Multimedia content analysis is applied in different real-world computer vision applications, and digital images constitute a major part of multimedia data. In last few years, the complexity of multimedia contents, especially the images, has grown exponentially, and on daily basis, more than millions of images are uploaded at different archives such as Twitter, Facebook, and Instagram. To search for a relevant image from an archive is a challenging research problem for computer vision research community. Most of the search engines retrieve images on the basis of traditional text-based approaches that rely on captions and metadata. In the last two decades, extensive research is reported for content-based image retrieval (CBIR), image classification, and analysis. In CBIR and image classification-based models, high-level image visuals are represented in the form of feature vectors that consists of numerical values. The research shows that there is a significant gap between image feature representation and human visual understanding. Due to this reason, the research presented in this area is focused to reduce the semantic gap between the image feature representation and human visual understanding. In this paper, we aim to present a comprehensive review of the recent development in the area of CBIR and image representation. We analyzed the main aspects of various image retrieval and image representation models from low-level feature extraction to recent semantic deep-learning approaches. The important concepts and major research studies based on CBIR and image representation are discussed in detail, and future research directions are concluded to inspire further research in this area.

/pdf/content-based-image-retrieval-and-feature-extraction-a-1x3x79153q.pdf

Content-Based Image Retrieval and Feature Extraction: A Comprehensive Review

Radiological images and machine learning: Trends, perspectives, and prospects.

Content based image retrieval with sparse representations and local feature descriptors : A comparative study

A survey on image data analysis through clustering techniques for real world applications

Deep learning architectures particularly Convolutional Neural Network (CNN) have shown an intrinsic ability to automatically extract the high level representations from big data CNN has produced impressive results in natural image classification, but there is a major hurdle to their deployment in medical domain because of the relatively lack of training data as compared to general imaging benchmarks such as ImageNet In this paper we present a comparative evaluation of the three milestone architectures ie LeNet, AlexNet and GoogLeNet and propose our CNN architecture for classifying medical anatomy images Based on the experiments, it is shown that the proposed Convolutional Neural Network architecture outperforms the three milestone architectures in classifying medical images of anatomy object

A deep learning architecture for classifying medical images of anatomy object

Content based medical image retrieval using dictionary learning

In compressed sensing the matrices that satisfy the Restricted Isometry Property (RIP) play an important role. To date, however, very few results for designing such matrices are available. For applications such as multiplier-less data compression, binary sensing matrices are of interest. The present paper constructs deterministic and binary sensing matrices using Euler Squares. In particular, given a positive integer $m$ different from $p,{p}^{2}$ for a prime $p$ , we show that it is possible to construct a binary sensing matrix of size $mtimes c{(mmu)}^{2}$ , where $mu $ is the coherence parameter of the matrix and $cin [1,2)$ . The matrices that we construct have small density (that is, percentage of nonzero entries in the matrix is small) with no function evaluation in their construction, which support algorithms with low computational complexity. Through experimental work, we show that our binary sensing matrices can be used for such applications as content based image retrieval. Our simulation results demonstrate that the Euler Square based CS matrices give better performance than their Gaussian counterparts.

Deterministic Compressed Sensing Matrices: Construction via Euler Squares and Applications

In the recent past, various methods have been proposed to construct deterministic compressed sensing (CS) matrices. Of interest has been the construction of binary sensing matrices as they are useful for multiplierless and faster dimensionality reduction. In most of these binary constructions, the matrix size depends on primes or their powers. In this study, we propose a composition rule which exploits sparsity and block structure of existing binary CS matrices to construct matrices of general size. We also show that these matrices satisfy optimal theoretical guarantees and have similar density compared to matrices obtained using Kronecker product. Simulation work shows that the synthesized matrices provide comparable results against Gaussian random matrices.

Composition of Binary Compressed Sensing Matrices

The construction of binary sensing matrices is one of the active directions in the emerging field of compressed sensing (CS). Due to their sparse structure and competitive performance, they provide multiplier-less and faster dimensionality reduction in applications such as data compression. This letter attempts to relate the notion of extremal set theory to the construction of good CS matrices. In particular, we show that extremal set theory is useful for constructing binary sensing matrices and bounding their maximum column size (i.e., number of columns). We also prove the existence of binary sensing matrices whose column size meets the upper bound. Simulation results show that the constructed matrices outperform Gaussian and Bernoulli random matrices, as well as other deterministic binary and bipolar constructions from the literature.

Construction of Binary Sensing Matrices Using Extremal Set Theory

In Compressed Sensing the matrices that satisfy the Restricted Isometry Property (RIP) play an important role. But to date, very few results for designing such matrices are available. For applications such as multiplier-less data compression, binary sensing matrices are of interest. The present work constructs deterministic and binary sensing matrices using Euler Squares. In particular, given a positive integer $m$ different from $p, p^2$ for a prime $p$, we show that it is possible to construct a binary sensing matrix of size $m \times c (m\mu)^2$, where $\mu$ is the coherence parameter of the matrix and $c \in [1,2)$. The matrices that we construct have smaller density (that is, percentage of nonzero entries in the matrix is small) with no function evaluation in their construction, which support algorithms with low computational complexity. Through experimental work, we show that our binary sensing matrices can be used for such applications as content based image retrieval. Our simulation results demonstrate that the Euler Square based CS matrices give better performance than their Gaussian counterparts.

R. Ramu Naidu

Papers

Content based medical image retrieval using dictionary learning

Deterministic Compressed Sensing Matrices: Construction via Euler Squares and Applications

Composition of Binary Compressed Sensing Matrices

Construction of Binary Sensing Matrices Using Extremal Set Theory

Deterministic compressed sensing matrices: Construction via Euler Squares and applications