Hybrid-Indexing Multi-type Features for Large-Scale Image Search

Different types of search engines are used to search image and text contents. Two types of image search methods are available in the Internet. They are query keyword based model and content based image retrieval models. Text query strings are used in the textual image retrieval model. Content based image retrieval (CBIR) model uses the visual information of the images. Image search methods use the text annotation and image visual features. Google image search and Bing image search engines are used to fetch images from the web. Image query string is used to search image on Internet. One click query image selection method is used to submit user intention for image retrieval. Content based image re-ranking is performed with visual and textual similarity metrics. Adaptive Weight Schema is used for the similarity analysis. Feature weight learning algorithm is applied to estimate feature weights for the images and its category. Query is expanded with keyword and visual information. Rank boost framework algorithm is enhanced to rank images with photographic quality. Content similarity and visual quality factors are used for the re-ranking process. In this paper, we propose an image indexing and retrieval using speech annotations based on a predefined structured syntax. To improve the retrieval effectively, N-best lists for index generation is used .so, a query expansion technique is explored to enhance the query terms. All this process is automatic, without extra effort from the user. This is critically important in web-based image search engine for any commercial, where the user interface has to be extremely simple.

Content-based image retrieval (CBIR) is one of the most important applications of computer vision. In recent years, there have been many important advances in the development of CBIR systems, especially Convolutional Neural Networks (CNNs) and other deep-learning techniques. On the other hand, current CNN-based CBIR systems suffer from high computational complexity of CNNs. This problem becomes more severe as mobile applications become more and more popular. The current practice is to deploy the entire CBIR systems on the server side while the client side only serves as an image provider. This architecture can increase the computational burden on the server side, which needs to process thousands of requests per second. Moreover, sending images have the potential of personal information leakage. As the need of mobile search expands, concerns about privacy are growing. In this article, we propose a fast image search framework, named DeepSearch, which makes complex image search based on CNNs feasible on mobile phones. To implement the huge computation of CNN models, we present a tensor Block Term Decomposition (BTD) approach as well as a nonlinear response reconstruction method to accelerate the CNNs involving in object detection and feature extraction. The extensive experiments on the ImageNet dataset and Alibaba Large-scale Image Search Challenge dataset show that the proposed accelerating approach BTD can significantly speed up the CNN models and further makes CNN-based image search practical on common smart phones.

A content-based image retrieval (CBIR) system is proposed for the retrieval of T1-weighted contrast-enhanced MRI (CE-MRI) images of brain tumors. In this CBIR system, spatial information in the bag-of-visual-words model and domain knowledge on the brain tumor images are considered for the representation of brain tumor images. A similarity metric is learned through a distance metric learning algorithm to reduce the gap between the visual features and the semantic concepts in an image. The learned similarity metric is then used to measure the similarity between two images and then retrieve the most similar images in the dataset when a query image is submitted to the CBIR system. The retrieval performance of the proposed method is evaluated on a brain CE-MRI dataset with three types of brain tumors (i.e., meningioma, glioma, and pituitary tumor). The experimental results demonstrate that the mean average precision values of the proposed method range from 90.4% to 91.5% for different views (transverse, coronal, and sagittal) with an average value of 91.0%.

Challenges faced by prevailing text metadata paradigms for online image search have inspired overwhelming research in Content Based Image Retrieval (CBIR). A multitude of approaches have been introduced within the literature, yet relatively few image search engines have been made publicly available on the web. Aside from challenges facing the user, such as describing a visual query using keywords, or finding an appropriate example image to initiate a visual search, all systems must inevitably grapple with the sensory and semantic gaps [Smeulders et al. 2000], which essentially represent a loss of information in the abstraction process. In this work, we challenge commonly suggested approaches to improving CBIR and illustrate drawbacks of relying on textual data, as well as visual data, in general CBIR search. We provide cogent examples using online visual search engines Behold™, Tiltomo Beta, Pixilimar, and Riya™ Beta. These examples demonstrate the effect of semantic ambiguities in natural language, which extend to search terms and text tags.

In this letter, we introduce a new spatio-temporal feature, namely optical flow energy image (OFEI), for video-based person re-identification. OFEI aims to exploit spatio-temporally stable regions across frames, which can capture discriminative cues such as human body parts and carry-on stuffs. Furthermore, we propose a novel matching method, denoted by multi-view relevance metric learning with list-wise constraints (mvRMLLC), to integrate the spatio-temporal (i.e., OFEI) and appearance features. Unlike previous works, mvRMLLC assumes that multiple features are generated from different views with distinct data distributions, while their similarities should be globally consistent. Multiple similarity metrics are then learned and fused by maximizing their global consistency and simultaneously allowing local discrepancies. Extensive experiments on two benchmarks demonstrate that OFEI outperforms the state-of-the-art spatio-temporal features, and mvRMLLC could further enhance the overall performance significantly.

Image annotation and retrieval has been a popular research topic for decades. Based on published journals from 2012 until 2015, a lot of research and studies has been focused on Content Based Image Retrieval (CBIR). In most cases, CBIR systems that use an image as the input query always face a problem called semantic gap due to the use of low-level features for similarity matching. The semantic gap will consequently reduce the performance of the CBIR systems. To overcome this problem, a new class of CBIR known as Annotation Based Image Retrieval (ABIR) has been developed. The ABIR systems, based on the annotation process of the images, employ bag of words for query. However it is found that employing pure bag of word only is not adequate to solve semantic problem. In this study, an attempt to use a Gaussian Mixture Model (GMM) based approach and spatial related information of the annotated objects has been performed in order to improve the performance of the ABIR systems. From the retrieval experiments, it is found that ABIR could achieve average performance up to 88% which is two times better than the CBIR systems in reducing the semantic problem.

Content-Based Image Retrieval (CBIR) allows to automatically extracting target images according to objective visual contents of the image itself. Representation of visual features and similarity match are important issues in CBIR. Color, texture and shape information have been the primitive image descriptors in content-based image retrieval systems. This paper presents a fast and efficient image indexing and search system based on color and texture features. The color features are represented by combines 2-D histogram and statistical moments and texture features are represented by combines the direction measure and a gray level co-occurrence matrix (GLCM). The detailed experimental analysis is carried out using precision and recall ondataset Wang. The time analysis is also performed to compare processing speeds of the proposed method with the existing similar best. The experimental results demonstrated that proposed method achieved a better image recognition, and the accuracy of classification based on this method has been significantly improved. The performance is measured in terms of recall and precision; also the obtained performances are compared with several state-of-the-art algorithms and showed that our algorithm is simple, fast, and efficient in terms of results and memory. Keywords: Co-occurrence Matrix, Direction Measure, 2-D Histogram, Statistical Moments, CBIR, GLCM

With the evolution of the Internet, and the availability of image capturing devices such as advanced cameras, picture scanners, the size of advanced image accumulation is expanding quickly. Efficient image searching, browsing and retrieval devices are required by clients from different domains, including remote sensing, fashion, wrongdoing prevention, publishing, medicine, architecture, etc. Here we are extracting color mean features and color standard deviation feature with the proposed method consists of HMMD (Hue Min Max Difference) color plane. It is proved in research work that HMMD along with color mean features and color standard deviation feature is tend to reduced the size of feature vectors, storage space and gives high performance than, RGB-color mean feature. Further, HMMD color space model will be used to improve the feature extraction and improve the precision. At the end, results are presented to show the efficiency of the proposed method. Keywords: HMMD, CBIR, Feature Extraction, Precision, Recall.

<div class="page" title="Page 1"><div class="layoutArea"><div class="column"><div class="page" title="Page 1"><div class="layoutArea"><div class="column"><p><span>This work aims to improve the speed of search by creating an indexing structure in CBIR system. We utilised an inverted index structure that usually used in text retrieval with a modification. The modified inverted index is built based on histogram data that generated using Multi Texton Histogram (MTH) and Multi Texton Co-Occurrence Descriptor (MTCD) from 10,000 images of Corel dataset. When building the inverted index, we normalised value of each feature into a real number and considered pairs of feature and value that owned by a particular number of images. Based on our investigation, on MTCD histogram of 5,000 data test, we found that by considering histogram variable values which owned by maximum 12% of images, the number of comparison for each query can be reduced by 67.47% in a rate, the precision is 82.2%, and the rate of access to disk is 32.83%. Furthermore, we named our approach as Histogram Inverted Index (HII). </span></p></div></div></div></div></div></div>

With growing number of stored image data, image search and image similarity problem become more and more important. The answer can be solved by Content-Based Image Retrieval systems. This paper deals with an image search using similarity measures based on circular sectors method. The method is inspired by human eye functionality. The main contribution of the paper is a modified method that increases accuracy for about 8% in comparison with original approach. Here proposed method has used HSB colour model and median function for feature extraction. The original approach uses RGB colour model with mean function. Implemented method was validated on 10 image categories where overall average precision was 67%.

The Internet provides an extensive quantity of data in the form of text and images. Search Engines like Google and Bing are intended to retrieve the most relevant answers for our textual queries. In search engines, queries are generally matched between text-to-text or text-to-image which excludes the entire domain of image-to-image matching. Searching for images based on text poses the problem of retrieving results primarily based on image description and tagging. The ideal solution to tackle the flaws of text-based image queries and achieve image-to-image matching is obtained by extracting features of the image and using these features to retrieve similar images. Extracting information from visual data and similarity matching fall under the domain of Content Based Image Retrieval (CBIR). CBIR analyzes image information using low level representation including color, shape, texture, and spatial representation of objects to set up feature vectors for image indexing. Deep Learning techniques like Convolutional Neural Networks (CNN) serve the purpose of fulfilling the feature extraction task. Retrieval methods are achieved based on the low-level features of an image and mathematical similarity metrics aid in determining the relevant images satisfying the query for similarity. However, low level features do not capture the idea behind the image and hence limiting the images to a specific domain ensures that accuracy and similarity are as expected. The proposed project is specific to the domain of garments in the fashion industry. The proposed project conducted a study on the use of different pre-trained CNN models for the purpose of image feature extraction and attempted to fine-tune the selected ResNet50 model for the custom dataset. The feature similarity matching was performed by selecting a similarity metric famously used by music streaming giant Spotify's algorithm, Annoy Indexing, optimized for time and accuracy.

Technological advances in digital imaging, broadband networking, and data storage have motivated people to communicate and express by sharing images, video, and other forms of media online [1]. Although the problems of acquiring, storing and transmitting the images are well addressed, capabilities to manipulate, index, sort, filter, summarize, or search through image database lack maturity. Modern image search engines [1–3, 30] retrieve the images based on their visual contents, commonly referred to as Content Based Image Retrieval (CBIR) systems. CBIR systems have found applications in various fields like fabric and fashion design, interior design as panoramic views [5, 20, 38–41], art galleries [22], museums, architecture/ engineering design [22], weather forecast, geographical information systems, remote sensing and management of earth resources [40, 41], scientific database management, medical imaging, trademark and copyright database management, the military, law enforcement and criminal investigations [41], intellectual property, picture archiving and communication systems, retailing and image search on the Internet (very general image content).

Image search is a challenging process in the field of Content Based Image Retrieval (CBIR). Image search-by-example, search-by-keyword and search-by-sketch methods seldom provide user interface that allows user to accurately formulate their search intent easily. To overcome such issue, a novel image search interface-Semantic Visual Query Builder (SeVQer) is proposed as a non-verbal interface which allows user to drag and drop from the image data provided to formulate user query. The drag and drop mechanism minimizes the difficulty of verbalizing query image into keywords or sketching a correct drawing of the query image. SeVQer was implemented and compared with 3 image search methods (search-by-example, search-by-keyword and search-by-sketch) in terms of task completion time and user satisfaction using traffic images. SeVQer achieved statistically significant lower task completion time with an average of 28 sec, a promising 50% reduction than search-by-sketch (average of 56 sec). The significance of this work is two-fold: the SeVQer user interface allows user to easily formulate intent specific query, while the novel architecture and methodology reduces the semantic gap in general.

Content-Based Image Retrieval (CBIR) Systems allow the search of images by similarity employing a numeric representation automatically or semi-automatically obtained from them to perform the search. Nevertheless, the query result does not always bring what the user expected. In this sense, CBIR systems face the semantic gap problem. One way of overcoming this problem is by the addition of diversity in query execution, so that the user can ask the system to return the most varied images regarding some similarity criteria. However, applying diversity on large datasets has a prohibitive computational cost and, moreover, the result often differs from the expected with a resulting subset that has images with high dissimilarity to the query image. In this paper we propose an approach to reduce the computational cost of Content-Based Image Retrieval systems regarding similarity and diversity criteria. The proposed approach employs dataset fractals analysis to estimate a suitable radius for a database subset to perform a similarity query regarding diversity. It selects closer images to the query center and applies the diversity factor to the subset, providing not only a better comprehension of the impact of the diversity factor to the query result, but also an improvement in execution time.

We present ElasticHash, a novel approach for high-quality, efficient, and large-scale semantic image similarity search. It is based on a deep hashing model to learn hash codes for fine-grained image similarity search in natural images and a two-stage method for efficiently searching binary hash codes using Elasticsearch (ES). In the first stage, a coarse search based on short hash codes is performed using multi-index hashing and ES terms lookup of neighboring hash codes. In the second stage, the list of results is re-ranked by computing the Hamming distance on long hash codes. We evaluate the retrieval performance of ElasticHash for more than 120,000 query images on about 6.9 million database images of the OpenImages data set. The results show that our approach achieves high-quality retrieval results and low search latencies.