Physical Features for Reproducing Images With Perceived Gloss Equivalent to Real Glossy Objects

Cloud detection of satellite images is a challenging task. Extracting discriminative image features is one of the crucial steps for accurate cloud detection. In this chapter, we introduce a texture-based image feature that combines the merits of grey-level co-occurrence matrix (GLCM) features and rotation invariant uniform local binary pattern (RIULBP). The cloud detection method based on proposed feature consists of three steps: (1) Enhancing the image and dividing it into non-overlap patches; (2) Calculating GLCM features and RIULBP independently on patches and determining their optimal key parameters based on cloud detection performance; (3) Combining optimal GLCM features and RIULBP and feeding them into SVM classifier to identify patches with cloud. The proposed detection method is quantitatively compared to methods that only use GLCM features and RIULBP. The overall detection accuracy shows that our proposed method outperforms the GLCM and RIULBP method on real images. The proposed cloud detection method facilitates cloud segmentation and classification tasks, which can aid to better analysis of satellite image.

Image analysis techniques and gray-level co-occurrence matrices (GLCM) for calculating bioturbation indices and characterizing biogenic sedimentary structures

This paper presents a method of evaluating unsupervised texture segmentation algorithms. The control scheme of texture segmentation has been conceptualized as two modular processes: (1) feature computation and (2) segmentation of homogeneous regions based on the feature values. Three feature extraction methods are considered: gray level co-occurrence matrix, Laws' texture energy and Gabor multi-channel filtering. Three segmentation algorithms are considered: fuzzy c-means clustering, square-error clustering and split-and-merge. A set of 35 real scene images with manually-specified ground truth was compiled. Performance is measured against ground truth on real images using region-based and pixel-based performance metrics.

High-content image generation for drug discovery using generative adversarial networks

Problem statement: Recently, there has been a huge progress in collection of varied image databases in the form of digital. Most of the users found it difficult to search and retrieve required images in large collections. In order to provide an effective and efficient search engine tool, the system has been implemented. In image retrieval system, there is no methodologies have been considered directly to retrieve the images from databases. Instead of that, various visual features that have been considered indirect to retrieve the images from databases. In this system, one of the visual features such as texture that has been considered indirectly into images to extract the feature of the image. That featured images only have been considered for the retrieval process in order to retrieve exact desired images from the databases. Approach: The aim of this study is to construct an efficient image retrieval tool namely, “Content Based Medical Image Retrieval with Texture Content using Gray Level Co-occurrence Matrix (GLCM) and k-Means Clustering algorithms”. This image retrieval tool is capable of retrieving images based on the texture feature of the image and it takes into account the Pre-processing, feature extraction, Classification and retrieval steps in order to construct an efficient retrieval tool. The main feature of this tool is used of GLCM of the extracting texture pattern of the image and k-means clustering algorithm for image classification in order to improve retrieval efficiency. The proposed image retrieval system consists of three stages i.e., segmentation, texture feature extraction and clustering process. In the segmentation process, preprocessing step to segment the image into blocks is carried out. A reduction in an image region to be processed is carried out in the texture feature extraction process and finally, the extracted image is clustered using the k-means algorithm. The proposed system is employed for domain specific based search engine for medical Images such as CT-Scan, MRI-Scan and X-Ray. Results: For retrieval efficiency calculation, conventional measures namely precision and recall were calculated using 1000 real time medical images (100 in each category) from the MATLAB Workspace database. For selected query images from the MATLAB-Image Processing tool Box-Workspace Database, the proposed tool was tested and the precision and recall results were presented. The result indicates that the tool gives better performance in terms of percentage for all the 1000 real time medical images from which the scalable performance of the system has been proved. Conclusion: This study proposed a model for the Content Based Medical Image Retrieval System by using texture feature in calculating the Gray Level Co Occurrence matrix (GLCM) from which various statistical measures were computed in order to increasing similarities between query image and database images for improving the retrieval performance along with the large scalability of the databases.

Image synthesis in magnetic resonance (MR) imaging has been an active area of research for more than ten years. MR image synthesis can be used to create images that were not acquired or replace images that are corrupted by artifacts, which can be of great benefit in automatic image analysis. Although synthetic images have been used with success in many applications, it is quite often true that they do not look like real images. In practice, an expert can usually distinguish synthetic images from real ones. Generative adversarial networks (GANs) have significantly improved the realism of synthetic images. However, we argue that further improvements can be made through the introduction of noise in the synthesis process, which better models the actual imaging process. Accordingly, we propose a novel approach that incorporates randomness into the model in order to better approximate the distribution of real MR images. Results show that the proposed method has comparable accuracy with the state-of-the-art approaches as measured by multiple similarity measurements while also being able to control the noise level in synthetic images. To further demonstrate the superiority of this model, we present results from a human observer study on synthetic images, which shows that our results capture the essential features of real MR images.

IPDNet: A dual convolutional network combined with image prior for single image dehazing

This work researched apple quality identification and classification from real images containing complicated disturbance information (background was similar to the surface of the apples). This paper proposed a novel model based on convolutional neural networks (CNN) which aimed at accurate and fast grading of apple quality. Specific, complex, and useful image characteristics for detection and classification were captured by the proposed model. Compared with existing methods, the proposed model could better learn high-order features of two adjacent layers that were not in the same channel but were very related. The proposed model was trained and validated, with best training and validation accuracy of 99% and 98.98% at 2590th and 3000th step, respectively. The overall accuracy of the proposed model tested using an independent 300 apple dataset was 95.33%. The results showed that the training accuracy, overall test accuracy and training time of the proposed model were better than Google Inception v3 model and traditional imaging process method based on histogram of oriented gradient (HOG), gray level co-occurrence matrix (GLCM) features merging and support vector machine (SVM) classifier. The proposed model has great potential in Apple’s quality detection and classification.

Super-resolution technique can be used to fix the low resolution problem for recognizing the iris at a distance. Two frequency domain super-resolution algorithms, Papoulis-Gerchberg (PG) and Projection onto Convex Sets, are implemented to increase the resolution of iris images. The performance analysis of these algorithms is carried out by extracting Gray Level Co-occurrence Matrix (GLCM) features of super-resoluted iris images. The super-resoluted iris region is normalized, extracted GLCM features and compared with the GLCM features of normalized original iris region. It has been observed that the GLCM features reconstructed images using above algorithm closely matches with that of original iris image. The error between the GLCM features of original normalized and normalized super-resoluted image using Papoulis-Gerchberg is less compared to that of Projection onto Convex Sets.

Speckle noise reduction algorithms are extensively used in the field of ultrasound image analysis with the aim of improving image quality, interpretation and diagnostic accuracy. The absence of noise free ground truth data necessitates the generation of synthetic images with features closely resembling real ultrasound images. In our recent work [1][2], we proposed a framework for generating such images including modelling and speckle artefact simulation techniques based on sampling and interpolation schemes that correspond to real ultrasound image acquisition systems. This paper extends the work by performing a comprehensive quality analysis of the generated synthetic images using second order statistical features. We use Gray Level Co-occurrence Matrix (GLCM) to analyse and compare the texture features with real ultrasound images. Experimental results show a high correlation between the quantitative measures obtained from GLCM features and subjective assessments by clinical experts. The proposed algorithm forms an important stage in the pipeline for generating synthetic ultrasound image database with application in speckle noise removal and evaluation.

A fast algorithm based on gray level co-occurrence matrix and Gabor feature for HEVC screen content coding

To detect non-thinned stands using very-high-resolution imagery, we assessed the relationship between the texture statistics derived from the gray level co-occurrence matrix (GLCM) and the density of Cryptomeria japonica stands. Because it was difficult to make the condition, like stand age and slope, consistent using real images and stands, simulated images were used. The results showed that each texture statistic had a unique pattern of variation, owing to stand density. Moreover, the amount of thinning affected the texture statistics. Because the values of the texture statistics varied according to the amount of it even if the stand density was the same, it was indicated that it was difficult to predict stand density using the texture derived from GLCM. Nevertheless, it should be possible to extract stands that have not been thinned using the texture statistics from very-high-resolution imagery, especially the homogeneity and the angular second moment.

Texture plays a very important role in image retrieval and classification,and texture feature extraction has been a research hotspot. Most present existing texture extraction algorithms can be only used to calculate texture features of gray image. Texture extraction algorithm for color image is very few. Referring to the analytical method of gray level co- occurrence matrix( GLCM),the authors analyzed the influence law of parameters( direction, distance,grayscale,window size) on GLCM texture features of color image. A color image texture feature extraction method( color GLCM,CGLCM) based on GLCM was realized. Through analyzing the influence law of these parameters on four texture features( ASM( angular second moment),Entropy,Contrast,Correlation),a proper parameter value range was given and the CGLCM method was optimized. The results of comparing CGLCM method with GLCM method show that the four texture features calculated with CGLCM method have better robustness and identification capability. These results can provide reference for image retrieval and classification based on texture information.

Relationship of CT Radiomics and Dose Texture to Radiation-Induced Swallow Dysfunction in Head and Neck Cancer

For accurate printing (reproduction), two important appearance attributes to consider are color and gloss. These attributes are related to two topics focused on in this dissertation: spectral reproduction and specular (gloss) printing. In the conventional printing workflow known as the metameric printing workflow, which we use mostly nowadays, high-quality prints -- in terms of colorimetric accuracy -- can be achieved only under a predefined illuminant (i.e. an illuminant that the printing pipeline is adjusted to; e.g. daylight). While this printing workflow is useful and sufficient for many everyday purposes, in some special cases, such as artwork (e.g. painting) reproduction, security printing, accurate industrial color communication and so on, in which accurate reproduction of an original image under a variety of illumination conditions (e.g. daylight, tungsten light, museum light, etc.) is required, metameric reproduction may produce satisfactory results only with luck. Therefore, in these cases, another printing workflow, known as spectral printing pipeline must be used, with the ideal aim of illuminant-invariant match between the original image and the reproduction. In this workflow, the reproduction of spectral raw data (i.e. reflectances in the visible wavelength range), rather than reproduction of colorimetric values (colors) alone (under a predefined illuminant) is taken into account. Due to the limitations of printing systems extant, the reproduction of all reflectances is not possible even with multi-channel (multi-colorant) printers. Therefore, practical strategies are required in order to map non-reproducible reflectances into reproducible spectra and to choose appropriate combinations of printer colorants for the reproduction of the mapped reflectances. For this purpose, an approach called Spatio-Spectral Gamut Mapping and Separation, SSGMS, was proposed, which results in almost artifact-free spectral reproduction under a set of various illuminants. The quality control stage is usually the last stage in any printing pipeline. Nowadays, the quality of the printout is usually controlled only in terms of colorimetric accuracy and common printing artifacts. However, some gloss-related artifacts, such as gloss-differential (inconsistent gloss appearance across an image, caused mostly by variations in deposited ink area coverage on different spots), are ignored, because no strategy to avoid them exists. In order to avoid such gloss-related artifacts and to control the glossiness of the printout locally, three printing strategies were proposed. In general, for perceptually accurate reproduction of color and gloss appearance attributes, understanding the relationship between measured values and perceived magnitudes of these attributes is essential. There has been much research into reproduction of colors within perceptually meaningful color spaces, but little research from the gloss perspective has been carried out. Most of these studies are based on simulated display-based images (mostly with neutral colors) and do not take real objects into account. In this dissertation, three psychophysical experiments were conducted in order to investigate the relationship between measured gloss values (objective quantities) and perceived gloss magnitudes (subjective quantities) using real colored samples printed by the aforementioned proposed printing strategies. These experiments revealed that the relationship mentioned can be explained by a Power function according to Stevens' Power Law, considering almost the entire gloss range. Another psychophysical experiment was also conducted in order to investigate the interrelation between perceived surface gloss and texture, using 2.5D samples printed in two different texture types and with various gloss levels and texture elevations. According to the results of this experiment, different macroscopic texture types and levels (in terms of texture elevation) were found to influence the perceived surface gloss level slightly. No noticeable influence of surface gloss on the perceived texture level was observed, indicating texture constancy regardless of the gloss level printed. The SSGMS approach proposed for the spectral reproduction, the three printing strategies presented for gloss printing, and the results of the psychophysical experiments conducted on gloss printing and appearance can be used to improve the overall print quality in terms of color and gloss reproduction.