Content-based Image Retrieval Research Articles

Query extraction based on encrypted features for CBIR from cloud

Due to the increasing use of mobile devices, content-based image retrieval is gaining massive popularity as mobile devices run on batteries. It cannot perform heavy image processing computation, so mobile users can extract just image features and offload them to the cloud. The cloud will perform content-based image searches and return a search result. COREL10K images dataset was selected, and VGG16, RESNET, DENSENET, and MOBILE NET algorithms were applied. Finally, the method with the best performance is preferred. Also, PAHE (Packed Additive Homomorphic Encryption) algorithm is selected to encrypt the feature vectors, and image similarity calculations are done with Secure Multi-party Computation (SMC). The following parameters are used for each algorithm to calculate accuracy, precision, recall, Jaccard index, error rates, and F1-score. The algorithms are then compared and selected the best algorithm. The best model obtained is VGG16, with the highest accuracy. The procedure can help Mobile users perform content-based image searches by extracting features and then uploading them to the cloud.

AI co-pilot: content-based image retrieval for the reading of rare diseases in chest CT

The aim of the study was to evaluate the impact of the newly developed Similar patient search (SPS) Web Service, which supports reading complex lung diseases in computed tomography (CT), on the diagnostic accuracy of residents. SPS is an image-based search engine for pre-diagnosed cases along with related clinical reference content (https://eref.thieme.de). The reference database was constructed using 13,658 annotated regions of interest (ROIs) from 621 patients, comprising 69 lung diseases. For validation, 50 CT scans were evaluated by five radiology residents without SPS, and three months later with SPS. The residents could give a maximum of three diagnoses per case. A maximum of 3 points was achieved if the correct diagnosis without any additional diagnoses was provided. The residents achieved an average score of 17.6 ± 5.0 points without SPS. By using SPS, the residents increased their score by 81.8% to 32.0 ± 9.5 points. The improvement of the score per case was highly significant (p = 0.0001). The residents required an average of 205.9 ± 350.6 s per case (21.9% increase) when SPS was used. However, in the second half of the cases, after the residents became more familiar with SPS, this increase dropped to 7%. Residents’ average score in reading complex chest CT scans improved by 81.8% when the AI-driven SPS with integrated clinical reference content was used. The increase in time per case due to the use of the SPS was minimal.

Usage of Water Marking-Based Techniques for Performing Necessary Operations on a Plaintext Image in the Cloud

To provide the image with security multiple encryption techniques are used. This way the image is converted to a form in which it is not read by a third party unless they have the watermark which is known to only the user. Some cryptographic protocols have been constructed, the emergence of quantum computers and quantum algorithms presents a problematic scenario for those protocols. Data-driven and Feedback-Enhanced Trust (DFET) is developed due to the multi cloud environment created by the multiple data centers. A method for quantum picture watermarking is provided to blend a grayscale quantum watermark into a quantum carrier image.Multiple image search protocols are used in which the image is searched based on their specialities. for example, Content-Based Image Retrieval (CBIR), Convolutional Neural Network (CNN). scale-invariant feature transform (SIFT) approach for encrypted images that protects privacy. PRISMA checklist in addition to a few components of the Cochrane Quality Assessment. social media and gaming applications have been widely adopted by the general public and the number of social media and gaming applications has increased, with the help of white hacking it has established a security technique, stealth robot conceals itself from the intended target/victim by using stealth tactics. Making it easier for protection.

Deep transfer learning enabled DenseNet model for content based image retrieval in agricultural plant disease images

Deep transfer learning enabled DenseNet model for content based image retrieval in agricultural plant disease images

Locality-Sensitive Hashing of Soft Biometrics for Efficient Face Image Database Search and Retrieval

As multimedia technology has advanced in recent years, the use of enormous image libraries has dramatically expanded. In applications for image processing, image retrieval has emerged as a crucial technique. Content-based face image retrieval is a well-established technology in many real-world applications, such as social media, where dependable retrieval capabilities are required to enable quick search among large numbers of images. Humans frequently use faces to recognize and identify individuals. Face recognition from official or personal photos is becoming increasingly popular as it can aid crime detectives in identifying victims and criminals. Furthermore, a large number of images requires a large amount of storage, and the process of image comparison and matching, consequently, takes longer. Hence, the query speed and low storage consumption of hash-based image retrieval techniques have garnered a considerable amount of interest. The main contribution of this work is to try to overcome the challenge of performance improvement in image retrieval by using locality-sensitive hashing (LSH) for retrieving top-matched face images from large-scale databases. We use face soft biometrics as a search input and propose an effective LSH-based method to replace standard face soft biometrics with their corresponding hash codes for searching a large-scale face database and retrieving the top-k of the matching face images with higher accuracy in less time. The experimental results, using the Labeled Faces in the Wild (LFW) database together with the corresponding database of attributes (LFW-attributes), show that our proposed method using LSH face soft biometrics (Soft BioHash) improves the performance of face image database search and retrieval and also outperforms the LSH hard face biometrics method (Hard BioHash).

Efficient medical image retrieval system using Geometric Invariant Point Bilateral Transformation (GIPBT)

Sensor rich environments assist CBIR system to provide granularity in detail for many applications. From sensor rich environments, CBIR can provide the process to exploit images that can integrate both search & retrieval mechanisms. Era of digital technology with Smart devices connected to internet so as to communicate is made possible with Internet of Things (IoT). As IoT deals with huge data in the form of images or videos, to be communicated between smart devices through IoT, deals with complex data processing. Proposed Image Retrieval System reduces the computation overhead for wide range of IoT applications. Medical Images are not only image which holds the pixel also the valuable information of medical diagnosis of every human being. Medical image retrieval has become an inescapable task in every hospital IT system due to the influx of medical pictures. A novel texture fusion technique and a rapid similarity measure metric were used in this study to create an efficient medical CBIR. Proposed feature extraction method of Geometric Invariant Point Bilateral Transformation (GIPBT) algorithm provides the texture information. In this method features are computed as point-to-point geometric information of bilateral filtered image. It automatically inoculates the universal information into the local descriptor and reinforces the feature depiction. To further enhance the descriptor, we used Histogram of Second Order Gradient (HSOG) feature extraction method. By use of these two features, we are performing the feature matching. To analyze and categorize the non-linearity between the features, we propose the kernalized discriminant analysis concept into the score prediction metric. Our proposed similarity measure method is Discriminant Kernalized Disparity (DKD) metric. In DKD, kernel applied Eigen decomposition is utilized for each feature set and disparity metric is evaluated. Finally the proposed system is simulated and evaluated with different medical database images and retrieval performance of Retrieval Efficiency, Normalized Average Rank of Retrieval, Precision, Recall, SSIM and processing Time. Some previous implementations are examined and compared to our results. The proposed method has produced Retrieval efficiency of 98.4%, NARR of 15.18%, Precision and Recall of 98.4%, F1 score of 98.39%, Correlation of 98.2%, SSIM of 97.92% and all at a speed of 30 s 5% more precision as well as less processing time are achieved compared to prior efforts by our proposed solution.

Two-layer content-based image retrieval technique for improving effectiveness

Two-layer content-based image retrieval technique for improving effectiveness

An Efficient CNN-Based Method for Content-Based Image Retrieval

Image recovery has been one of the most fascinating and active study fields in the field of computer vision. The use of content-based image retrieval (CBIR) systems allows for the automatic indexing, searching, retrieval, and exploration of picture datasets. Important characteristics in content-based picture retrieval systems include colour - texture elements. As a result, content-based image retrieval (CBIR) is attractive as a source of precise and speedy retrieval in the modern era. The (CBIR) system uses a feature-based approach to retrieve images from image databases. Low grade characteristics and high grade characteristics are the two categories that image features fall under. Low level aspects of an image include colour, texture, and shape, whereas high level features define the image's semantic content. CBIR is a rapidly developing technology, and as datasets grow as a result of recent advancements in multimedia, it is crucial to enhance this technology to suit user needs.

Material and textural features-based retrieval using feature similarity mapping for synthetic images

Content Based image retrieval (CBIR) is one of the prominent application of image processing where image retrieval from the database is made automatic based on the content in it. The materialist details of the images contains high degree of information and can serve as important toll for analysis. Different variant of content based image retrieval work by locating an object in the image and then retrieving images with similar object in it. The method works using different similarity assessment techniques. In this research work, we have developed a new material feature and HMMD space CBIR technique which works by transforming the domain to HMMD space and then finding the material and Texture Features along with other relevant features. These features forms he feature vector and are then deployed to assess the similarity of the two images which then generates a relevant and irrelevant image search. The system has higher accuracy of assessment as verified by experimentation for precision, productivity and precision agriculture.

CBIR-ANR: A content-based image retrieval with accuracy noise reduction

CBIR-ANR: A content-based image retrieval with accuracy noise reduction

A deep learning content-based image retrieval approach using cloud computing

Due to the rapid growth in multimedia content and its visual complexity, contentbased image retrieval (CBIR) has become a very challenging task. Existing works achieve high precision values at first retrieval levels such as top 10 and top 20 images, but low precision values at subsequent levels such as top 40, 50, and 70, so the goal of this paper is to propose a new CBIR approach that achieves high precision values at all retrieval levels. The proposed method combines features extracted from the pre-trained AlexNet model and discrete cosine transform (DCT). Then principal components analysis (PCA) is performed on AlexNet’s features and feeding these combination to multiclass support vector machine (SVM). The euclidean distance is used to measure the similarity between query and stored images features within the predicted class by SVM. Finally top similar images are ranked and retrieved. All above techniques require huge computational power which may not be available on client machine thus, the processing of these tasks is processed on cloud. Experimental results on the benchmark Corel-1k show that the proposed method achieves high precision value 97% along all retrieval levels top 10, 20 and 70 images and requiring less memory compared to other methods.

An Accurate and Privacy-Preserving Retrieval Scheme Over Outsourced Medical Images

With the rapid advancement in medical imaging techniques, Content-Based (medical) Image Retrieval (CBIR), which can assist in disease diagnosis, has gained much attention in both academia and industry. However, due to patients’ sensitive information involved in medical images, privacy-preserving CBIR is a challenge worth exploiting. Though several privacy-preserving CBIR schemes have been put forth, they can only resist known-background attack (KBA), and do not suffice for protecting the image privacy in outsourced settings. In this article, aiming at the above challenge, we first design a novel Privacy-preserving Mahalanobis Distance Comparison (PMDC) method to improve the accuracy of medical images retrieval. Then, combined with the Mahalanobis distance based Fuzzy C-Means (FCM-M) algorithm, a scheme named TAMMIE is proposed to achieve accurate and privacy-preserving medical image retrieval over encrypted data. With TAMMIE, an image owner can securely outsource the images and indexes to a cloud server, and query users can request retrieval services from the cloud server while keeping their queries private. Detailed security analysis shows that our proposed schemes are secure under the attack stronger than KBA. Furthermore, thorough empirical experiments conducted on two real-world and one synthetic datasets also demonstrate the efficiency of TAMMIE.

Shuffled-Xception-DarkNet-53: A content-based image retrieval model based on deep learning algorithm

This paper proposes Shuffled-Xception-DarkNet-53, an advanced version of DarkNet-53 for Content-Based Image Retrieval (CBIR). The proposed model introduced the notion of the Shuffled -Xception module, which uses three sets of 1 × 1, 3 × 3, and 5 × 5 size filters using a serial connection in place of a single 3 × 3 size filter to extract more refined features from the input images. Instead of the standard 2D Convolution operation, 'Group Convolution' is employed in the proposed Shuffled -Xception module to make the training process of the proposed CNN more efficient. Furthermore, 'Group Convolution' improves the co-relations among the filters of the corresponding Shuffled -Xception module, resulting in more informative features. Between every two serial Group Convolution layers of the same size, one Channel Shuffle layer is used to prevent the loss of information flow among the channels of different groups. The proposed method outperformed the twelve compared methods, including conventional and CNN-based CBIR methods, in ten standard image datasets.

Unsupervised Content Based Image Retrieval Using Pre-Trained CNN and PCNN Features Extractors

Unsupervised Content Based Image Retrieval Using Pre-Trained CNN and PCNN Features Extractors

Content based video retrieval system using two stream convolutional neural network

Content based video retrieval system using two stream convolutional neural network

Efficient and secure content-based image retrieval with deep neural networks in the mobile cloud computing

Smart devices offer a variety of more convenient forms to help us record our lives and generate a large amount of data in this process. Limited by the local storage capacity, many users outsource their image data directly to the cloud server. However, images stored in plaintext on the cloud server are very insecure, resulting in image privacy information can be easily leaked. Therefore, users will encrypt the images and outsource them to the cloud server, but the encrypted images cannot be retrieved. Therefore, we proposed a secure and efficient ciphertext image retrieval scheme based on image content retrieval (CBIR) and approximate homomorphic encryption (HE). First, we used approximate homomorphic encryption to encrypt images after resizing and uploaded the ciphertext images to the cloud for feature extraction of ciphertext. At the same time, the large images (size, dimension, and resolution) would generate data inflation after using homomorphic encryption. Therefore, the original images are encrypted using the chaotic image encryption scheme to reduce ciphertext size and computation costs. Second, we proposed two deepening network depth optimization strategies that address the problem of insufficient neural network depth. Finally, reducing the dimensionality of the ciphertext feature vector using locally sensitive hashing (LSH) can accelerate the retrieval of ciphertext images. Compared with other literature, our ciphertext image retrieval scheme can significantly reduce the rounds of user-server communication.

Deep learning for content-based image retrieval in FHE algorithms

AbstractContent-based image retrieval (CBIR) is a technique used to retrieve image from an image database. However, the CBIR process suffers from less accuracy to retrieve many images from an extensive image database and prove the privacy of images. The aim of this article is to address the issues of accuracy utilizing deep learning techniques such as the CNN method. Also, it provides the necessary privacy for images using fully homomorphic encryption methods by Cheon–Kim–Kim–Song (CKKS). The system has been proposed, namely RCNN_CKKS, which includes two parts. The first part (offline processing) extracts automated high-level features based on a flatting layer in a convolutional neural network (CNN) and then stores these features in a new dataset. In the second part (online processing), the client sends the encrypted image to the server, which depends on the CNN model trained to extract features of the sent image. Next, the extracted features are compared with the stored features using a Hamming distance method to retrieve all similar images. Finally, the server encrypts all retrieved images and sends them to the client. Deep-learning results on plain images were 97.87% for classification and 98.94% for retriever images. At the same time, the NIST test was used to check the security of CKKS when applied to Canadian Institute for Advanced Research (CIFAR-10) dataset. Through these results, researchers conclude that deep learning is an effective method for image retrieval and that a CKKS method is appropriate for image privacy protection.

Privacy-preserving multi-source content-based image retrieval for IoT in cloud computing

Privacy-preserving multi-source content-based image retrieval for IoT in cloud computing

Batik Images Retrieval Using Pre-trained model and K-Nearest Neighbor

Batik is an Indonesian cultural heritage that should be preserved. Over time, many batik motifs have sprung up, which can lead to mutual claims between craftsmen. Therefore, it is necessary to create a system to measure the similarity of a batik motif. This research is focused on making Content-Based Image Retrieval (CBIR) on batik images. The dataset used in this research is big data Batik images. The authors used transfer learning on several pre-trained models and used Convolutional Neural Network (CNN) Autoencoder from previous studies to extract features on all images in the database. The extracted features calculate the Euclidean distance between the query and all images in the database to retrieve images. The image closest to the query will be retrieved according to the number of r, namely 3, 5, 10, or 15. Before the image is retrieved, the retrieval system is used to re-ranked with K-Nearest Neighbor (KNN), which classifies the retrieved image. The results of this study prove that MobileNetV2 + KNN is the best model in terms of Image Retrieval Batik, followed by InceptionV3 and VGG19 as the second and third ranks. Moreover, CNN Autoencoder from previous research and InceptionResNetV2 are ranked fourth and fifth. In this study, it was also found that the use of KNN re-ranking can increase the precision value by 0.00272. For further research, deploying these models, especially for MobileNetV2 is an approach for seeing a major impact on batik craftsmanship for decreasing batik motif plagiarism.

Hybrid Bag-of-Visual-Words and FeatureWiz Selection for Content-Based Visual Information Retrieval.

Recently, content-based image retrieval (CBIR) based on bag-of-visual-words (BoVW) model has been one of the most promising and increasingly active research areas. In this paper, we propose a new CBIR framework based on the visual words fusion of multiple feature descriptors to achieve an improved retrieval performance, where interest points are separately extracted from an image using features from accelerated segment test (FAST) and speeded-up robust features (SURF). The extracted keypoints are then fused together in a single keypoint feature vector and the improved RootSIFT algorithm is applied to describe the region surrounding each keypoint. Afterward, the FeatureWiz algorithm is employed to reduce features and select the best features for the BoVW learning model. To create the codebook, K-means clustering is applied to quantize visual features into a smaller set of visual words. Finally, the feature vectors extracted from the BoVW model are fed into a support vector machines (SVMs) classifier for image retrieval. An inverted index technique based on cosine distance metric is applied to sort the retrieved images to the similarity of the query image. Experiments on three benchmark datasets (Corel-1000, Caltech-10 and Oxford Flower-17) show that the presented CBIR technique can deliver comparable results to other state-of-the-art techniques, by achieving average accuracies of 92.94%, 98.40% and 84.94% on these datasets, respectively.