Retrieval Of Similar Images Research Articles

Integration of a three-colour channel with the four diagonals of the GLCM approach for similar image retrieval

Integration of a three-colour channel with the four diagonals of the GLCM approach for similar image retrieval

Integration of a three-colour channel with the four diagonals of the GLCM approach for similar image retrieval

Integration of a three-colour channel with the four diagonals of the GLCM approach for similar image retrieval

Content-based Image Retrieval by Using Deep Learning for Interstitial Lung Disease Diagnosis with Chest CT.

Background Evaluation of interstitial lung disease (ILD) at CT is a challenging task that requires experience and is subject to substantial interreader variability. Purpose To investigate whether a proposed content-based image retrieval (CBIR) of similar chest CT images by using deep learning can aid in the diagnosis of ILD by readers with different levels of experience. Materials and Methods This retrospective study included patients with confirmed ILD after multidisciplinary discussion and available CT images identified between January 2000 and December 2015. Database was composed of four disease classes: usual interstitial pneumonia (UIP), nonspecific interstitial pneumonia (NSIP), cryptogenic organizing pneumonia, and chronic hypersensitivity pneumonitis. Eighty patients were selected as queries from the database. The proposed CBIR retrieved the top three similar CT images with diagnosis from the database by comparing the extent and distribution of different regional disease patterns quantified by a deep learning algorithm. Eight readers with varying experience interpreted the query CT images and provided their most probable diagnosis in two reading sessions 2 weeks apart, before and after applying CBIR. Diagnostic accuracy was analyzed by using McNemar test and generalized estimating equation, and interreader agreement was analyzed by using Fleiss κ. Results A total of 288 patients were included (mean age, 58 years ± 11 [standard deviation]; 145 women). After applying CBIR, the overall diagnostic accuracy improved in all readers (before CBIR, 46.1% [95% CI: 37.1, 55.3]; after CBIR, 60.9% [95% CI: 51.8, 69.3]; P < .001). In terms of disease category, the diagnostic accuracy improved after applying CBIR in UIP (before vs after CBIR, 52.4% vs 72.8%, respectively; P < .001) and NSIP cases (before vs after CBIR, 42.9% vs 61.6%, respectively; P < .001). Interreader agreement improved after CBIR (before vs after CBIR Fleiss κ, 0.32 vs 0.47, respectively; P = .005). Conclusion The proposed content-based image retrieval system for chest CT images with deep learning improved the diagnostic accuracy of interstitial lung disease and interreader agreement in readers with different levels of experience. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Wielpütz in this issue.

A shape and texture features fusion to retrieve similar Trademark Image Material

Trademark images or materials such as symbols, text, logos, image, design or phrase are used to unique representation of any organization. Retrieval of trademark material images are important to protect the new trademark image that is to be registered. Therefore, retrieval of similar trademark images is required. In this paper, an approach is presented to extract more similar trademark images so that a unique trademark image can be registered. In this paper, Zernike moment of the query image and dataset images are computed, then most similar images from the dataset are retrieved at the first layer refinement. In the second layer, texture features are extracted of query image and refined dataset images to retrieve most appropriate similar images. Zernike moments is applied to extract global shape features and Scale Invariant Feature Transform (SIFT) and Speeded-Up Robust Feature (SURF) are applied to extract texture features on the basis of a few key-points of the trademark images. A weighted average of both the key-points feature vectors is computed for retrieving the rank1, rank5, rank10, rank15 and rank20 most similar images using Euclidean distance. Experiments have been performed on a proposed dataset to perform the analysis and found that proposed work perform better and improves the accuracy.

Content-Based Medical Image Retrieval Using Delaunay Triangulation Segmentation Technique

This article presents a novel technique for retrieval of lung images from the collection of medical CT images. The proposed content-based medical image retrieval (CBMIR) technique uses an automated image segmentation technique called Delaunay triangulation (DT) in order to segment lung organ (region of interest) from the original medical image. The proposed method extracts novel and discriminant features from the segmented lung region instead of extracting novel features from the whole original image. For the extraction of shape features, the authors employ edge histogram descriptor (EHD) and geometric moments (GM), and for the extraction of texture features, the authors use gray-level co-occurrence matrix (GLCM) technique. The shape and texture features are combined to form the hybrid feature which is used for retrieval of similar lung images. The proposed method is evaluated using two benchmark datasets of lung CT images. The simulation results prove that the proposed CBMIR framework shows improved performance in terms of retrieval accuracy and retrieval time.

Discriminative shared transform learning for sketch to image matching

Sketch to digital image matching refers to the problem of matching a sketch image (often drawn by hand or created by a software) against a gallery of digital images (captured via an acquisition device such as a digital camera). Automated sketch to digital image matching has applicability in several day to day tasks such as similar object image retrieval, forensic sketch matching in law enforcement scenarios, or profile linking using caricature face images on social media. As opposed to the digital images, sketch images are generally edge-drawings containing limited (or no) textural or colour based information. Further, there is no single technique for sketch generation, which often results in varying artistic or software styles, along with the interpretation bias of the individual creating the sketch. Beyond the variations observed across the two domains (sketch and digital image), automated sketch to digital image matching is further marred by the challenge of limited training data and wide intra-class variability. In order to address the above problems, this research proposes a novel Discriminative Shared Transform Learning (DSTL) algorithm for sketch to digital image matching. DSTL learns a shared transform for data belonging to the two domains, while modeling the class variations, resulting in discriminative feature learning. Two models have been presented under the proposed DSTL algorithm: (i) Contractive Model (C-Model) and (ii) Divergent Model (D-Model), which have been formulated with different supervision constraints. Experimental analysis on seven datasets for three case studies of sketch to digital image matching demonstrate the efficacy of the proposed approach, highlighting the importance of each component, its input-agnostic behavior, and improved matching performance.

Distress Image Retrieval for Infrastructure Maintenance via Self-Trained Deep Metric Learning Using Experts’ Knowledge

Distress image retrieval for infrastructure maintenance via self-trained deep metric learning using experts’ knowledge is proposed in this paper. Since engineers take multiple images of a single distress part for inspection of road structures, it is necessary to construct a similar distress image retrieval method considering the input of multiple images to support determination of the level of deterioration. Thus, the construction of an image retrieval method while selecting an effective input from multiple images is described in this paper. The proposed method performs deep metric learning by using a small number of effective images labeled by experts’ knowledge with information about their effectiveness and a large number of unlabeled images via a self-training approach. Specifically, an end-to-end learning approach that performs retraining of the model by assigning pseudo-labels to these unlabeled images according to the output confidence of the model is achieved. Thus, the proposed method can select an effective image from multiple images that are input at the retrieval as a query image. This is the main contribution of this paper. As a result, the proposed method realizes highly accurate retrieval of similar distress images considering the actual situation of inspection in which multiple images of a distress part are input.

Image Retrieval Using the Fused Perceptual Color Histogram.

Extracting visual features for image retrieval by mimicking human cognition remains a challenge. Opponent color and HSV color spaces can mimic human visual perception well. In this paper, we improve and extend the CDH method using a multi-stage model to extract and represent an image in a way that mimics human perception. Our main contributions are as follows: (1) a visual feature descriptor is proposed to represent an image. It has the advantages of a histogram-based method and is consistent with visual perception factors such as spatial layout, intensity, edge orientation, and the opponent colors. (2) We improve the distance formula of CDHs; it can effectively adjust the similarity between images according to two parameters. The proposed method provides efficient performance in similar image retrieval rather than instance retrieval. Experiments with four benchmark datasets demonstrate that the proposed method can describe color, texture, and spatial features and performs significantly better than the color volume histogram, color difference histogram, local binary pattern histogram, and multi-texton histogram, and some SURF-based approaches.

A deep community based approach for large scale content based X-ray image retrieval.

A computer assisted system for automatic retrieval of medical images with similar image contents can serve as an efficient management tool for handling and mining large scale data, and can also be used as a tool in clinical decision support systems. In this paper, we propose a deep community based automated medical image retrieval framework for extracting similar images from a large scale X-ray database. The framework integrates a deep learning-based image feature generation approach and a network community detection technique to extract similar images. When compared with the state-of-the-art medical image retrieval techniques, the proposed approach demonstrated improved performance. We evaluated the performance of the proposed method on two large scale chest X-ray datasets, where given a query image, the proposed approach was able to extract images with similar disease labels with a precision of 85%. To the best of our knowledge, this is the first deep community based image retrieval application on large scale chest X-ray database.

Deep multi query image retrieval

There exist few studies investigating the multi-query image retrieval problem. Existing methods are not based on hash codes. As a result, they are not efficient and fast. In this study, we develop an efficient and fast multi-query image retrieval method when the queries are related to more than one semantic. Image hash codes are generated by a deep hashing method. Consequently, the method requires lower storage space, and it is faster compared to the existing methods. The retrieval is based on the Pareto front method. Reranking performed on the retrieved images by using non-binary deep-convolutional features increase retrieval accuracy considerably. Unlike previous studies, the method supports an arbitrary number of queries. It outperforms similar multi-query image retrieval studies in terms of retrieval time and retrieval accuracy.

Texture and colour region separation based image retrieval using probability annular histogram and weighted similarity matching scheme

Content-based image retrieval (CBIR) uses primitive image features for retrieval of similarimages from a dataset. Generally, researchers extract these visual features fromthe whole image. Therefore, the extracted features contain overlappedinformation of texture, colour, and shape features, and it is a criticalchallenge in the field of CBIR. This problem can be overcome by extracting thecolour features from the colour as well as shape and texture features from theintensity dominant part only. In this study, the authors have proposed aniterative algorithm to separate colour and texture dominant part of the imageinto two different images. Here, a combination of edge maps and gradients hasbeen used to achieve separate colour and texture images. Further,scale-invariant feature transform and 2D dual-tree complex wavelet transform hasbeen realised to extract unique shape and texture features from the textureimage. Simultaneously, a probability-based semantic centred annular histogramhas been suggested to extract unique colour features from the colour image.Finally, a novel weighted distance-based feature comparison scheme has beenproposed for similarity matching and retrieval. All the image retrievalexperiments have been carried out on seven standard datasets and demonstratedsignificant improvements over other state-of-arts CBIR systems

Effective and efficient crowd-assisted similarity retrieval of medical images in resource-constraint Mobile telemedicine systems

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.

Image Retrieval System using Residual Neural Network in a Distributed Environment

Development of Content-Based Image Retrieval systems supports retrieval of similar images based on selected features. Selection of appropriate features for this process is a difficult task. In this regard, deep learning concept helps in choosing appropriate features for retrieval. In this work, Content-Based Image Retrieval system is proposed using Convolution Neural Network known as Residual Neural Network model. The dataset used to build retrieval system is collection of web images 50,000 of 250 categories. The model is trained on 40% of image data and tested on 60% of data. When user submits a query image from the client-side, similar features are extracted by the model on server-side. Later, the features of query image are compared with trained images data and similarity is measured using the metric of Euclidean distance. The retrieved resultant images are displayed on Graphical User Interface. The results are comparatively higher with the existing systems. The proposed work is also compared with Google’s Image retrieval system for random query images and our proposed work has shown a better performance by 14.27%.

Content based Image Retrieval System using Combination of Color and Shape Features, and Siamese Neural Network

With an advent of technologya huge collection of digital images is formed as repositories on world wide web (WWW). The task of searching for similar images in the repository is difficult. In this paper, retrieval of similar images from www is demonstrated with the help of combination of image features as color and shape and then using Siamese neural network which is constructed to the requirement as a novel approach. Here, one-shot learning technique is used to test the Siamese Neural Network model for retrieval performance. Various experiments are conducted with both the methods and results obtained are tabulated. The performance of the system is evaluated with precision parameter and which is found to be high.Also, relative study is made with existing works.

Development of Retrieval System using Color from Multi Segments and Shape features from Images as Combination

The world of digital information has been generous to produce large data. The task of finding similar images in such a vast repository in real-time is very challenging. In this paper, Content Based Retrieval System is proposed to retrieve similar images with a novel approach of combining the image features like color and shape. The work includes extraction of color feature from images by dividing them into five significant portions, which emphasizes on center portion of an image where object may reside. This process is carried out and represented using color histograms. Next, shape features are extracted using Hu - moments for the entire image. Later, by combining these two features, similar image retrieval is done based on a query. Various trials of retrieval have been carried out with different categories and results are tabulated. These results are compared with existing works and shows high performance.

An Enhanced Framework for Content Based Medical Image Retrieval using Deep Neural Network

As the technology growth fuelled by low cost tech in the areas of compute, storage the need for faster retrieval and processing of data is becoming paramount for organizations. The medical domain predominantly for medical image processing with large size is critical for making life critical decisions. Healthcare community relies upon technologies for faster and accurate retrieval of images. Traditional, existing problem of efficient and similar medical image retrieval from huge image repository are reduced by Content Based Image Retrieval (CBIR) . The major challenging is an semantic gap in CBIR system among low and high level image features. This paper proposed, enhanced framework for content based medical image retrieval using DNN to overcome the semantic gap problem. It is outlines the steps which can be leveraged to search the historic medical image repository with the help of image features to retrieve closely relevant historic image for faster decision making from huge volume of database. The proposed system is assessed by inquisitive amount of images and the performance efficiency is calculated by precision and recall evaluation metrics. Experimental results obtained the retrieval accuracy is 79% based on precision and recall and this approach is preformed very effectively for image retrieval performance.

Image Retrieval using Visual Phrases

Keypoint based descriptors are widely used for various computer vision applications. During this process, key-points are initially detected from the given images which are later represented by some robust and distinctive descriptors like scale-invariant feature transform (SIFT). Keypoint based image-to-image matching has gained significant accuracy for image retrieval type of applications like image copy detection, similar image retrieval and near duplicate detection. Local keypoint descriptors are quantized into visual words to reduce the feature space which makes image-to-image matching possible for large scale applications. Bag of visual word quantization makes it efficient at the cost of accuracy. In this paper, the bag of visual word model is extended to detect frequent pair of visual words which is known as frequent item-set in text processing, also called visual phrases. Visual phrases increase the accuracy of image retrieval without increasing the vocabulary size. Experiments are carried out on benchmark datasets that depict the effectiveness of proposed scheme.

SSIR: Secure similarity image retrieval in IoT

With the development of the Internet of Things (IoT) technology, we are entering a new era of computing technology. This emerging technology allows connectivity for everyone and everything. Thus, IoT encapsulates some intelligence in Internet-connected objects to communicate, exchange information, sharing multimedia data, take a decision, invoke various actions and provide amazing services through smart devices. A huge amount of sensitive information and multimedia data such as images and videos are sharing which generates traffic in the network. Moreover, multimedia data contains high dimension property, which affects image processing including storage and retrieval in IoT environment. Additionally, limited storage capabilities and computing power are drawbacks of smart devices which makes the situation more complicated. To overcome this problem, users prefer to store their multimedia data on a cloud server to make local storage and computation flexible in smart devices, but still security and privacy concerns. To get rid of this challenges, the emergence of Intel Software Guard Extension (SGX) provide a new solution. In this paper, a novel secure similarity image retrieval (SSIR) scheme based on the primitive of content-based image retrieval (CBIR) is proposed to protect the images search. In addition, the proposed SSIR scheme enables the resource-constrained clients to move the process of images as well as the outsource searching operations to the cloud server which reduce the cost. Furthermore, the security analysis shows our scheme is secure in the proposed model. Experiment results illustrate that our scheme is well fitting for images retrieval in practical applications.

Similar image retrieval in large-scale trademark databases based on regional and boundary fusion feature.

In order to retrieve similar trademarks from large-scale trademark databases, combining the characteristics of trademark images, this paper presents a trademark image retrieval method based on regional and border feature fusion. Based on the target image extraction, the proposed approach describes the target region and border features. The region feature description is mainly based on the concept of partition block statistics. The region is divided into equal-area unit using concentric circles, and feature extraction is performed in each small block unit. For the border feature description, this study first detect corners, and then construct a Delaunay graph and extract features by combining the corner detected and the Delaunay triangulation reconstruction. In the search process, the method also incorporates information such as the trademark's color characteristics, trademark classification, and trademark keywords. The present study carried out image retrieval experiment on CE-SHAPE-1 database containing 1400 MPEG-7 core experimental shape, a classification trademark database containing 2000 images, and a national trademark database containing approximately 4.89 million images. The experimental results show that the proposed approach combines the advantages of region and border feature description, and can choose the best among various local optimizations, which makes the retrieval result more effective, more in line with human visual perception, and improves the retrieval accuracy.

Medical image retrieval using self-organising map on texture features

The process of capturing, transfer and sharing of information in the form of digital images have become easier due to the use of advanced technologies. Retrieval of desired images from these huge collections of image databases is one of the popular research areas and has its applications in various fields. An image set consists of images containing objects of different colours, shapes, orientations and sizes. The surface texture of the object in an image may also vary from another object in a different image. These factors make the process of image retrieval a difficult one. In this paper, Self-Organising Map is applied on local texture features for organising the brain magnetic resonance images according to their similarity. The correlation among the pixels is considered for the retrieval of most similar images to the input query image. The experimental results obtained prove the effectiveness of the proposed method for medical images.