Content-based Image Retrieval Method Research Articles

Content-Based Image Retrieval Using Discrete Wavelet Transform and Convolutional Neural Network

Due to the development of internet and digital media techniques the size of digital image collection is increasing rapidly. Various techniques for storing, searching and retrieving images become essential for large image archives. This leads to an existence of Image Retrieval System. Content-Based Image Retrieval (CBIR) is a process of retrieving the expected images from large image databases based on the features of the query image and this is performed by various feature extraction techniques. In this work, two different methods of CBIR have been proposed. The first method is CBIR using Discrete Wavelet Transform (DWT), which extracts the texture feature of an image and histogram extracts the color feature of an image. And also the results will be ranked according to the chi-square distance calculation. The second method is CBIR using Convolutional Neural Network (CNN). In CNN method the features are extracted using VGG16 pre-trained model and canny edge detection is used for detecting the edges of an image. Finally, the performances of DWT and CNN based methods are analyzed and compared.

A Symbolic Contour Representation of Shape for Recognition and Retrieval

Image retrieval technique is one of the most important and vital part of huge image storages. A precise retrieval engine is required to meet the needs of users. In this regard, content-based image retrieval (CBIR) methods based on image contents such as shape, color and texture have been introduced as an alternative of traditional methods to improve the retrieval precision. Of all features of an image, shape holds more valuable information than others. However, due to the dynamic nature of real worlds’ objects, a shape of an object is subject to occlusion, transformation and deformation. This is the main challenge of shape-based retrieval techniques and shape descriptors. In this paper, a new shape representation and description called Symbolic Contour-based Shape Retrieval (SCSR) method is introduced to overcome drawbacks of previous methods in terms of computation time and accuracy. The performance of the proposed method has been compared to other state-of-art methods on three popular datasets, Vehicles, Brown and Mpeg7.

Application of content based image retrieval in digital image search system

Multimedia data is growing rapidly in the current digital era, one of which is digital image data. The increasing need for a large number of digital image datasets makes the constraints faced eventually drain a lot of time and cause the process of image description to be inconsistent. Therefore, a method is needed in processing the data, especially in searching digital image data in large image dataset to find image data that are relevant to the query image. One of the proposed methods for searching information based on image content is content based image retrieval (CBIR). The main advantage of the CBIR method is automatic retrieval process, compared to traditional keyword. This research was conducted on a combination of the HSV color histogram methods and the discrete wavelet transform to extract color features and textures features, while the chi-square distance technique was used to compare the test images with images into a database. The results have showed that the digital image search system with color and texture features have a precision value of 37.5% - 100%, with an average precision value of 80.71%, while the percentage accuracy is 93.7% - 100% with an average accuracy is 98.03%.

Comparison of Pairwise Similarity Distance Methods for Effective Hashing

Content-based image retrieval (CBIR) methods search for points with the most similar content to query features from within a large dataset. The most notable approach for this purpose is an approximate nearest neighbor (ANN) searching. The main properties expected from a retrieval system can be listed as follows; low storage requirement, high retrieve speed, and high average precision. Hashing, which can generate discriminative and low-dimensional binary codes, is one of today’s most effective ANN searching methods. Although there are various hashing approaches in the literature, almost all hashing approaches consist of low-dimension feature representation and binarization sections. This study focuses on the low-dimension feature representation. Hand-crafted or deep learning based approaches are used for feature extraction in hashing methods. These features are the main components that affect the performance in creating binary codes. Contrastive loss is often used in the literature to update the learnable parameters of these feature extraction algorithms. The distance parameter of these data points critical to calculating contrastive loss. In this study, contrastive loss performance is tested using five different distance methods (Euclidean, Manhattan, Cosine, Minkowski, Chebyshev) for more effective feature representation. Retrieval performance is tested using low-dimensional feature vectors produced by these methods in MNIST and CIFAR-10 datasets. It is thought that the information obtained from this study is very useful for new researchers.

Content Based Image Retrieval Using Deep Learning Convolutional Neural Network

Content-based image retrieval (CBIR) is a widely used method for image retrieval from large and unlabeled image collections. However, users are not satisfied with the traditional methods of retrieving information. Moreover the abundance of online networks for production and distribution, as well as the quantity of images accessible to consumers, continues to expand. Therefore, in many areas, permanent as well as widespread digital image processing takes place. Therefore, the rapid access to these large image databases as well as the extraction of identical images from this large set of images from a given image (Query) pose significant challenges as well as involves efficient techniques. A CBIR system’s efficiency depends fundamentally on the calculation of feature representation as well as similarity. For this purpose, they present a basic but powerful deep learning system focused on Convolutional Neural Networks (CNN) and composed of feature extraction and classification for fast image retrieval. We get some promising findings from many detailed observational studies for a number of CBIR tasks using image database, which reveals some valuable lessons for improving the efficiency of CBIR. CBIR systems allow another image dataset to locate related images to such a query image. The search per picture function of Google search has to be the most popular CBIR method.

Pre-trained CNNs Models for Content based Image Retrieval

Content based image retrieval (CBIR) systems is a ‎common recent method for image retrieval and is ‎based mainly ‎on two pillars extracted features and similarity measures. Low ‎level image presentations, ‎based on colour, texture and shape ‎properties are the most common feature extraction methods used ‎by ‎traditional CBIR systems. Since these traditional handcrafted ‎features require good prior domain ‎knowledge, inaccurate ‎features used for this type of CBIR systems may widen the ‎semantic gap and ‎could lead to very poor performance retrieval ‎results. Hence, features extraction methods, which ‎are ‎independent of domain knowledge and have automatic ‎learning capabilities from input image are ‎highly useful. Recently, ‎pre-trained deep convolution neural networks (CNN) with ‎transfer learning ‎facilities have ability to generate and extract ‎accurate and expressive features from image data. Unlike ‎other ‎types of deep CNN models which require huge amount of data ‎and massive processing time ‎for training purposes, the pre-‎trained CNN models have already trained for thousands of ‎classes of large-scale data, including huge ‎images and their ‎information could be easily used and transferred. ResNet18 ‎and ‎SqueezeNet are successful and effective examples of pre-‎trained CNN models used recently in many ‎machine learning ‎applications, such as classification, clustering and object ‎recognition. In this ‎study, we have developed CBIR systems ‎based on features extracted using ResNet18 and SqueezeNet ‎pre-‎trained CNN models. Here, we have utilized these pre-trained ‎CNN models to extract two groups of features ‎that are stored ‎separately and then later are used for online image searching and ‎retrieval. Experimental ‎results on two popular image datasets ‎Core-1K and GHIM-10K show that ResNet18 features ‎based on ‎the CBIR method have overall accuracy of 95.5% and 93.9% for ‎the two datasets, respectively, which ‎greatly outperformed the ‎traditional handcraft features based on the CBIR method.‎

Full Direction Local Neighbors Pattern (FDLNP)

In this paper, we proposed the Full Direction Local Neighbor Pattern (FDLNP) algorithm, which is a novel method for Content-Based Image Retrieval. FDLNP consists of many steps, starting from generating Max and Min Quantizers followed by building two matrix types (the Eight Neighbors Euclidean Decimal Coding matrix, and Full Direction Matrixes). After that, we extracted Gray-Level Co-occurrence Matrix (GLCM) from those matrixes to derive the important features from each GLCM matrixes and finishing with merging the output of previous steps with Local Neighbor Patterns (LNP) histogram. For decreasing the feature vector length, we proposed five extension methods from FDLNP by choosing the specific direction matrixes. Our results demonstrate the effectiveness of our proposed algorithm on color and texture databases, comparing with recent works, with regard to the Precision, Recall, mean Average Precision (mAP), and Average Retrieval Rate (ARR). For enhancing the image retrieval accuracy, we proposed a novel framework that combined the image retrieval system with clustering and classification algorithms. Moreover, we proposed a distributed model that used our FDLNP method with Hadoop to get the ability to process a huge number of images in a reasonable time.

Convolutional neural network based dictionary learning to create hash codes for content-based image retrieval

Abstract This study investigates the suitability of sparse vectors in the dictionary learning (DL) method for content-based image retrieval (CBIR) tasks. Since DL usually performs the learning process in an unsupervised manner, it cannot generate robust features for the retrieval task, especially if a complex background is involved. In order to overcome this drawback, a DL approach using the feature representation power of the convolutional neural network (CNN) is proposed. The initialization values of the dictionaries in the proposed CNN based DL method are taken randomly from the middle layers of the CNN architecture. The vector of each image obtained from the CNN architecture is used as DL input. The lambda vectors produced by the DL structure are converted into binaries. In this way, DL acts as a hash code generator. The performance of the proposed framework is tested on modified COREL dataset. The results prove that it is an open-to-improvement approach and is promising.

A novel approach of image retrieval towards segmentation

At the present time, it becomes simple to stockpile vast quantity of images by means of image processing approach. The hasty right of entry to these ample groups of images and retrieve related images of a specified image from this massive assortment of images presents key challenges and requires competent algorithms. In this manuscript, the authors intend a structure which is proficient to select the most appropriate features to examine newly expected images in that way improving the retrieval accuracy and competence. An enhanced algorithm is projected now. The algorithm comprises of scheming feature vectors after segmentation which will be used in likeness contrast linking query image and database images. The structure is skilled for dissimilar images in the database. The projected method has been tested on a variety of real images and its concert is found to be reasonably acceptable when compared with the concert of conventional methods of content-based image retrieval. The major objective of the anticipated method is to endow with an exact outcome with lesser computational time.

Directional Magnitude Local Hexadecimal Patterns: A Novel Texture Feature Descriptor for Content-Based Image Retrieval

Social media platforms such as Twitter, Facebook, and Flicker, and the evolution of digital image capturing devices have resulted in the generation of a massive number of images. Thus, we experienced an exponential growth in digital image repositories in the last decade. Content-based image retrieval (CBIR) has been extensively employed to reduce the dependency on textual annotations for image searching. Effective feature descriptor is mandatory to retrieve the most relevant images from the repository. Additionally, CBIR methods often experience the semantic gap problem, which must also be addressed. In this paper, we propose a novel texture descriptor, Directional Magnitude Local Hexadecimal Patterns (DMLHP), based on the texture orientation and magnitude to retrieve the most relevant images. The objective of the proposed feature descriptor is to examine the relationship between the neighboring pixels and their adjacent neighbors based on texture orientation and magnitude. Our DMLHP texture descriptor is capable of capturing the texture and semantic information of the images effectively with the same visual content. Furthermore, the proposed method employs a learning-based approach to lessen the semantic gap problem and to improve the understanding of the contents of query images to retrieve the most relevant images. The presented descriptor provides remarkable results by achieving the average retrieval precision (ARP) of 66%, 92%, 83%, average retrieval recall (ARR) of 66%, 92%, 83%, average retrieval specificity (ARS) of 99%, 99%, 76%, and average retrieval accuracy (ARA) of 98%, 99%, 85% on the AT&T, MIT Vistex, and Brodatz Texture image repositories, respectively. Our experiments reveal that the proposed DMLHP descriptor achieves far better performance, i.e., 95% on AT&T, 92% on BT, and 99% on MIT Vistex, when used with a learning-based approach over a non-learning-based approach (similarity measure). Experimental results show that the proposed texture descriptor outperforms state-of-the-art descriptors such as LNIP, LTriDP, LNDP, LDGP, LEPSEG, and CSLBP for CBIR.

Content-based image retrieval: A review of recent trends

With the availability of internet technology and the low-cost of digital image sensor, enormous amount of image databases have been created in different kind of applications. These image databases increase the demand to develop efficient image retrieval search methods that meet user requirements. Great attention and efforts have been devoted to improve content-based image retrieval method with a particular focus on reducing the semantic gap between low-level features and human visual perceptions. Due to the increasing research in this field, this paper surveys, analyses and compares the current state-of-the-art methodologies over the last six years in the CBIR field. This paper also provides an overview of CBIR framework, recent low-level feature extraction methods, machine learning algorithms, similarity measures, and a performance evaluation to inspire further research efforts.

A Comparative Evaluation of Feature Extraction and Similarity Measurement Methods for Content-based Image Retrieval

A Comparative Evaluation of Feature Extraction and Similarity Measurement Methods for Content-based Image Retrieval

Detailed wrinkle generation of virtual garments from a single image

The presence of proper wrinkles is important while modeling realistic virtual garments. Unlike previously used full 3D information methods, our approach achieves detailed garment generation from a single image. First, we retrieve a garment image similar to the initial virtual garment based on content-based image retrieval (CBIR) method. Then, we preprocess the image with a combination of human body reshaping, image segmentation and shape recovery, to obtain the 3D wrinkle details. Finally, the garment height are synthesized into the virtual garment. For better suit the posture of the human body, excess garment energy are released to remove the unmatched wrinkles. We apply our method to various styles of virtual garments, and it enable virtual characters in general pose to be dressed in these garments and complete wrinkle generation. Compared with existing garment modeling methods, the experimental results show that the proposed method could quickly capture the realistic wrinkles of virtual garments with less manual operation and achieve more realistic wrinkles for virtual garments.

Eagle-Eyed Multitask CNNs for Aerial Image Retrieval and Scene Classification

In recent years, convolutional neural networks (CNNs) have become the predominant method for content-based aerial image retrieval (CBAIR) and aerial scene classification (ASC) due to their overwhelming performance advantages. However, existing CNN-based models have the following shortcomings: first, they do not deal with large intraclass variations, thereby overlooking the possibility of fine-grained retrieval and classification; second, all similarity learning methods for CBAIR consider similarity between two images as a constant, neglecting the fact that image similarity is uncertain in nature; third, similarity learning is separated from ASC, ignoring the advantages of joint optimization. To address these issues, we propose a novel metric learning method called center-metric learning, and couple it with a new kind of loss called positive-negative center loss, which, with the help of several “experts,” enables CNNs to cope successfully with within-class variations. Besides, we propose similarity distribution learning, making the first attempt to embed uncertainty regarding similarity into the training process. The resulting fine-grained similarity predictions can further strengthen CNNs’ fine discrimination ability. Furthermore, three tasks, that is, center-metric learning, similarity distribution learning, and ASC, are incorporated into one CNN, benefitting from one another and leading to a better generalization capability. Just like an eagle, our model is able to discriminate subtle differences among aerial images, hence the name “eagle-eyed multitask CNN.” We carry out extensive experiments over four publicly available aerial image sets and achieve a performance better than all existing methods.

CONTENT-BASED FEATURE FUSION REPRESENTATION FOR MARINE INVERTEBRATES

Marine species representation and retrieval is crucial for its studies and conservation. The images of these animals are usually captured underwater with complex background, at different angle, position, and size, which makes it very hard to provide a good representation with the current methods. Most of the current methods only support content-based representation for marine life images with clear background (taken in laboratory or in environments which have been set up), containing just one animal in an image, or the animal is positioned nicely at the centre of the image. Responding to these important needs, a multi-feature method for Content-based Image Retrieval (CBIR) that employs colour, shape, and texture information of marine life images is proposed. The colour feature vectors are obtained by extracting first and second order of Colour Moments. Shape information is constructed through the implementation of Discrete Wavelet transform up to four sub-bands and the extraction of Canny edge feature. Texture features are obtained with the Zernike Moments (ZM) of order four and the extraction of few Grey Level Co-occurrence Matrix properties. We conducted two experiments to determine the best order of ZM as well as to measure the retrieval performance of the proposed descriptor. Retrieval results based on marine invertebrate and Fish4Knowledge datasets clearly shown that the proposed method has effectively obtained the best precision value at 11 standard recall levels (72.42%) and MAP value (67.7%). The proposed method is further measured based on the statistical two-tailed paired t-test and has revealed a significant improvement in retrieval effectiveness.

BoVW model based on adaptive local and global visual words modeling and log-based relevance feedback for semantic retrieval of the images

The core of a content-based image retrieval (CBIR) system is based on an effective understanding of the visual contents of images due to which a CBIR system can be termed as accurate. One of the most prominent issues which affect the performance of a CBIR system is the semantic gap. It is a variance that exists between low-level patterns of an image and high-level abstractions as perceived by humans. A robust image visual representation and relevance feedback (RF) can bridge this gap by extracting distinctive local and global features from the image and by incorporating valuable information stored as feedback. To handle this issue, this article presents a novel adaptive complementary visual word integration method for a robust representation of the salient objects of the image using local and global features based on the bag-of-visual-words (BoVW) model. To analyze the performance of the proposed method, three integration methods based on the BoVW model are proposed in this article: (a) integration of complementary features before clustering (called as non-adaptive complementary feature integration), (b) integration of non-adaptive complementary features after clustering (called as a non-adaptive complementary visual words integration), and (c) integration of adaptive complementary feature weighting after clustering based on self-paced learning (called as a proposed method based on adaptive complementary visual words integration). The performance of the proposed method is further enhanced by incorporating a log-based RF (LRF) method in the proposed model. The qualitative and quantitative analysis of the proposed method is carried on four image datasets, which show that the proposed adaptive complementary visual words integration method outperforms as compared with the non-adaptive complementary feature integration, non-adaptive complementary visual words integration, and state-of-the-art CBIR methods in terms of performance evaluation metrics.

Content Based Image Retrieval (CBIR) by Statistical Methods

An image retrieval system is a computer system for browsing, looking and recovering pictures from a huge database of advanced pictures. The objective of Content-Based Image Retrieval (CBIR) methods is essentially to extract, from large (image) databases, a specified number of images similar in visual and semantic content to a so-called query image. The researchers were developing a new mechanism to retrieval systems which is mainly based on two procedures. The first procedure relies on extract the statistical feature of both original, traditional image by using the histogram and statistical characteristics (mean, standard deviation). The second procedure relies on the T- test to measure the independence between more than images, (coefficient of correlate, T- test, Level of significance, find the decision), and, through experimental test, it was found that this proposed method of retrieval technique is powerful than the classical retrieval System.

A novel image retrieval method based on multi-features fusion

Image retrieval is an important research topic in pattern recognition and computer vision. We propose a novel content-based image retrieval method. At the image description stage, our method first modifies the traditional micro-structure descriptor (MSD) to capture the direct relationship between the shape and texture features and that between the color and texture features. Our method then extracts the uniform local binary patterns (LBP) histogram of the image to capture the color difference information. At the image comparison stage, our method first compares the descriptors of the images to compute their similarities. The similarity between each pair of images is then updated by also considering the similarities to comparable images within the dataset. Accordingly, our method obtains the final similarities of the images. Experimental results demonstrate the effectiveness of our method for image retrieval.

An Efficient Content Based Image Retrieval using an Optimized Neural Network for Medical Application

Content Based Image Retrieval (CBIR) is a popular method to search and retrieve the similar images. For medical applications, it plays an important role to find the diseasessuch as breast cancer in human body. Many existing methods were presented for improving the performance of CBIR method. Nevertheless, retrieval time and accuracy of CBIR are further to be improved. To solve this issue, an optimal classifier is to be used in CBIR. In this paper, Artificial Neural Network based on Particle Swarm Optimization based (PSO-ANN) is presented as an optimized classifier. Also, the features of images such as shape, texture, mean and standard deviation are extracted. To increase the speed of the classification, these extracted features are to be clustered using k-means clustering algorithm. From the clustered features, similar images of query image are retrieved using the proposed PSO-ANN classifier. Simulation results prove that performance of this proposed CBIR outperforms than that of existing methods in terms of accuracy and CBIR time.

Retrieval of colour and texture images using local directional peak valley binary pattern

Many content-based image retrieval (CBIR) methods are being developed to store more and more information about images in shorter feature vectors and to improve image retrieval rate. In the proposed method, two-step approach to CBIR has been developed. The first step generates an image mask from local binary pattern (LBP). This LBP mask is then utilized to draw comparison between the centre pixel and the eight surrounding pixels. The second step involves drawing the peak and valley patterns of local directional binary pattern for each image which is then combined with the colour histogram to retrieve similar images. Existing methods suffer from lower average image retrieval accuracy even with larger feature vectors. The proposed method overcomes such problems through shorter feature vectors that can store more information about the image. As illustrated through experimental results, the proposed method produces promising results with shorter feature vector of length 56 and improved image retrieval rate of about 5–10%. Our method outperforms similar techniques when tested with public data sets.