representation vector of the query image and the gallery image for retrieval. Therefore, a compact and rich feature representation has become the key to image retrieval. In this paper, we propose a new image retrieval framework, which combines the features extracted by convolutional neural network (CNN) and Transformer, and retains local and global information to the greatest extent through convolution and self-attention. Specifically, we co-training CNN and Transformer to generate image feature descriptors, and combine multiple metric learning loss functions to train the model. Experiments show that this method achieves high accuracy in image retrieval. For example, we obtained a rank-1 score of 87.1% on the button Re-ID dataset, which is significantly better than existing methods.

Local descriptors are very effective features in bag-of-visual-words (BoW) and vector of locally aggregated descriptors (VALD) models for image retrieval. Different kinds of local descriptors represent different visual content. We recognize that spatial contextual information play an important role in image matching, image retrieval and image recognition. Therefore, to explore efficient features, firstly, a new local composite descriptor is proposed, which combines the advantages of SURF and color name (CN) information. Then, VLAD method is used to encode the proposed composite descriptors to a vector. Third, local deep features are extracted and fused with the encoded vector in the image block. Finally, to implement efficient retrieval system, a novel image retrieval framework is organized a novel image retrieval framework is organized based on the proposed feature fusion strategies. The proposed methods areis verified on three benchmark datasets, i.e., Holidays, Oxford5k and Ukbench. Experimental results show that our methods achieves good performance. Eespecially, the mAP and N-S score achieve 0.8281 and 3.5498 on Holidays and Ukbench datasets, respectively.

Recently, research in the field of content-based image retrieval has attracted a lot of attention. Nevertheless, most existing methods cannot be easily applied to medical image databases, as global image descriptions based on color, texture, or shape do not supply sufficient semantics for medical applications. The concept for content-based image retrieval in medical applications (IRMA) is therefore based on the separation of the following processing steps: categorization of the entire image; registration with respect to proto- types; extraction and query-dependent selection of local features; hierarchical blob representation including object identification; and finally, image retrieval. Within the first step of processing, images are classified according to image modality, body orientation, ana- tomic region, and biological system. The statistical classifier for the anatomic region is based on Gaussian kernel densities within a probabilistic framework for multiobject recognition. Special empha- sis is placed on invariance, employing a probabilistic model of vari- ability based on tangent distance and an image distortion model. The performance of the classifier is evaluated using a set of 1617 radiographs from daily routine, where the error rate of 8.0% in this six-class problem is an excellent result, taking into account the dif- ficulty of the task. The computed posterior probabilities are further- more used in the subsequent steps of the retrieval process. © 2003

This paper presents a novel feature extraction framework for content-based image retrieval (CBIR). Discrete wavelet transform (DWT) based Local tetra pattern (LTrP) is used to obtain the feature map from an input image. Decomposition of DWT up to single level and the features obtained from it would make the CBIR system very sensitive to noise. Therefore, decomposition up to three scales is used to remove noise. On each of the sub band LTrP is applied and 130 features are extracted. Further, Artificial Neural Network (ANN) is employed for index matching and image retrieval task which gives the classification accuracy of 97.9 % for Corel 1K database. We have compared our proposed feature extraction scheme with LTrP and other existing local descriptor. Results show that combination of DWT and Local Tetra Patterns (DWT + LTrP) extracts more robust features than LTrP alone. Also, the effect of different wavelet filters on the accuracy of the system has been analyzed. Proposed framework has been tested on Corel-1000 and Corel-10000 databases. We have used average retrieval rate, precision, and recall for performance measure of the CBIR system. Proposed method outperforms the retrieval rate from 75.9% using LTrP to 97.9% using proposed method on Corel 1K database. Improvement in performance measures as compared to the other existing methods evidence that, the proposed spatio-frequency local descriptor is more robust for image retrieval task.

Recent years, the stereo image has become an emerging media in the field of 3D technology, which leads to an urgent demand of stereo image retrieval. In this paper, we attempt to introduce a framework for object-based stereo image retrieval (OBSIR), which retrieves images containing the similar objects to the one captured in the query image by the user. The proposed approach consists of both online and offline procedures. In the offline procedure, we propose a salient object segmentation method making use of both color and depth to extract objects from each image. The extracted objects are then represented by multiple visual feature descriptors. In order to improve the image search efficiently, we construct an approximate nearest neighbor (ANN) index using cluster-based locality sensitive hashing (LSH). In the online stage, the user may supply the query object by selecting a region of interest (ROI) in the query image, or clicking one of the objects recommended by the salient object detector. For the image retrieval evaluation we build a new dataset containing over 10K stereo images. The experiments on this dataset show that the proposed method can effectively recommend the correct object and the final retrieval result is also better than other baseline methods.

This paper presents an effective and efficient framework for Crowd-assisted Mobile Similarity Retrieval of the large-scale medical images in the resource-constraint mobile telemedicine systems (MTS), called the CMSR. The CMSR processing works as follows: when a user submits a retrieval medical image IR, a buffer checking processing is first invoked to check if the full (or partial) retrieval results have been cached in the buffer previously. After that, a parallel image data filtering and refinement processing is conducted at a master node level. Finally, the candidate images are concurrently validated by a mCrowd system to derive an answer set that is transmitted to the retrieval node. To better facilitate the effective and efficient CMSR processing, three enabling techniques, i.e., category-based image data interleaving placement scheme, hindex-support image filtering algorithm and a kNN-based buffering scheme are developed. To improve the retrieval throughput, finally, we propose an extension of the CMSR method called mCMSR to optimize the multiple CMSRs. The experimental results show that the performances of the CMSR and the mCMSR methods are: 1) effective in improving the retrieval accuracy; 2) efficient in minimizing the response time by decreasing the network transmission cost while increasing the parallelism of I/O and CPU.

This paper proposes a formal framework for image and video retrieval using discrete Markov random fields (MRF). The training dataset consists of images with keywords (regions are not labeled). The model is built using a discrete vocabulary of vector quantized region or point features generated from the training images. Since performance is dependent on the size of the vocabulary, a large vocabulary of a couple of million visterms is used. Such large vocabularies cannot be generated by conventional clustering algorithms so hierarchical k-means is used to generate it. Unlike many previous techniques, our MRF based model doesn't require an explicit annotation step for retrieval. The model directly ranks all test images according to the posterior probability of an image given a query. Traditionally, most models are trained by maximizing likelihood - instead this model is trained by maximizing average precision. Image and video retrieval experiments are performed on two standard datasets (a Corel dataset and a TRECVID3 dataset) which consist of 4,500 images and about 44,100 keyframes respectively. The results show that based on a large visual vocabulary the model runs extremely fast on even very large datasets while having comparable retrieval performance to the best performing (continuous feature) models.

<p>Land surface curvature (LSC) is a basic attribute of topography and influences local effects of gravitational energy and surface material transport. However, the calculation of LSCs based on triangulated irregular networks (TINs) has not been fully studied, which restricts further geoscience studies based on TIN digital elevation models (DEMs). The triangular facets and vertices of a TIN are both expressions of the land surface; therefore, based on their adjacency relationship, the LSCs can be calculated. In this study, we propose a mathematical vector framework to enhance LSC system theory. In this framework, LSC can be calculated based on both triangular facets and vertices, and the selection of weighting methods in the framework is flexible. We use the concept of the curvature tensor to interpret and calculate the commonly used LSC, which provides a new perspective in geoscience research. We also investigate the capacity of the TIN-based method to perform LSCs calculations and compare it with grid-based methods. Based on a mathematically simulated surface, we reach the following conclusions. First, the TIN-based method has similar effects on the scale to the grid-based methods of EVANS and ZEVENBERGEN. Second, the TIN-based method is less error sensitive than the grid-based methods by the EVANS and ZEVENBERGEN polynomials for the high error DEMs. Third, the shape of the TIN triangles exerts a great influence on the LSCs calculation, which means that the accuracy of LSCs calculation can be further improved with the optimized TIN but will be discontinuous. Based on three real landforms with different data sources, we discuss the possible applications of the TIN-based method, e.g., the classification of land surface concavity–convexity and hillslope units. We find that the TIN-based method can produce visually better classification results than the grid-based method. This qualitative comparison reflects the potential of using TINs in multiscale geoscience research and the capacity of the proposed TIN-based LSC calculation methods. Our proposed mathematical vector framework for LSCs calculations from TINs is a preliminary approach to mitigate the multiple-scale problem in geoscience. In addition, this research integrates mathematical vector and geographic theories and provides an important reference for geoscience research.</p><p> </p>

The​‍​‌‍​‍‌​‍​‌‍​‍‌ rapid evolution of digital healthcare platforms has raised the need for secure and smart methods that can protect patient data while maintaining accurate disease prediction. The present study offers a futuristic e-healthcare system entitled Optimized Multi-Agent Deep Learning Framework for Lung Cancer Image Retrieval Using Medical Imaging Data. The circulated copy intends to focus on the prediction as well as the detection of lung diseases by utilizing machine learning (ML) and deep learning (DL) models to attain high diagnostic accuracy. A web-based front end has been created using the Django framework to facilitate easy user access to predictions and medical insights. In an attempt to preserve the privacy and security of sensitive health records, blockchain technology has been merged for data storage that is decentralized and tamper-proof. Besides that, multi-agent-based privacy metrics have been activated to keep track of, study, and raise the privacy levels through the system, thus providing an adaptive shield against the leakage of data and unauthorized access. The suggested scheme enhances the security of data privacy and at the same time raises the level of trust, transparency, and efficiency in digital healthcare applications. Such a combined system is an excellent example of how healthcare services can be revolutionized by the union of AI-powered disease detection and privacy-preserving ​‍​‌‍​‍‌​‍​‌‍​‍‌methods.

Most existing object-based image retrieval systems are based on single object matching, with its main limitation being that one individual image region (object) can hardly represent the user’s retrieval target, especially when more than one object of interest is involved in the retrieval. Integrated Region Matching (IRM) has been used to improve the retrieval accuracy by evaluating the overall similarity between images and incorporating the properties of all the regions in the images. However, IRM does not take the user’s preferred regions into account and has undesirable time complexity. In this article, we present a Feedback-based Image Clustering and Retrieval Framework (FIRM) using a novel image clustering algorithm and integrating it with Integrated Region Matching (IRM) and Relevance Feedback (RF). The performance of the system is evaluated on a large image database, demonstrating the effectiveness of our framework in catching users’ retrieval interests in object-based image retrieval.

To overcome the semantic gap in the retrieval process, the user relevance feedback frame work is added to the current image retrieval system. Relevance feedback method iteratively refines and updates the retrieved result by learning the user-labeled examples to further improves the overall performance. In the proposed scheme feature descriptor derived from the EDBTC compressed data stream. Firstly, a color image is decomposed using EDBTC scheme to produce two new image representations, namely color quantizer and bitmap image by using Improved LBG-VQ (ILBG)algorithm. Two image feature descriptors called Color Histogram Feature (CHF), and Bit Pattern Feature(BPF) can be subsequently generated from the EDBTC color quantizer and its corresponding bitmap image respectively without performing the decoding process. The similarity degree between two images is simply measured with the similarity distance score of their feature descriptor. Second, we presented a relevance feedback (RF) framework for effective image retrieval by using a support vector machine (SVM). Effectiveness of EDBTC feature descriptor is quantitatively examined and compared in the RGB color space as well as in HSI color channel. Extensive experiments shows that there is a significant improvement in retrieval performance with the proposed method using SVMRF compared with the retrieval performance without RF.

In the evolving field of healthcare, centralized cloud-based medical image retrieval faces challenges related to security, availability, and adversarial threats. Existing deep learning-based solutions improve retrieval but remain vulnerable to adversarial attacks and quantum threats, necessitating a shift to more secure distributed cloud solutions. This article proposes SFMedIR, a secure and fault tolerant medical image retrieval framework that contains an adversarial attack-resistant federated learning for hashcode generation, utilizing a ConvNeXt-based model to improve accuracy and generalizability. The framework integrates quantum-chaos-based encryption for security, dynamic threshold-based shadow storage for fault tolerance, and a distributed cloud architecture to mitigate single points of failure. Unlike conventional methods, this approach significantly improves security and availability in cloud-based medical image retrieval systems, providing a resilient and efficient solution for healthcare applications. The framework is validated on Brain MRI and Kidney CT datasets, achieving a 60-70% improvement in retrieval accuracy for adversarial queries and an overall 90% retrieval accuracy, outperforming existing models by 5-10%. The results demonstrate superior performance in terms of both security and retrieval efficiency, making this framework a valuable contribution to the future of secure medical image management.