Large-scale Image Database Research Articles

Computational Snapshot Multispectral Cameras: Toward dynamic capture of the spectral world

Multispectral cameras collect image data with a greater number of spectral channels than traditional trichromatic sensors, thus providing spectral information at a higher level of detail. Such data are useful in various fields, such as remote sensing, materials science, biophotonics, and environmental monitoring. The massive scale of multispectral data-at high resolutions in the spectral, spatial, and temporal dimensions-has long presented a major challenge in spectrometer design. With recent developments in sampling theory, this problem has become more manageable through use of undersampling and constrained reconstruction techniques. This article presents an overview of these state-of-the-art multispectral acquisition systems, with a particular focus on snapshot multispectral capture, from a signal processing perspective. We propose that undersampling-based multispectral cameras can be understood and compared by examining the efficiency of their sampling schemes, which we formulate as the spectral sensing coherence information between their sensing matrices and spectrum-specific bases learned from a large-scale multispectral image database. We analyze existing snapshot multispectral cameras in this manner, and additionally discuss their optical performance in terms of light throughput and system complexity.

Age estimation using effective brain local features from T1-weighted images.

This paper proposes a simple method of selecting effective brain local features for age estimation from T1-weighted MR images. We also employ the high-resolution AAL atlas, which is defined by 1,024 local regions, to improve the accuracy of age estimation. We evaluate performance of the proposed method using 1,099 T1-weighted images from a large-scale brain MR image database of healthy Japanese, and demonstrate that the proposed method exhibits efficient performance of age estimation compared with conventional methods.

A Privacy-Preserving Framework for Large-Scale Content-Based Information Retrieval Using K-Secure Sum Protocol

We propose a privacy protection framework for large-scale content-based information retrieval. It offers two layers of protection. To begin with, robust hash values are utilized as quiries to avoid uncovering unique content or features. Second, the customer can choose to exclude certain bits in a hash values to further expand the ambiguity for the server. Due to the reduced information, it is computationally difficult for the server to know the customer's interest. The server needs to give back the hash values of every single possible to the customer. The customer performs a search within the candidate list to locate the best match. Since just hash values are exchanged between the client and the server, the privacy of both sides is ensured. We present the idea of tunable privacy, where the privacy protection level can be balanced by policy. It is acknowledged through hash-based piecewise inverted indexing. The thought is to gap a highlight vector into pieces and list every piece with a sub hash value. Each sub hash value is connected with an inverted index list. The framework has been broadly tested using a large scale image database. We have assessed both retrieval performance and privacy-preserving performance for a specific content identification application. Two unique developments of robust hash algorithms are utilized. One depends on random projections; the other depends on the discrete wavelet transform. Both algorithm exhibit satisfactory performances in comparison with state-of-the-art retrieval performances. The outcomes demonstrate that the privacy upgrade somewhat enhances the retrieval performance. We consider the majority voting attack for evaluating the query category and identification. The test results demonstrate that this attack is a threat when there are close duplicities, yet the achievement rate diminishes with the quantity of discarded bits and the number of distinct items.

Toward a No-Reference Image Quality Assessment Using Statistics of Perceptual Color Descriptors.

Analysis of the statistical properties of natural images has played a vital role in the design of no-reference (NR) image quality assessment (IQA) techniques. In this paper, we propose parametric models describing the general characteristics of chromatic data in natural images. They provide informative cues for quantifying visual discomfort caused by the presence of chromatic image distortions. The established models capture the correlation of chromatic data between spatially adjacent pixels by means of color invariance descriptors. The use of color invariance descriptors is inspired by their relevance to visual perception, since they provide less sensitive descriptions of image scenes against viewing geometry and illumination variations than luminances. In order to approximate the visual quality perception of chromatic distortions, we devise four parametric models derived from invariance descriptors representing independent aspects of color perception: 1) hue; 2) saturation; 3) opponent angle; and 4) spherical angle. The practical utility of the proposed models is examined by deploying them in our new general-purpose NR IQA metric. The metric initially estimates the parameters of the proposed chromatic models from an input image to constitute a collection of quality-aware features (QAF). Thereafter, a machine learning technique is applied to predict visual quality given a set of extracted QAFs. Experimentation performed on large-scale image databases demonstrates that the proposed metric correlates well with the provided subjective ratings of image quality over commonly encountered achromatic and chromatic distortions, indicating that it can be deployed on a wide variety of color image processing problems as a generalized IQA solution.

Hybrid Swarm Intelligence Method for Post Clustering Content Based Image Retrieval

Content Based Image Retrieval is one of the most promising method for image retrieval where searching and retrieving images from large scale image database is a critical task. In Content Based Image Retrieval many visual feature like color, shape, and texture are extracted in order to match query image with stored database images. Matching the query image with each image of large scale database results in large number of disc scans which in turns slows down the systems performance.The proposed work suggested an approach for post clustering Content Based Image Retrieval, in which the database images are clustered into optimized clusters for further retrieval process. Various clustering algorithms are implemented and results are compared. Among all, it is found that hybrid ACPSO algorithm performs better over basic algorithms like k-means, ACO, PSO etc. Hybrid ACPSO has the capability to produce good cluster initialization and form global clustering.This paper discusses work-in-progress where we have implemented till clustering module and intermediate results are produced. These resulted clusters will further be used for effective Content Based Image Retrieval.

Interleaved text/image deep mining on a large-scale radiology database for automated image interpretation

Despite tremendous progress in computer vision, there has not been an attempt to apply machine learning on very large-scale medical image databases. We present an interleaved text/image deep learning system to extract and mine the semantic interactions of radiology images and reports from a national research hospital's Picture Archiving and Communication System. With natural language processing, we mine a collection of ∼216K representative two-dimensional images selected by clinicians for diagnostic reference and match the images with their descriptions in an automated manner. We then employ a weakly supervised approach using all of our available data to build models for generating approximate interpretations of patient images. Finally, we demonstrate a more strictly supervised approach to detect the presence and absence of a number of frequent disease types, providing more specific interpretations of patient scans. A relatively small amount of data is used for this part, due to the challenge in gathering quality labels from large raw text data. Our work shows the feasibility of large-scale learning and prediction in electronic patient records available in most modern clinical institutions. It also demonstrates the trade-offs to consider in designing machine learning systems for analyzing large medical data.

Scalable Feature Matching by Dual Cascaded Scalar Quantization for Image Retrieval.

In this paper, we investigate the problem of scalable visual feature matching in large-scale image search and propose a novel cascaded scalar quantization scheme in dual resolution. We formulate the visual feature matching as a range-based neighbor search problem and approach it by identifying hyper-cubes with a dual-resolution scalar quantization strategy. Specifically, for each dimension of the PCA-transformed feature, scalar quantization is performed at both coarse and fine resolutions. The scalar quantization results at the coarse resolution are cascaded over multiple dimensions to index an image database. The scalar quantization results over multiple dimensions at the fine resolution are concatenated into a binary super-vector and stored into the index list for efficient verification. The proposed cascaded scalar quantization (CSQ) method is free of the costly visual codebook training and thus is independent of any image descriptor training set. The index structure of the CSQ is flexible enough to accommodate new image features and scalable to index large-scale image database. We evaluate our approach on the public benchmark datasets for large-scale image retrieval. Experimental results demonstrate the competitive retrieval performance of the proposed method compared with several recent retrieval algorithms on feature quantization.

Sequential Compact Code Learning for Unsupervised Image Hashing.

Effective hashing for large-scale image databases is a popular research area, attracting much attention in computer vision and visual information retrieval. Several recent methods attempt to learn either graph embedding or semantic coding for fast and accurate applications. In this paper, a novel unsupervised framework, termed evolutionary compact embedding (ECE), is introduced to automatically learn the task-specific binary hash codes. It can be regarded as an optimization algorithm that combines the genetic programming (GP) and a boosting trick. In our architecture, each bit of ECE is iteratively computed using a weak binary classification function, which is generated through GP evolving by jointly minimizing its empirical risk with the AdaBoost strategy on a training set. We address this as greedy optimization by embedding high-dimensional data points into a similarity-preserved Hamming space with a low dimension. We systematically evaluate ECE on two data sets, SIFT 1M and GIST 1M, showing the effectiveness and the accuracy of our method for a large-scale similarity search.

Spherical hashing: binary code embedding with hyperspheres.

Many binary code embedding schemes have been actively studied recently, since they can provide efficient similarity search, and compact data representations suitable for handling large scale image databases. Existing binary code embedding techniques encode high-dimensional data by using hyperplane-based hashing functions. In this paper we propose a novel hypersphere-based hashing function, spherical hashing, to map more spatially coherent data points into a binary code compared to hyperplane-based hashing functions. We also propose a new binary code distance function, spherical Hamming distance, tailored for our hypersphere-based binary coding scheme, and design an efficient iterative optimization process to achieve both balanced partitioning for each hash function and independence between hashing functions. Furthermore, we generalize spherical hashing to support various similarity measures defined by kernel functions. Our extensive experiments show that our spherical hashing technique significantly outperforms state-of-the-art techniques based on hyperplanes across various benchmarks with sizes ranging from one to 75 million of GIST, BoW and VLAD descriptors. The performance gains are consistent and large, up to 100 percent improvements over the second best method among tested methods. These results confirm the unique merits of using hyperspheres to encode proximity regions in high-dimensional spaces. Finally, our method is intuitive and easy to implement.

Large-scale image recognition based on parallel kernel supervised and semi-supervised subspace learning

Kernel discriminant subspace learning technique is effective to exploit the structure of image dataset in the high-dimensional nonlinear space. However, for large-scale image recognition applications, this technique usually suffers from large computational burden. Although some kernel accelerating methods have been presented, how to greatly reduce computing time and simultaneously keep favorable recognition accuracy is still challenging. In this paper, we introduce the idea of parallel computing into kernel subspace learning and build a parallel kernel discriminant subspace learning framework. In this framework, we firstly design a random non-overlapping equal data division strategy to divide the whole training set into several subsets and assign each computational node a subset. Then, we separately learn kernel discriminant subspaces from these subsets without mutual communications and finally select the most appropriate subspace to classify test samples. Under the built framework, we propose two novel kernel subspace learning approaches, i.e., parallel kernel discriminant analysis (PKDA) and parallel kernel semi-supervised discriminant analysis (PKSDA). We show the superiority of the proposed approaches in terms of time complexity as compared with related methods, and provide the fundamental supports for our framework. For experiment, we establish a parallel computing environment and employ three public large-scale image databases as experiment data. Experimental results demonstrate the efficiency and effectiveness of the proposed approaches.

No-reference image sharpness assessment in autoregressive parameter space.

In this paper, we propose a new no-reference (NR)/blind sharpness metric in the autoregressive (AR) parameter space. Our model is established via the analysis of AR model parameters, first calculating the energy- and contrast-differences in the locally estimated AR coefficients in a pointwise way, and then quantifying the image sharpness with percentile pooling to predict the overall score. In addition to the luminance domain, we further consider the inevitable effect of color information on visual perception to sharpness and thereby extend the above model to the widely used YIQ color space. Validation of our technique is conducted on the subsets with blurring artifacts from four large-scale image databases (LIVE, TID2008, CSIQ, and TID2013). Experimental results confirm the superiority and efficiency of our method over existing NR algorithms, the stateof-the-art blind sharpness/blurriness estimators, and classical full-reference quality evaluators. Furthermore, the proposed metric can be also extended to stereoscopic images based on binocular rivalry, and attains remarkably high performance on LIVE3D-I and LIVE3D-II databases.

Weighted Component Hashing of Binary Aggregated Descriptors for Fast Visual Search

Towards low bit rate mobile visual search, recent works have proposed to aggregate the local features and compress the aggregated descriptor (such as Fisher vector, the vector of locally aggregated descriptors) for low latency query delivery as well as moderate search complexity. Even though Hamming distance can be computed very fast, the computational cost of exhaustive linear search over the binary descriptors grows linearly with either the length of a binary descriptor or the number of database images. In this paper, we propose a novel weighted component hashing (WeCoHash) algorithm for long binary aggregated descriptors to significantly improve search efficiency over a large scale image database. Accordingly, the proposed WeCoHash has attempted to address two essential issues in Hashing algorithms: “what to hash” and “how to search.” “What to hash” is tackled by a hybrid approach, which utilizes both image-specific component (i.e., visual word) redundancy and bit dependency within each component of a binary aggregated descriptor to produce discriminative hash values for bucketing. “How to search” is tackled by an adaptive relevance weighting based on the statistics of hash values. Extensive comparison results have shown that WeCoHash is at least 20 times faster than linear search and 10 times faster than local sensitive hash (LSH) when maintaining comparable search accuracy. In particular , the WeCoHash solution has been adopted by the emerging MPEG compact descriptor for visual search (CDVS) standard to significantly speed up the exhaustive search of the binary aggregated descriptors.

English

Content-based image retrieval (CBIR) is a technique which uses visual content to search and compare images from large scale image databases according to the interests of users. Visual content of the image like color, shape, texture and spatial layout are widely used in CBIR. Texture features has been successfully used to provide a meaningful tool for searching image databases, as texture images generally contain unique visual patterns or spatial arrangements of pixels, so that describing textures, gray- level or color alone, may not yield to classify similar ones. In this paper we mainly concentrate on Spectral methods which extract texture features from the energy distribution in the frequency domain. The most popular spectral feature extraction methods are Fourier, wavelet, and Gabor filtering. In the first process it will extract the features from query and database images to a distinguishable extent using Gabor and wavelet Transforms. In the second process it involves matching these features to yield a result that is visually similar by feature matching process.

Retrieval of Images Using SVM

Image retrieval is a technique which is used to search and retrieve images from a large database of digital images. Content-based image retrieval (CBIR) is a technique which allows searching images from large scale image database based on contents as needed by user.This paper introduces a technique to retrieve images by classifying it on the basis of the features and characteristics it contains using Support Vector Machine (SVM). The dataset of images is created which is used for feature matching purpose by SVM to find similar images from the database and based on user requirements images are retrieved.

A novel visual codebook model based on fuzzy geometry for large-scale image classification

The codebook model has been developed as an effective means for image classification. However, the inherent operation of assigning visual words to image feature vectors in traditional codebook approaches causes serious ambiguities in image classification. In particular, the nearest word may not be the best fit to a feature, and multiple words may be equally appropriate for one specific feature. To resolve these ambiguities, we propose a novel visual codebook model based on the n-dimensional fuzzy geometry (n-D FG) theory, where all visual words and features are modeled as fuzzy points in the n-D FG space, and appropriate uncertainty is introduced to each fuzzy point to enhance the representation capacity. This n-D FG-codebook model not only inherits advantages from the fuzzy set theory, but also facilitates the analysis and determination of the relationship between visual words and features in geometric form. By explicitly taking into account the ambiguities, we propose a novel measure of similarity between the visual words and fuzzy features. Following the proposed codebook model and the novel similarity measure, we develop two useful image classification algorithms by modifying popular image coding algorithms (i.e. SPM and LLC). Finally, experimental results demonstrate that the classification accuracy of the proposed algorithms is dramatically improved for a standard large-scale image database. For example, with a codebook size of 256, the proposed algorithms achieve similar performance as traditional algorithms with a codebook size of 1024, indicating that the proposed algorithms reduce the computational cost by 75% while achieving almost identical classification accuracy to traditional algorithms. Thus, the proposed algorithms represent a more efficient and appropriate scheme for big image data.

Reconfigurable content-based image retrieval on peer-to-peer networks

Performing content–based image retrieval (CBIR) from Internet scale databases connected through peer–to–peer (P2P) networks, abbreviated as P2P–CBIR, helps to explore the large–scale image database distributed over connected peers. For P2P topology, the flexible decentralised unstructured P2P network topology is adopted, based on which informed–like searching approach enables flexible routing control when peers join/leave. The scalable retrieval control can be developed based on the P2P–CBIR framework, which can adapt the query scope and progressively refine the accuracy during the retrieval process. By reconfiguring system at each regular interval times, we can effectively reduce trivial peer routing and retrieval operations due to imprecise configurations. Experiments demonstrated that the average recall rate of the proposed P2P–CBIR method with reconfiguration is higher than that without about 10.73%, while the latter outperforms previous methods, i.e., firework query model (FQM) and breadth–first search (BFS), about 27% and 57%, respectively, under the same time–to–live (TTL) setting.

EMR: A Scalable Graph-Based Ranking Model for Content-Based Image Retrieval

Graph-based ranking models have been widely applied in information retrieval area. In this paper, we focus on a well known graph-based model - the Ranking on Data Manifold model, or Manifold Ranking (MR). Particularly, it has been successfully applied to content-based image retrieval, because of its outstanding ability to discover underlying geometrical structure of the given image database. However, manifold ranking is computationally very expensive, which significantly limits its applicability to large databases especially for the cases that the queries are out of the database (new samples). We propose a novel scalable graph-based ranking model called Efficient Manifold Ranking (EMR), trying to address the shortcomings of MR from two main perspectives: scalable graph construction and efficient ranking computation. Specifically, we build an anchor graph on the database instead of a traditional <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> -nearest neighbor graph, and design a new form of adjacency matrix utilized to speed up the ranking. An approximate method is adopted for efficient out-of-sample retrieval. Experimental results on some large scale image databases demonstrate that EMR is a promising method for real world retrieval applications.

Effective optimizations of cluster-based nearest neighbor search in high-dimensional space

Nearest neighbor (NN) search in high-dimensional space plays a fundamental role in large-scale image retrieval. It seeks efficient indexing and search techniques, both of which are simultaneously essential for similarity search and semantic analysis. However, in recent years, there has been a rare breakthrough. Achievement of current techniques for NN search is far from satisfactory, especially for exact NN search. A recently proposed method, HB, addresses the exact NN search efficiently in high-dimensional space. It benefits from cluster-based techniques which can generate more compact representation of the data set than other techniques by exploiting interdimensional correlations. However, HB suffers from huge cost for lower bound computations and provides no further pruning scheme for points in candidate clusters. In this paper, we extend the HB method to address exact NN search in correlated, high-dimensional vector data sets extracted from large-scale image database by introducing two new pruning/selection techniques and we call it HB+. The first approach aims at selecting more quickly the subset of hyperplanes/clusters that must be considered. The second technique prunes irrelevant points in the selected subset of clusters. Performed experiments show the improvement of HB+ with respect to HB in terms of efficiency (I/O cost and CPU response time) and also demonstrate the superiority over other exact NN indexes.

Social images tag ranking based on visual words in compressed domain

With the introduction of many image compression standards, the social images are stored and transmitted in compressed formats such as JPEG. For large-scale image database, tag ranking must fully decompress the compressed data to predict tag relevance based on visual content. In order to improve the accuracy of tag ranking and further reduce the ranking time, social images tag ranking based on visual words in compressed domain is proposed in this paper, which includes three steps: (1) low-resolution social images are constructed from the compressed image data; (2) visual words are created according to extracted SIFT descriptors in low-resolution social image; (3) the neighbor voting model is utilized to rank the image tags after matching the similarity based on visual words of an image. In order to evaluate the performance of the proposed method, average NDCG (normalized discounted cumulative gain) and tag ranking time are compared. Experimental results show that the proposed method can significantly reduce the time of image tag ranking under ensuring the ranking accuracy of social image tags.

Applying latent semantic analysis to large-scale medical image databases

Latent Semantic Analysis (LSA) although has been used successfully in text retrieval when applied to CBIR induces scalability issues with large image collections. The method so far has been used with small collections due to the high cost of storage and computational time for solving the SVD problem for a large and dense feature matrix. Here we present an effective and efficient approach of applying LSA skipping the SVD solution of the feature matrix and overcoming in this way the deficiencies of the method with large scale datasets. Early and late fusion techniques are tested and their performance is calculated. The study demonstrates that early fusion of several composite descriptors with visual words increase retrieval effectiveness. It also combines well in a late fusion for mixed (textual and visual) ad hoc and modality classification. The results reported are comparable to state of the art algorithms without including additional knowledge from the medical domain.