Retrieval Speed Research Articles

Improving Speed and Accuracy of Image Retrieval using Elastic Search and Features Nearest Neighbor Search

A developing interest had shown as late in structure closest neighbor search arrangements inside Elastic search–one of the most well-known full-content web indexes. In this paper, we focus explicitly around Elastic search and Features Nearest Neighbor search (ESFNNS), which accomplishes sensitive speed-ups over the current term coordinate gauge. Features Nearest Neighbor search performs the image retrieval, which integrates the features of color, shape, and texture. This will engage an Elastic search with the capacity of quick data retrieval and accuracy when compared to the FENSHSES method.

Semantic Correlation Based Deep Cross-Modal Hashing For Faster Retrieval

Due to growth of multi-modal data, large amount of data is being generated. Nearest Neighbor (NN) search is used to retrieve information but it suffers when there is high-dimensional data. However Approximate Nearest Neighbor (ANN) is a searching method which is extensively used by the researchers where data is represented in form of binary code using semantic hashing. Such representation reduces the storage cost and retrieval speed. In addition, deep learning has shown good performance in information retrieval which efficiently handle scalability problem. The multi-modal data has different statistical properties so there is a need to have method which finds semantic correlation between them. In this paper, experiment is performed using correlation methods like CCA, KCCA and DCCA on NMIST dataset. NMIST dataset is multi-view dataset and result proves that DCCA outperforms over CCA and KCCA by learning representations with higher correlations. However, due to flexible requirements of users, cross-modal retrieval plays very important role which works across the modalities. Traditional cross-modal hashing techniques are based on the hand-crafted features. So performance is not satisfactory as feature learning and binary code generation is independent process. In addition, traditional cross-modal hashing techniques fail to bridge the heterogeneous gap over various modalities. So many deep-based cross-modal hashing techniques were proposed which improves the performance in comparison with non-deep cross-modal techniques. Inside the paper, we presented a comprehensive survey of hashing techniques which works across the modalities.

The optimization of bibliographic information resource integration of digital library

ABSTRACT The integration of bibliographic information resource of digital library can increase retrieval speed and make sharing easy. With the current method, knowledge chain is used to integrate the information resources of the digital library to realize the integration of its bibliography. Therefore, this paper proposes a method for bibliographic information resource integration based on Service-Oriented Architecture (SOA). With content relevance and attribute correlation, the information resources are related, and by using SOA, the information resource integration framework of digital library bibliography is formed and the information resource retrieval platform is constructed. The experiment proves that this method can improve the information resource utilization efficiency of digital library.

VISE

We present VISE, or Vehicle Image Search Engine, to support the fast search of similar vehicles from low-resolution traffic camera images. VISE can be used to trace and locate vehicles for applications such as police investigations when high-resolution footage is not available. Our system consists of three components: an interactive user-interface for querying and browsing identified vehicles; a scalable search engine for fast similarity search on millions of visual objects; and an image processing pipeline that extracts feature vectors of objects from video frames. We use transfer learning technique to integrate state-of-the-art Convolutional Neural Networks with two different refinement methods to achieve high retrieval accuracy. We also use an efficient high-dimensional nearest neighbor search index to enable fast retrieval speed. In the demo, our system will offer users an interactive experience exploring a large database of traffic camera images that is growing in real time at 200K frames per day.

Anomia in people with rapidly evolving severe relapsing-remitting multiple sclerosis: both word retrieval inaccuracy and delay are common symptoms

ABSTRACTBackground: Multiple Sclerosis (MS) is a neurodegenerative disease that produces plaques throughout the central nervous system. MS can present in four different clinical courses. Of these, Relapsing-Remitting MS (RRMS) is the main clinical course, especially at early stages of the disease. Rapidly evolving severe (RES) RRMS is a form of RRMS in which an individual has two or more disabling relapses in one year and evidence of increasing lesions on two consecutive MRI scans. MS affects the cortical and subcortical pathways of the brain leading to impairment in both physical and cognitive skills. Speech, language and communication deficits more broadly, have been acknowledged in the MS literature, but relatively little research has focused on these symptoms.Aims: To examine communication deficits in people with (RES) RRMS, with specific focus on anomic symptoms – difficulties in word retrieval, examining measures of both accuracy and latency (time intervals for accurate word retrieval).Methods & Procedures: A communication screening assessment was conducted with 100 participants with (RES) RRMS. This screening assessment consisted of the ACE-R cognitive screen, a bespoke picture naming task, reading words aloud from the National Adult Reading Test (NART) and the Pyramids and Palm Trees Test. The picture naming task obtained timed naming responses for sixty pictures of objects from the International Picture Naming Project (IPNP). Results for participants with MS (PWMS) were compared to matched neurotypical control participants (n = 40) and normative test data.Outcomes & Results: The group mean performance for PWMS was below the lower end of the neuro-typical control range for the cognitive screen and picture naming tasks. The reading aloud and semantic association mean scores were within the neuro-typical range but towards the lower end of this range. Anomic symptoms for PWMS presented as both lapses in word retrieval and reduced speed of word retrieval. Word retrieval latency was on average 26% slower for PWMS. Within the anomic symptoms, there were instances of inaccuracy (42% of participants) as well as slow naming latency (31% of participants) in retrieving words. There was evidence of mild dysarthria for 33% of participants. Regression analyses suggested the anomic symptoms were most strongly associated with semantic processing deficits.Conclusions: Anomic symptoms are common in (RES) RRMS, and present as inaccuracy as well as slow word retrieval latency. The prevalence and cognitive nature of anomic symptoms require further research across the range of presentations of MS.

Direct and generative autobiographical memory retrieval: How different are they?

Theories of autobiographical memory have emphasised effortful generative retrieval, but recent research indicates that subjectively effortless direct retrieval is common. We compared the processes of direct and generative retrieval. Sixty-five participants retrieved 24 autobiographical memories across three cue types: concrete, emotional, and personal. We recorded retrieval latency, and participants judged direct versus generative retrieval and rated memory specificity, vividness, significance, rehearsal, and emotionality. Overall, direct retrieval was common, especially for personal cues. Directly retrieved memories were recalled faster, were less likely to be specific, and were rated more significant, rehearsed, and emotional than generatively retrieved memories. The speed of both direct and generative retrieval varied similarly according to cue type, suggesting they did not involve fundamentally different cognitive processes. These findings challenge theories that assume direct retrieval bypasses constructive processes. Instead we suggest that both direct and generative retrieval involve construction that is similarly affected by cue concreteness and relevance.

Efficient retrieval algorithm for multimedia image information

The research on the retrieval of multimedia image data information is of great significance for increasing the retrieval rate of multimedia image information. Due to the certain similar characteristics of massive multimedia image information, the picture information features are confused. The traditional image retrieval method mainly uses the image information feature to classify and retrieve. When the picture information is disordered, it is impossible to classify the mass multimedia image information features, resulting in slow retrieval speed and low accuracy. A new high-efficiency retrieval algorithm for massive multimedia image information is proposed and optimized. Based on the theory of granular computing, an image region similarity measurement method for content retrieval is proposed. The image feature information table is transformed into an ordered matrix form. By studying the ordered matrix, the concept of image feature granules and granule granules is introduced, the importance of image features is analyzed from different granularity levels, and the order relationship between regions in the image feature information table is maintained, and the weight of the theoretical image feature is calculated based on the granularity for implementing the image region similarity measurement method. The example shows that the similarity measure method can measure the degree of similarity between image regions objectively and effectively, and provides a new idea and method for the research of granular computing theory in multimedia image content retrieval.

Cuckoo Search Algorithm Based Feature Selection in Image Retrieval System

Efficiency an d retrieval time are very important issues in any content-based image retrieval system. In this study, an efficient image retrieval system was introduced depending on several features extracted from the database images, namely color moment (Mean, Standard Deviation), GLCM, and DWT( only LL-sub band). To increase the retrieval speed, Cuckoo search algorithm was used to select the important positions that contain full power features from the (LL-sub band). On using the Cuckoo search algorithm, only (50) important positions were chosen out of the total (24576) positions within (LL- sub band). These positions were stored for later use when entering a query image. Thus, the time taken to retrieve images was greatly reduced and this process also increased the efficiency of the system due to the fact that the selected positions gave the lowest distance measures between the query images and the similar images when evaluated using Manhattan distance measure. Two effectual performance measures (precision & recall) were used to calculate the accuracy of the system. The findings proved the system efficiency when compared to other previous works. Keywords: CBIR, Color Moment, GLCM, DWT, Cuckoo Search algorithm, Manhattan measure DOI : 10.7176/JEP/10-15-08 Publication date :May 31 st 2019

A dimensional reduction guiding deep learning architecture for 3D shape retrieval

The state-of-the-art shape descriptors are usually lengthy for gaining high retrieval precision. With the rapidly growing number of 3-dimensional models, the retrieval speed becomes a prominent problem in shape retrieval. In this paper, by exploiting the capabilities of the dimensionality reduction methods and the deep convolutional residual network (ResNet), we developed a method for extracting short shape descriptors (with just 2 real numbers, named 2-descriptors) from lengthy descriptors, while keeping or even improving the retrieval precision of the original lengthy descriptors. Specifically, an attraction and repulsion model is devised to strengthen the direct dimensionality reduction results. In this way, the dimensionality reduction results turn into desirable labels for the ResNet. Moreover, to extract the 2-descriptors using ResNet, we transformed it as a classification problem. For this purpose, the range of each component of the dimensionality reduction results (including two components in total) is uniformly divided into n intervals corresponding to n classes. Experiments on 3D shape retrieval show that our method not only accelerates the retrieval speed greatly but also improves the retrieval precisions of the original shape descriptors.

Color image storage and retrieval using quantum mechanics

In this paper, two algorithms for storing and retrieving a color image using quantum mechanics are proposed. The first algorithm encodes a pixel’s color information with an angle. In this case, it has some advantages in retrieval speed, required qubits and quantum measurements. In the second algorithm, a pixel’s color is divided into three channels: R, G and B, and each channel is encoded with an angle. In this case, it has an advantage in retrieval accuracy. By example analysis, the proposed algorithms are compared with the other algorithms in some aspects, e.g., the total number of qubits, the total number of measurements and the accuracy of retrieval. It can be found that the first algorithm has the advantage in the speed of retrieval, the total number of qubits and the total number of measurements, and the second algorithm has the advantage in the accuracy of retrieval.

Content-based image retrieval by combining convolutional neural networks and sparse representation

As stored data and images on memory disks increase, image retrieval has a necessary task on image processing. Although lots of researches have been reported for this task so far, semantic gap between low level features of images and human concept is still an important challenge on content-based image retrieval. For this task, a robust method is proposed by a combination of convolutional neural network and sparse representation, in which deep features are extracted by using CNN and sparse representation to increase retrieval speed and accuracy. The proposed method has been tested on three common databases on image retrieval, named Corel, ALOI and MPEG7. By computing metrics such as P(0.5), P(1) and ANMRR, experimental results show that the proposed method has achieved higher accuracy and better speed compared to state-of-the-art methods.

Diffusion approximations for load balancing mechanisms in cloud storage systems

AbstractIn large storage systems, files are often coded across several servers to improve reliability and retrieval speed. We study load balancing under the batch sampling routeing scheme for a network of n servers storing a set of files using the maximum distance separable (MDS) code (cf. Li (2016)). Specifically, each file is stored in equally sized pieces across L servers such that any k pieces can reconstruct the original file. When a request for a file is received, the dispatcher routes the job into the k-shortest queues among the L for which the corresponding server contains a piece of the file being requested. We establish a law of large numbers and a central limit theorem as the system becomes large (i.e. n → ∞), for the setting where all interarrival and service times are exponentially distributed. For the central limit theorem, the limit process take values in ℓ2, the space of square summable sequences. Due to the large size of such systems, a direct analysis of the n-server system is frequently intractable. The law of large numbers and diffusion approximations established in this work provide practical tools with which to perform such analysis. The power-of-d routeing scheme, also known as the supermarket model, is a special case of the model considered here.

A Genome-Wide Detection of Copy Number Variations Using SNP Genotyping Arrays in Braque Français Type Pyrénées Dogs.

Simple SummaryCopy number variations (CNVs) are important sources of variation in mammalian species. In this study, we used a single nucleotide polymorphisms (SNP) array to detect CNVs in Braque Français, type Pyrénées dogs (BRA). Results overlapped moderately in comparison with previous studies on CNVs in dogs, leading to the identification of 16 novel CNVRs. Several genes were annotated in the CNV regions (CNVRs) detected, some of which related to muscle structure development. This breed is known to be excellent upland game birds dogs. The selection for such hunting behavior could have driven the presence of these genes into the CNVRs. Copy number variations may be of interest to study associations between genomic and phenotypic variation.Copy number variants (CNVs) are an important source of genetic variation complementary to single nucleotide polymorphisms (SNPs). Only few studies have been conducted in dogs on CNVs derived from high-density SNP array data, and many canine breeds still remain uncharacterized, e.g., the Braque Français, type Pyrénées breed (BRA). Therefore, in an effort to more comprehensively investigate the canine genome for CNVs, we used a high-density SNP array (170 K) to discover CNVs in BRA. The CNV regions (CNVRs) were identified through the merging of two different CNVRs datasets, obtained separately from SNP data using the PennCNV and SVS software. A total of 45 stringent CNVRs, ranging from 3.5 kb to 458,716 kb in length were detected in 26 dog samples. Results overlapped moderately in comparison with previous studies on CNVs in dogs, leading to the identification of 16 novel CNVRs. A total of 159 genes were annotated in the CNVRs detected with stringent quality criteria in particular high classification stringency and false discovery rate correction. The gene ontology enrichment analysis provided information on biological processes and cellular components related to muscle structure development and muscle cell differentiation. Considering that BRA is a breed used for speed in hunting and retrieval, for the ability to find feathered game, and for pointing, we can hypothesize that selection for such hunting behavior could have driven, at least in part, the presence of these genes into the CNVRs.

Predictors of lexical retrieval in Hindi–English bilingual speakers

AbstractWhen bilinguals name pictures while in ‘monolingual mode’, we expect that under conditions of language-constraint and no cognate facilitation, factors influencing lexical retrieval in monolinguals ought to exert similar effects on bilinguals. To this end, we carried out a L1-only naming task on early Hindi–English bilinguals. Results of linear mixed effects analysis reveal AoA, Familiarity, Image Agreement and Codability (availability of alternate names) to be the most significant predictors of lexical retrieval speed for early bilinguals, confirming our expectations. However, we report, for the first time, a by-subject variation in Codability for bilinguals. Implications of the results are discussed in the context of current theories of bilingual lexical access and competition. In preparation for this study, Hindi norms from bilinguals for items in the Snodgrass and Vanderwart set have been established, which will be of use for stimuli selection in experimental studies involving bilinguals.

Handling Massive N -Gram Datasets Efficiently

Two fundamental problems concern the handling of large n -gram language models: indexing , that is, compressing the n -grams and associated satellite values without compromising their retrieval speed, and estimation , that is, computing the probability distribution of the n -grams extracted from a large textual source. Performing these two tasks efficiently is vital for several applications in the fields of Information Retrieval, Natural Language Processing, and Machine Learning, such as auto-completion in search engines and machine translation. Regarding the problem of indexing, we describe compressed, exact, and lossless data structures that simultaneously achieve high space reductions and no time degradation with respect to the state-of-the-art solutions and related software packages. In particular, we present a compressed trie data structure in which each word of an n -gram following a context of fixed length k , that is, its preceding k words, is encoded as an integer whose value is proportional to the number of words that follow such context. Since the number of words following a given context is typically very small in natural languages, we lower the space of representation to compression levels that were never achieved before, allowing the indexing of billions of strings. Despite the significant savings in space, our technique introduces a negligible penalty at query time. Specifically, the most space-efficient competitors in the literature, which are both quantized and lossy, do not take less than our trie data structure and are up to 5 times slower. Conversely, our trie is as fast as the fastest competitor but also retains an advantage of up to 65% in absolute space. Regarding the problem of estimation, we present a novel algorithm for estimating modified Kneser-Ney language models that have emerged as the de-facto choice for language modeling in both academia and industry thanks to their relatively low perplexity performance. Estimating such models from large textual sources poses the challenge of devising algorithms that make a parsimonious use of the disk. The state-of-the-art algorithm uses three sorting steps in external memory: we show an improved construction that requires only one sorting step by exploiting the properties of the extracted n -gram strings. With an extensive experimental analysis performed on billions of n -grams, we show an average improvement of 4.5 times on the total runtime of the previous approach.

Reading and math tests differentially predict number transcoding and number fact speed longitudinally: A random intercept cross-lagged panel approach.

Children’s early math abilities have been claimed to depend differentially on various cognitive competencies (e.g., core number skills, working memory, and general math and reading abilities). Clarifying the relative importance of these different cognitive markers in predicting key early math skills would provide a conceptual framework for understanding development of math competence. To this end, we assessed 267 six-year-olds’ core number (dot enumeration, number comparison) abilities, visuospatial working memory, and standardized math and reading test performance, as well as their number fact retrieval speed and ability to transcode number strings (e.g., “4,073”) at 6, 7, and 8 years. To minimize interpretive difficulties associated with previous analyses, we used a random intercept cross-lagged panel model to characterize the reciprocal relationship between number transcoding ability and number fact speed over time. We tested the hypotheses that general math scores would predict individual differences in number fact speed, while general reading scores would predict individual differences in number transcoding accuracy. Findings showed that both standardized tests and core number measures differentially predict math skills in the early school years. Dot enumeration and general math ability predicted individual differences in number fact speed, while general reading and general math predicted individual differences the ability to transcode number strings over time. We suggest combining standardized assessments of math and reading, together with measures of core numerical ability, at school entry offers important information about the factors associated with key early math skills. (PsycINFO Database Record (c) 2019 APA, all rights reserved)

Equivalent Continuous Formulation of General Hashing Problem.

Hashing-based approximate nearest neighbors search has attracted broad research interest, due to its low computational cost and fast retrieval speed. The hashing technique maps the data points into binary codes and, meanwhile, preserves the similarity in the original space. Generally, we need to solve a discrete optimization problem to learn the binary codes and hash functions, which is NP-hard. In the literature, most hashing methods choose to solve a relaxed problem by discarding the discrete constraints. However, such a relaxation scheme will cause large quantization error, which makes the learned binary codes less effective. In this paper, we present an equivalent continuous formulation of the discrete hashing problem. Specifically, we show that the discrete hashing problem can be transformed into a continuous optimization problem without any relaxations, while the transformed continuous optimization problem has the same optimal solutions and the same optimal value as the original discrete hashing problem. After transformation, the continuous optimization methods can be applied. We devise the algorithms based on the idea of DC (difference of convex functions) programming to solve this problem. The proposed continuous hashing scheme can be easily applied to the existing hashing models, including both supervised and unsupervised hashing. We evaluate the proposed method on several benchmarks and the results show the superiority of the proposed method compared with the state-of-the-art hashing methods.

Research on application of multimedia image processing technology based on wavelet transform

With the development of information technology, multimedia has become a common information storage technology. The original information query technology has been difficult to adapt to the development of this new technology, so in order to be able to retrieve useful information in a large amount of multimedia information which has become a hot topic in the development of search technology, this paper takes the image in the multimedia information storage technology as the research object, uses the wavelet transform to divide the picture into the advantages of the low-frequency and high-frequency characteristics, and establishes the multimedia processing technology model based on the wavelet transform. The simulation results of face, vehicle, building, and landscape images show that different wavelet basis functions and different layers of images are decomposed, and the retrieval results and retrieval speed of images are different, When taking four layers of wavelet decomposition, the cubic b-spline wavelet as the wavelet basis function makes the classification result optimal, and the accuracy rate is 89.08%.

Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features

Color, texture, and shape are the common features used for the retrieval systems. However, many medical images have a spot of color information. Therefore, the discriminative texture and shape features should be extracted to obtain a satisfied retrieval result. In order to increase the credibility of the retrieval process, many features can be combined to be used for medical image retrieval. Meanwhile, more features require more processing time, which will decrease the retrieval speed. In this paper, wavelet decomposition is adopted to generate different resolution images. Bag-of-feature, texture, and LBP feature are extracted from three different-level wavelet images. Finally, the similarity measure function is obtained by fusing these three types of features. Experimental results show that the proposed multi-feature fusion method can achieve a higher retrieval accuracy with an acceptable retrieval time.

Research on Key Technologies of Massive Videos Management Under the Background of Cloud Platform

With the rapid development of mobile internet and smart city, video surveillance is popular in areas such as transportation, schools, homes, and shopping malls. It is important subject to manage the massive videos quickly and accurately. This paper tries to use Hadoop cloud platform for massive video data storage, transcoding and retrieval. The key technologies of cloud computing and Hadoop are introduced firstly in the paper. Then, we analyze the functions of video management platform, such as user management, videos storage, videos transcoding, and videos retrieval. According to the basic functions and cloud computing, each module design process and figure are provided in the paper. The massive videos management system based on cloud platform will be better than the traditional videos management system in the aspects of storage capacity, transcoding performance and retrieval speed.