Fusion Based Image Retrieval Using Local and Global Descriptor

Advancements in internet accessibility and the affordability of digital picture sensors have led to the proliferation of extensive image databases utilized across a multitude of applications. Addressing the semantic gap between low-level attributes and human visual perception has become pivotal in refining Content-Based Image Retrieval (CBIR) methodologies, especially within this context. As this field is intensely researched, numerous efficient algorithms for CBIR systems have surfaced, precipitating significant progress in the artificial intelligence field. In this study, we propose employing a hard voting ensemble approach on features derived from three robust deep learning architectures: Inception, Exception, and Mobilenet. This is aimed at bridging the divide between low-level image features and human visual perception. The Euclidean method is adopted to determine the similarity metric between the query image and the features database. The outcome was a noticeable improvement in image retrieval accuracy. We applied our approach to a practical dataset named CBIR 50, which encompasses categories such as mobile phones, cars, cameras, and cats. The effectiveness of our method was thereby validated. Our approach outshone existing CBIR algorithms with superior accuracy (ACC), precision (PREC), recall (REC), and F1-score (F1-S), proving to be a noteworthy addition to the field of CBIR. Our proposed methodology could be potentially extended to various other sectors, including medical imaging and surveillance systems, where image retrieval accuracy is of paramount importance.

As the use of digital media increases, effective retrieval and management techniques become more important. In order to extract useful information from this huge amount of data, many content based image retrieval (CBIR) systems have been developed. A typical CBIR system captures image features such as color, texture, or shape of objects in the query image and tries to retrieve images from the database with similar features. The main advantage of CBIR systems with relevance feedback is that these systems take into account the gap between the high-level concepts and low-level features and subjectivity of human perception of visual content. In this paper, a CBIR system based on color histogram has been presented and a new approach for image storage and retrieval called association-based image retrieval (ABIR) has been studied. The results of both systems have been shown.

Bag of Features (BoF) has been successfully exploited in content-based image retrieval for several years. Due to its performance and popularity, several extensions have been proposed that involve feature description, dictionary building, feature encoding and post-query process, etc. This paper proposes a dynamically weighting scheme for BoF-based image retrieval based on feedback. It involves two contributions: (i) analyzing the statistical distribution characteristic of similar BoF representations and (ii) computing weights dynamically based on the feedback obtained from different initial query results. We quantitatively evaluate the proposed method on two different databases. Experiments confirm that the proposed weighting scheme has better performance than the baseline of BoF-based image retrieval systems. Meanwhile, the results demonstrate the effectiveness of the weighting scheme in terms of the precision of top-N returned images.

State-of-the-art hierarchical localisation pipelines (HLoc) employ image retrieval (IR) to establish 2D-3D correspondences by selecting the top-k most similar images from a reference database. While increasing <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> improves localisation robustness, it also linearly increases computational cost and runtime, creating a significant bottleneck. This paper investigates the relationship between global and local descriptors, showing that greater similarity between the global descriptors of query and database images increases the proportion of feature matches. Low similarity queries significantly benefit from increasing k, while high similarity queries rapidly experience diminishing returns. Building on these observations, we propose an adaptive strategy that adjusts <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> based on the similarity between the query's global descriptor and those in the database, effectively mitigating the feature-matching bottleneck. Our approach reduces computational costs and processing time without sacrificing accuracy. Experiments on three indoor and outdoor datasets show that AIR-HLoc reduces feature matching time by up to 30% while preserving state-of-the-art accuracy. The results demonstrate that AIR-HLoc facilitates a latency-sensitive localisation system.

In the field of computer vision and image processing CBIR (Content based image retrieval) system become an active research area. The CBIR technique involves feature extraction based on image features (like color, shape and texture) and defining rules for comparing image. A classifier is also used by authors for image classification. For this purpose an image database taken from James Z. Wang research group website is used by many authors. Due to enormous increase in the size of database traditional methods of image retrieval by using keywords does not provide accurate result. Thus the concept of CBIR system is emerged. In last couple of years many method of feature extraction is developed but since now researcher are not able to develop a system which has gained high accuracy of human visual perception in distinguishing pictures. Therefore earlier researchers have concentrated to increase the retrieval accuracy of CBIR system by using different combination of features. The objective of this paper is to present review on a CBIR technique which combined four kinds of features set including every kind of feature for developing feature vector. Color based features (histogram), statistical features (mean, median and standard deviation), spatial features (Gabor feature and wavelet features) and texture features (GLCM) is used for forming feature vector. A SVM classifier is used with CBIR system to increase retrieval accuracy. SVM (support vector machine) is a machine learning classifier which provides good classification accuracy. Keywords: CBIR, SVM, NN, GLCM, HSV Color space, Euclidean distance matrix.

The use of Computer-Aided Diagnosis in dermatology raises the necessity of integrating Content-Based Image Retrieval (CBIR) technologies. The latter could be helpful to untrained users as a decision support system for skin lesion diagnosis. However, classical CBIR systems perform poorly due to semantic gap. To alleviate this problem, we propose in this paper an intelligent Content-Based Dermoscopic Image Retrieval (CBDIR) system with Relevance Feedback (RF) for melanoma diagnosis that exhibits: efficient and accurate image retrieval as well as visual features extraction that is independent of any specific diagnostic method. After submitting a query image, the proposed system uses linear kernel-based active SVM, combined with histogram intersection-based similarity measure to retrieve the K most similar skin lesion images. The dominant (melanoma, benign) class in this set will be identified as the image query diagnosis. Extensive experiments conducted on our system using a 1097 image database show that the proposed scheme is more effective than CBDIR without the assistance of RF.

This paper presents novel approaches for combining re-ranking and rank aggregation methods aiming at improving the effectiveness of Content-Based Image Retrieval (CBIR) systems. Given a query image as input, CBIR systems retrieve the most similar images in a collection by taking into account image visual properties. In this scenario, accurately ranking collection images is of great relevance. Aiming at improving the effectiveness of CBIR systems, re-ranking and rank aggregation algorithms have been proposed. However, different re-ranking and rank aggregation approaches, applied to different image descriptors, may produce different and complementary image rankings. In this paper, we present four novel approaches for combining these rankings aiming at obtaining more effective results. Several experiments were conducted involving shape, color, and texture descriptors. The proposed approaches are also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate that our approaches can improve significantly the effectiveness of image retrieval systems.

Content-Based Image Retrieval (CBIR) plays a vital role in various digital image processing fields such as image retrieval, classification, feature extraction, clustering, and indexing. In some cases, the high computational time as well the poor performance of similarity score makes the process of image retrieval an unsuitable one for CBIR having larger datasets. To overcome this trauma, the article presents a combined scheme to perform image retrieval and feature extraction using an eminent utilization of angular patterned wavelet Fourier descriptor with Randomized Robust Learning. With this prominent technique, both the local and the global feature descriptors are extracted to attain a maximum retrieval accuracy. Furthermore, the learning process is made prominent, owing to the unique extracted features. It makes the process of indexing similar images faster and the retrieval of relevant images with less computational time in an organized manner. Our proposed methodology is executed in MATLAB and is compared with the existing methodologies regarding retrieval accuracy and surfing time by fast indexed output.

In recent trends, Content Based image retrieval (CBIR) is a vast as well as an attractive research area, where various active researchers are doing their respective work. It is the widely used technique of image retrieval, which enables the system to retrieve the relevant images from wide range of image database following the user's query image. In designing of good CBIR system, to select an appropriate feature descriptor which can represent the image content efficiently is not an easy task. In this proposed work, an efficient CBIR system has been suggested for image retrieval which mainly focused on the classification of image database as well as appropriate image representation. Here, we used HSV histogram, discrete wavelet transform and local as well as global edge histogram descriptor with SVM classifier based on RBF kernel function. In the scheme of feature evaluation, first extracted quantized HSV histogram to extract the color feature of image, applied discrete wavelet transform on the each component (Hue, Saturation and value components) of the HSV image to extract the complex texture pattern of image and for evaluation of geometric as well as spatial information of image applied local as well as global edge histogram descriptor on the Value component of HSV Image. After combining the all feature vectors, SVM Classifier applied on the image feature database to classify the images appropriately. For experimental analysis, this proposed methodology applied on the Wang image database of 1-k images with 10 categories. On the basis of Precision, recall and accuracy, it is found that this system, based on classification, is performing well in comparison to other existing proposed schemes.

In this paper, we propose a new visual feature extraction method for content-based image retrieval (CBIR) based on wavelet transform which has both spatial-frequency and multi-resolution characteristics. We extract visual features for each frequency band in wavelet transformation and use them for CBIR. The lowest frequency band involves utilizing the spatial information of an original image. We extract 64 feature vectors using fuzzy homogeneity in the wavelet domain, which considers both the wavelet coefficients and the spatial information of each coefficient. In addition, we extract 3 feature vectors using the energy values of high frequency bands, and store those to the image database. As a query, we retrieve the most similar image from the image database according to the 10 largest homograms (normalized fuzzy homogeneity vectors) and 3 energy values. Simulation results show that the proposed method has good accuracy in image retrieval using 90 texture images.

In recent years, with the development of digital image techniques and digital albums in the Internet, the use of digital image retrieval process has increased dramatically. An image retrieval system is a computer system for browsing, searching and retrieving images from large databases of digital images. In order to increase the accuracy of image retrieval, a content-based image retrieval system(CBIR) based on interactive genetic algorithm (IGA) is proposed. Color, texture and edge have been the primitive low level image descriptors in content based image retrieval systems. In this paper we proposed a system that splits the retrieval process into two stages. In the query stage, the feature descriptors of a query image were extracted and then used to evaluate the similarity between the query image and those images in the database. In the evolution stage, the most relevant images were retrieved by using the IGA. IGA is employed to help the users identify the images that are most satisfied to the users' need. The experimental evaluation of the system is based on a 10000 WANG color image database. Experimental results demonstrate the feasibility of the proposed approach.

Content-Based Image Retrieval (CBIR) systems play a crucial role in managing the exponential growth of digital image collections. Their task is to retrieve relevant images by analysing the content of a query image rather than relying on metadata. The idea here is to extract relevant features from the query image and find a similar set of features in other images. The current generation of CBIR systems faces difficulties in bridging the “semantic gap” between image features at low levels and human perception at high levels which reduces retrieval precision. The research targets CBIR performance enhancement by developing state-of-the-art deep learning techniques for feature extraction. We implemented two approaches which included a custom Convolutional Neural Network (CNN) with six convolutional layers and a finetuned ResNet50 model trained on the CIFAR-10 dataset, and the finetuned model demonstrated better performance than numerous existing CBIR systems. The networks extracted 512-dimensional feature vectors from their penultimate layer for subsequent similarity-matching operations. The fine-tuned ResNet50 model delivered better retrieval results than our custom CNN model since it reached a Mean Average Precision (MAP) score of 98.7%, while the custom CNN achieved 87.3%. We built a web-based interface that allows users to perform real-time image retrieval through multiple evaluation metrics.

Content-based image retrieval (CBIR) has been widely researched for medical images. In application of histo- pathological images, there are two issues that need to be carefully considered. The one is that the digital slide is stored in a spatially continuous image with a size of more than 10K x 10K pixels. The other is that the size of query image varies in a large range according to different diagnostic conditions. It is a challenging work to retrieve the eligible regions for the query image from the database that consists of whole slide images (WSIs). In this paper, we proposed a CBIR framework for the WSI database and size-scalable query images. Each WSI in the database is encoded and stored in a matrix of binary codes. When retrieving, the query image is first encoded into a set of binary codes and analyzed to pre-choose a set of regions from database using hashing method. Then a multi-binary-code-based similarity measurement based on hamming distance is designed to rank proposal regions. Finally, the top relevant regions and their locations in the WSIs along with the diagnostic information are returned to assist pathologists in diagnoses. The effectiveness of the proposed framework is evaluated in a fine-annotated WSIs database of epithelial breast tumors. The experimental results show that proposed framework is both effective and efficiency for content-based whole slide image retrieval.

Content Based Image Retrieval (CBIR) is a process in which for a given query image similar images will be retrieved based on the image content similarity. Image content refers to its visual features, which are mathematical representations of a digital image. The image retrieval task primarily depends on image feature extraction and similarity measurement between the feature vectors. The performance of CBIR process not only decided by the optimum features extracted from the image but also on the proper choice of the similarity/dissimilarity measures (distance metrics). As the image features broadly diversified in terms of color, texture and shape based, using the same distance metric may not work well for all of these features. In this paper, first we presented overview of geometric and statistical distance metrics used in CBIR along with the comparative analysis of these measures on color and texture features. Color features extracted by computing color histograms in HSV space and texture features by wavelet decompositions. Geometrical distances such as Manhattan, Chebyshev, Euclidean, statistical distance metrics such as Cosine Similarity, Chi-square, KullbackLeibler, Jeffrey and cumulative statistical distance metrics of Kolmogorov-Smirnov, Cramer von Mises and Earthmover's distances were analyzed for feature similarity. We gave certain conclusions on the performance of all these distance metrics in terms of Mean Average Precision (MAP) and Recall rates with color and texture features respectively.

Content-based image retrieval (CBIR) is a hard task which consists in retrieving similar content from a large multimedia database. In the literature, in order to extract descriptors from the images the CBIR techniques use several low-level features such as color, texture, shape, contours, among others. In the recent years, several local descriptors based on the detection of feature points have been used to retrieve the most similar images with different geometric and photometric characteristics. In this paper we propose a CBIR technique that involves the combination of a local descriptor obtained from the Speeded Up Robust Feature (SURF) algorithm together with an effective and fast object matching operation in order to improve the search speed and the retrieval accuracy related to the Mexican archaeological imaging. In order to reduce the computational complexity of the proposed method, Quarter Common Intermediate Format (QCIF) is used previous of computing the SURF descriptor. To measure the performance of the proposed technique the precision and recall metrics are used. The experimental results show the accuracy of the proposed CBIR technique applied to a data base of Mexican culture images that are captured by several environmental conditions and different acquisition equipment.