Image Dictionary Research Articles

A method for extracting Martian terrain features based on unsupervised contrastive learning

Intelligent recognition of Martian surface terrain is of great significance to autonomous exploration of Mars rovers. Feature extraction methods for Martian terrain images are currently mainly divided into two categories: traditional shallow visual feature extraction and deep feature extraction based on supervised learning. Loss of image information and the need for a large amount of labeled data are key issues to be addressed. A method for Martian terrain feature recognition based on unsupervised contrastive learning is proposed. By establishing an image dictionary dataset, two sets of neural networks, "query" and "encoding", are used to compare a single image with other images in the "dictionary" dataset, and the network is trained using the similarity functional as the loss function, thereby realizing feature recognition of Martian terrain images. The proposed method also has the ability to recognize new types of terrain images outside the training dataset, and has outstanding superiority in subsequent recognition and classification. Computer simulation verification shows that the recognition accuracy of the proposed method is and the 85.4%recognition accuracy of new types of terrain images is 84.5%.

“WHITE” AND “BLACK” IMAGES IN THE POETRY OF M. MAKATAEV

In this article were considered two monochromes ―white‖and ―black‖in the poetic texts of Mukagali Makataev, who isa famous Kazakh poet, writer and translator of the 60sand 70s of the 20th century. A quantitative and qualitative methodsof analysis wereused, a frequency dictionary of color images was developed based on the material from the poetry collection ―МҰҚАҒАЛИ(MUKAGALI)‖ (2012). In addition, a detailed semantic and structural analysis of two monochromes was conducted to determine their role and the way in which the color semantics are represented: as main or additional elements. The generalized structural and semantic analysis revealed that Makataev uses these images as a contrast between darkness and lightness, comparing them and being indecisive in choosing a color. Black and white colors form thematic blocks such as animate/inanimate nature, the theme of moral choices, the theme of creativity, motherland, and love.Both colors reveal in their own way the theme of love and the theme of death through different images. Moreover, we can notice that the semantics of the white color is based on a well-knownand traditional image, while the black color contains the cultural background characteristic of the Kazakh people.

Screening based sparse classification method for the detection of corn leaf diseases

Detection of diseases in corn plant at early stage reduces the chance of productivity loss. Recognizing the different kind of disease in corn plant requires the identification of lesion part of the plant along with the extraction of proper features from the region of interest. Although several imaging tools and classifier were developed in the recent past towards identifying different kinds of disease in corn plant but most of the classification models do not meet the specific requirement due to improper selection of feature and classifier. In this paper, we proposed a two-step based sparse recognition model for the identification of corn disease. First step emphasizes with the construction of image dictionary by extracting multiple features from the lesion part of training image and followed it in the second phase, uses the screening and angle rule based sparse classifier to recognize the different corn diseases. Utilizing the data from the kaggle dataset and comparing with the other state of art, our method yielded an average classification accuracy of 88.55%. This makes the framework feasible and effective for the detection of corn plant disease.

Sparse Dictionary-Based Magnetic Resonance Superresolution Imaging with Joint Loss Function Learning.

Magnetic resonance image has important application value in disease diagnosis. Due to the particularity of its imaging mechanism, the resolution of hardware imaging needs to be improved by increasing radiation intensity and radiation time. Excess radiation can cause the body to overheat and, in severe cases, inactivate the protein. This problem is expected to be solved by the image superresolution method based on joint dictionary learning, which has good superresolution performance. In the process of dictionary learning, the loss function will directly affect the dictionary performance. The general method only uses the cascade error as the optimization function in dictionary training, and the method does not consider the individual reconstruction error of high- and low-resolution image dictionary. In order to solve the above problem, In this paper, the loss function of dictionary learning is optimized. While ensuring that the coefficients are sufficiently sparse, the high- and low-resolution dictionaries are trained separately to reduce the error generated by the joint high- and low-resolution dictionary block pair and increase the high-resolution reconstruction error. Experiments on neck and ankle MR images show that the proposed algorithm has better superresolution reconstruction performance on ×2 and ×4 compared with bicubic interpolation, nearest neighbor, and original dictionary learning algorithms.

Kronecker component with robust low-rank dictionary for image denoising

Robust Kronecker Component Analysis (RKCA) model is a newly proposed denoising method, which transforms the basic sparse representation model used for 2-D data into the tensor sparse representation used for 3-D data. This model is based on the idea that the dictionary in the basic sparse representation model can be separated into two separable dictionaries using the Kronecker Product and the mode-n product. Moreover, the original 3-D data can also be decomposed into a sparse matrix and two dictionaries by using Tucker factorization. It uses the Frobenius norm constraint to get two low-rank dictionaries. In this paper, we take the Nuclear norm into RKCA to better capture the low-rank property of the two dictionaries. Firstly, we design a novel denoising model named Kronecker Component with Low-Rank Dictionary (KCLD), which replaces the Frobenius norm by Nuclear norm in order to capture the low-rank property better. Further, we design a more effective denoising model named Kronecker Component with Robust Low-Rank Dictionary (KCRD) by combining the Frobenius norm and the Nuclear norm. KCRD fuses the advantages of Frobenius norm and the Nuclear norm, thus can get the better low-rank dictionary. Then, an augmented Lagrange multiplier method is used by convex relaxation of the split variable to optimize the two proposed model. Last, through the comparison of a large number of experiments, our models are more competitive and effective than other proposed denoising methods in different types of images.

Super Resolution for Noisy Images Using Convolutional Neural Networks

The images in high resolution contain more useful information than the images in low resolution. Thus, high-resolution digital images are preferred over low-resolution images. Image super-resolution is one of the principal techniques for generating high-resolution images. The major advantages of super-resolution methods are that they are economical, independent of the image capture devices, and can be statically used. In this paper, a single-image super-resolution network model based on convolutional neural networks is proposed by combining conventional autoencoder and residual neural network approaches. A convolutional neural network-based dictionary method is used to train low-resolution input images for high-resolution images. In addition, a linear refined unit thresholds the convolutional neural network output to provide a better low-resolution image dictionary. Autoencoders aid in the removal of noise from images and the enhancement of their quality. Secondly, the residual neural network model processes it further to create a high-resolution image. The experimental results demonstrate the outstanding performance of our proposed method compared to other traditional methods. The proposed method produces clearer and more detailed high-resolution images, as they are important in real-life applications. Moreover, it has the advantage of combining convolutional neural network-based dictionary learning, autoencoder image enhancement, and noise removal. Furthermore, residual neural network training with improved preprocessing creates an efficient and versatile single-image super-resolution network.

Внутренний мир человека в метафорических моделях с объектной областью «драгоценные камни» (на материале словарей поэтических образов)

The article characterizes the inner world of a person in metaphorical models with the object domain “precious stones” in dictionaries of images. The research material is fragments of texts of Russian literature, including figurative comparisons of the realities of the inner world of a person with precious stones. Sources of the material are: Dictionary of Poetic Images by N.V. Pavlovich; Dictionary of the Language of Poetry by N.N. Ivanova and O.E. Ivanova; Materials for the Dictionary of Metaphors and Comparisons of Russian Literature of the 19th-20th Centuries by N.A. Kozhevnikova and Z.Yu. Petrova. The article uses the following research methods and techniques: analysis of theoretical sources on the problem, collection of material, observation, classification and systematization, quantitative calculations. The research includes the following stages: detection in dictionary materials of the realization of metaphorical models containing a comparison of an object of the inner world with the object domain “precious stones”; determination of the composition of the models; description of the subject and object areas; determination of the grounds for comparisons; identification of the most significant subjects and objects of comparison and the main metaphorical models; indication of trends in the development of imagery reflected in the implementation of metaphorical models in texts of different times. The study shows that dictionaries of images contain a significant number of implementations of metaphorical models of the inner person with the “precious stone” object domain. These models capture ideas about features and properties of the realities of the inner world important for Russian culture, relating to the invisible organs of a person, their feelings, emotions, intelligence. The main subjects of comparison are soul, heart, love, sadness, dream, thought; the main objects of comparison are diamond, pearl and rhinestone. These comparisons are much more common than others and are reflected in all three dictionaries. The hardness, transparency, brilliance of a cut diamond; the color and purity of pearls; the transparency and fragility of crystal, its ability to sound allow them to be metaphorical analogues for especially valuable and attractive realities of the inner world of a person. The figurative characteristic of the inner world is also based on the peculiarities of the formation of diamond (earth’s interior, pressure, high temperatures) and pearls (water depths, closeness in the shell). The materials of the dictionaries reflect the trends in the development imagery; the replenishment of figurative series with new elements, the reduction of traditionally elevated realities, the concretization of images. The implementation of metaphorical models with the object domain “precious stones” reflect in versatile ways the ideas about the inner world of a person that exist in Russian culture. The author declares no conflicts of interests.

Recognition of Odia Character in an Image by Dividing the Image into Four Quadrants

This paper deals with optical character recognition of Odia characters written in a particular font family ‘AkrutiOriAshok-99’ with different font sizes 18, 20, 22, 24, 26, 28, 36, 48 and 72 in Bold style. The font ‘AkrutiOriAshok-99’ is a font from the typing software ‘Akruti’. The basic idea behind the approach followed in this paper is the character decomposition into four quadrants and then extracting features from each quadrant. The image processing techniques like converting the image to gray, resizing of image and converting gray image to binary are used in this approach. The system explained in this paper has two major parts: DictionaryBuilding and FindingMatch. For DictionaryBuilding, dictionary of images which are created either by scanning a document or a document converted to image, both written in same font family in different sizes. The features are extracted from each image in any font size in the ‘Dictionary’ using Preprocessing, FindPath, GettingFeaturesLeft or GettingFeaturesRight, VisitSubQuad, RemainingSubQuad, WriteToExcel and CommonFeature modules. The part FindingMatch is responsible for finding a correct match in the dictionary for the input image. For this, FeatureExtraction and Recognition modules have been used. Longest Common Subsequence (LCS) has been used for finding the common feature in DictionaryBuilding as well as finding the correct match. A total of 1800 characters, 200 characters of each font size have been tested and 98.1% of correctness has been achieved.

No Reference, Opinion Unaware Image Quality Assessment by Anomaly Detection.

We propose an anomaly detection based image quality assessment method which exploits the correlations between feature maps from a pre-trained Convolutional Neural Network (CNN). The proposed method encodes the intra-layer correlation through the Gram matrix and then estimates the quality score combining the average of the correlation and the output from an anomaly detection method. The latter evaluates the degree of abnormality of an image by computing a correlation similarity with respect to a dictionary of pristine images. The effectiveness of the method is tested on different benchmarking datasets (LIVE-itW, KONIQ, and SPAQ).

Adaptive and dynamic ordering of illumination patterns with an image dictionary in single-pixel imaging

Single-pixel imaging (SPI) is a novel optical imaging technique capable of handling unusual imaging conditions such as invisible wavebands and indirect line of sight. In SPI, the target object is sequentially illuminated with various structured-light patterns and a single-pixel detector is used to collect the total light intensity. Unlike conventional imaging, a pixelated sensor array is replaced with a single-pixel detector in SPI but the trade-off is that massive measurements are required to recover an object image with acceptable quality. To shorten the length of projection pattern sequence and image capturing time, it is feasible to arrange the illumination patterns in an optimized sequential order. For common Fourier SPI, we propose a novel scheme to adaptively and dynamically determine the order of illumination patterns based on the average spectrum of training images and the feedback of recorded single-pixel intensity values. Simulated and experimental results indicate that our proposed scheme can significantly enhance the imaging quality under low sampling rates.

Design of Optimal Illumination Patterns in Single-Pixel Imaging Using Image Dictionaries

Single-pixel imaging (SPI) has a major drawback that many sequential illuminations are required for capturing one single image with long acquisition time. Basis illumination patterns such as Fourier patterns and Hadamard patterns can achieve much better imaging efficiency than random patterns. But the performance is still sub-optimal since the basis patterns are fixed and non-adaptive for varying object images. This Letter proposes a novel scheme for designing and optimizing the illumination patterns adaptively from an image dictionary by extracting the common image features using principal component analysis (PCA). Simulation and experimental results reveal that our proposed scheme outperforms conventional Fourier SPI in terms of imaging efficiency.

ИССЛЕДОВАНИЕ И РАЗРАБОТКА «УНИВЕРСАЛЬНОГО СЛОВАРЯ ОБРАЗОВ» ДЛЯ СОЗДАНИЯ ЧЕЛОВЕКО-МАШИННОГО ИНТЕРФЕЙСА

The project urgency is evidenced by the measurement of subject-matter popularity on the Internet – a query to the Net on the topic of the subject gives 18900 results, and a novelty is defined by specification, for instance, the “Universal Image Dictionary” query gives “No results found for” and 1 result M24.RU – 10 unknown: monsters, stairs, funnels and keys… www.m24.ru/articles/112668/ … The project offered supposes the creation of the bank of different images already existing and having a wide distribution and which can be a means of international communication for people having no any other channel for information exchange. Such images could include common gestures, traffic signs, signs in transport, in the streets, in public accommodations and in state offices. They will include both single images, and their combinations forming a single conceptual complex (rules of table etiquette, on transport, and at the stadium etc.). It should be emphasized clearly that the dictionary offered is intended for interpersonal communication. A computer identification of images cannot be in this case a basic purpose for project realization. The orientation to interpersonal communication gives us a possibility to choose images for the dictionary and, what is not less significant, to set problems actually solvable at every stage of its creation.

Multivariate copula statistical model and weighted sparse classification for radar image target recognition

We propose in this paper a new method for targets recognition from radar images. To characterize the radar images, we adopt a statistical multivariate modeling using copula in the complex wavelet domain. For the recognition step, we investigate the weighted sparse representation-based classification (WSRC) method. To build the dictionary, the estimated copula parameters are stacked together in a matrix structure. In order to include the locality information of this dictionary for each unknown radar image to recognize, we affect weights for its atoms (columns). That is done by calculating the Kullback–Leibler divergence (KLD) between the multivariate copula parameters of training and test radar images. Finally, the unknown radar image is recognized through the SRC classifier. Several empirical results carried out on the SAR (synthetic aperture radar) and ISAR (inverse synthetic aperture radar) images demonstrate that the proposed method achieves high recognition rates and outperforms the remaining methods.

Halftoning-based BTC image reconstruction using patch processing with border constraint

This paper presents a new halftoning-based block truncation coding (HBTC) image reconstruction using sparse representation framework. The HBTC is a simple yet powerful image compression technique, which can effectively remove the typical blocking effect and false contour. Two types of HBTC methods are discussed in this paper, i.e., ordered dither block truncation coding (ODBTC) and error diffusion block truncation coding (EDBTC). The proposed sparsity-based method suppresses the impulsive noise on ODBTC and EDBTC decoded image with a coupled dictionary containing the HBTC image component and the clean image component dictionaries. Herein, a sparse coefficient is estimated from the HBTC decoded image by means of the HBTC image dictionary. The reconstructed image is subsequently built and aligned from the clean, i.e. non-compressed image dictionary and predicted sparse coefficient. To further reduce the blocking effect, the image patch is firstly identified as “border” and “non-border” type before applying the sparse representation framework. Adding the Laplacian prior knowledge on HBTC decoded image, it yields better reconstructed image quality. The experimental results demonstrate the effectiveness of the proposed HBTC image reconstruction. The proposed method also outperforms the former schemes in terms of reconstructed image quality.

Identification of external forces via truncated response sparse decomposition under unknown initial conditions

When structural dynamic design for smart control and health monitoring is executed, imposed excitations on structures are one of most important issues in structural engineering. Identification of structural excitations, such as force reconstruction, moving force identification, and so on, has drawn increasing attentions in the last decades. Assumption of known initial conditions is a precondition for existing deterministic force reconstruction methods. However, initial conditions are often unknown and hard to be estimated. To address this problem, a novel truncated response sparse decomposition method is proposed for calculating the external forces under unknown initial conditions. The truncated response sparse decomposition involves two basic steps, that is, response sparse decomposition and force estimation. First, a collection of basis vectors is defined for expressing unknown forces. Unknown initial conditions are represented in modal space. Structural responses induced by both external forces and initial conditions are then normalized as potential response features to form an image dictionary, which is adapted to decompose the measured responses via sparse regularization. Second, the response features with lower decomposed amplitudes and small scaling factors are eliminated from the decomposed results. The remaining features are used for estimating the external forces. In order to assess the accuracy and the feasibility of the proposed force reconstruction method, some numerical simulations on a planar truss structure and a series of experimental studies are carried out. The illustrated results show the robustness and the applicability of the proposed method for addressing the force reconstruction problem under unknown initial conditions. Some related issues are discussed as well.

A variational image segmentation method exploring both intensity means and texture patterns

Existing image segmentation methods usually consider only intensity or texture features, and thus cannot work well on images with both varying intensity and salient texture patterns. This paper aims to solve this problem by exploring both intensity and texture features for better image segmentation. To this end, we propose a novel variational image segmentation model, which uses constant vectors to represent intensity means in different image subregions and structured dictionaries to encode local texture patterns in images. We develop an effective algorithm to implement the proposed variational model by seeking for intensity means and a specific dictionary for the input image and meanwhile computing the representation coefficients of image patches with respect to the learned dictionary. We derive closed-form solutions for all these components, which result in the high efficiency of our proposed method. Extensive evaluation experiments with comparison to existing methods have been done on both synthetic and real-world images. The results demonstrate the superiority of our proposed method in effectively segmenting images with both unsmooth intensity variations and salient texture patterns.

A Novel Adversarial Based Hyperspectral and Multispectral Image Fusion

In order to reconstruct a high spatial and high spectral resolution image (H2SI), one of the most common methods is to fuse a hyperspectral image (HSI) with a corresponding multispectral image (MSI). To effectively obtain both the spectral correlation of bands in HSI and the spatial correlation of pixels in MSI, this paper proposes an adversarial selection fusion (ASF) method for the HSI–MSI fusion problem. Firstly, the unmixing based fusion (UF) method is adopted to dig out the spatial correlation in MSI. Then, to acquire the spectral correlation in HSI, a band reconstruction-based fusion (BRF) method is proposed, regarding H2SI as the product of the optimized band image dictionary and reconstruction coefficients. Finally, spectral spatial quality (SSQ) index is designed to guide the adversarial selection process of UF and BRF. Experimental results on four real-world images demonstrate that the proposed strategy achieves smaller errors and better reconstruction results than other comparison methods.

Fusion of United Sparse Principal Component Analysis Dictionary Based on Linear Unmixing Image Technique

Based on the linear unmixing images of different surface objects, online dictionary learning algorithm was utilized to compute the sparse dictionaries for multispectral linear unmixing images and panchromatic images. Principal component analysis (PCA) was then utilized to generate united sparse PCA dictionaries through the extraction of the first principal components of panchromatic images and unmixing image dictionaries. The number of dictionaries is determined to be 480 after taking into consideration of the limitation in computing power and root-mean-square error of restructured images. Based on these dictionaries, orthogonal matching pursuit method was utilized to calculate the sparse coefficients of multispectral and panchromatic images, separately, while nonnegative matrix factorization fusion algorithm was utilized to calculate multispectral and panchromatic sparse coefficients to obtain sparse coefficient of the fusional image on all bands, with the resulted matrix having a size of $480 \times 255\,025$ . These united sparse PCA dictionaries and fusion sparse coefficients were then used to reconstruct the fusional image. Through the analysis of five quantitative indices of fusion assessment, the proposed fusion algorithm has retained the multispectral information of images and enhanced the detailed information in image texture.

Deformable Dictionary Learning for SAR Image Change Detection

This paper proposes a novel method based on deformable dictionary learning for detecting the regions of change between multitemporal image pairs. We build on our previous work, which constructed a pair of dictionaries. The main shortcoming of this method was its dependence on a large amount of training data. In practice, there is often a shortage of ground-truthed training images, which limits the expression capability of the resulting dictionaries. This paper overcomes this challenge by incorporating the concept of deformation, wherein each atom of a dictionary is no longer a simple image patch, but instead is a flexible image deformation function. This enables the creation of more expressive dictionaries, capable of generalizing to a far greater variety of image patterns, while using a far smaller amount of ground-truthed images for supervised dictionary training. Deformation similarity is employed for patch matching to find the best set of atoms in the difference image (DI) dictionary for reconstructing image patches for a new input DI. Each such atom can be deformed to achieve a better match, thus extending generality while reducing the number of atoms needed in the dictionary. Multiple deformed atoms are weighted and combined to best reconstruct the input DI patch. Then, the same set of deformations and weights is projected to the corresponding atoms in the CD dictionary to obtain the output change-detection map. Experiments in six realistic synthetic aperture radar data sets demonstrate the robustness and efficiency of the proposed method in comparison with five other state-of-the-art methods from the literature.

P‐5.3: A super resolution reconstruction algorithm based on spatial autoregression regularization

In a lot of micro display applications, we need to enlarge and recognize a region of interest (ROI), which often get a low‐resolution image because of limited resolution source image. This paper proposed a novel image reconstruction algorithm based on spatial autoregression regularization and sparse representation. This reconstruction algorithm trained an image dictionary with the same sparse coefficient by sparse K‐SVD, and then import the autoregressive regularization item to construct the objective function which can realize local adaptive control of the image. In order to obtain further clear image, the degradation model was used which can realize the global constraints. The experimental results show that the proposed algorithm has considerable effectiveness in terms of both objective measurements and visual evaluation.