Multi-scale Gaussian Filtering Research Articles

Contrast enhancement method in aero thermal radiation images based on cyclic multi-scale illumination self-similarity and gradient perception regularization.

In aerospace, the effects of thermal radiation severely affect the imaging quality of infrared (IR) detectors, which blur the scene information. Existing methods can effectively remove the intensity bias caused by the thermal radiation effect, but they have limitations in the ability of enhancing contrast and correcting local dense intensity or global dense intensity. To address the limitations, we propose a contrast enhancement method based on cyclic multi-scale illumination self-similarity and gradient perception regularization solver (CMIS-GPR). First, we conceive to correct for intensity bias by amplifying gradient. Specifically, we propose a gradient perception regularization (GPR) solver to correct intensity bias by directly decomposing degraded image into a pair of high contrast images, which do not contain intensity bias and exhibit inverted intensity directions. However, we find that the GPR fails for dense intensity area due to small gradient of the scene. Second, to cope with the cases of dense intensity, we regard the dense intensity bias as the sum of multiple slight intensity bias. Then, we construct a cyclic multi-scale illumination self-similarity (CMIS) model by using multi-scale Gaussian filters and structural similarity prior to removing the dense intensity layer by layer. The result acts as coarse correction for GPR, which does not need to be overly concerned with whether the result has intensity residuals or not. Finally, the coarse corrected result is input to the GPR module to further correct residual intensity bias by enhancing contrast. Extensive experiments in real and simulated data have demonstrated the superiority of the proposed method.

Image enhancement method based on multi algorithm fusion

This research suggests an image enhancement method based on multi algorithm fusion. The illumination component and reflection component are obtained by morphological closure. On the one hand, multiple inputs of the estimated illumination and the corresponding weights are fused by multi-scale fusion technology. On the other hand, space conversion technology is used. Two adjusted images are obtained based on multi-scale Gaussian filter and adaptive brightness enhancement algorithm. Then details are extracted from these two images through PCA fusion strategy. The reflection component is improved significantly after above operations. Finally, combine the illumination and reflection components. Compared with the classical algorithm, our method can simultaneously achieve brightness improvement, naturalness maintenance and contrast enhancement.

Rain Removal Algorithm Based on Retinex in Low Light Automatic Driving Scenario

In the field of automatic driving, clear image is one of the important prerequisites for the decision-making system relying on computer vision to make correct decisions. Rainy days and low illumination environment are two common scenes that seriously affect image quality. Researchers have proposed many effective methods for these two research fields. However, few applications have been studied in the field of automatic driving comprehensively. To solve the problem, a low illumination image enhancement method in rainy days is proposed, which combines the two scenes and can be applied to the field of automatic driving. This algorithm takes good advantage of the fact that raindrops cannot appear in the same frame at different times to eliminate the noise of raindrops in the image .And its main process is to fuse continuous image frames by maximum method through multi-scale Gaussian filtering. Thus, the fused image is used as the illumination map and the original image to be denoised is used as the input of Multi-Scale Retinex(MSR) method.Finally, the reflection image which can be directly applied in automatic driving is obtained.

A Fast Image Sensor System with an Efficient Multi-Scale Gaussian Filtering Circuit

A Fast Image Sensor System with an Efficient Multi-Scale Gaussian Filtering Circuit

Fusion method for infrared and other-type images based on the multi-scale Gaussian filtering and morphological transform

Fusion method for infrared and other-type images based on the multi-scale Gaussian filtering and morphological transform

Extracting method of tidal creek features under heterogeneous background at Yellow River Delta using remotely sensed imagery.

The Yellow River Delta exhibits irregular tidal flat, with tidal creeks that vary in width and experience tidal creek current anisotropy. Given such characteristics, the GF-2 multi-spectral image was selected as the data source to characterize the details of tidal creeks. First, the normali-zed difference water index (NDWI) and OTSU classification were used to delineate the wide tidal creeks. Second, the modified fuzzy C-means clustering algorithm (MFCM) and multi-scale Gaussian matching filter (MGMF) were used to enhance the narrow tidal creeks on the basis of weakening the heterogeneity of tidal flat background. Then, the adaptive threshold segmentation was conducted to delineate the narrow tidal creeks. Finally, the complete tidal creek networks were delineated by combining the wide and narrow tidal creeks. We fully used the spatial resolution and spectral information of the GF-2 image and took into account the geometric features of the linear features, ensuring the spatial continuity of the tidal creek extraction results. In the four tested areas, the Kappa coefficient was greater than 0.8 and the overall accuracy was greater than 97%, which performed better than the maximum likelihood method and support vector machine. The results showed that the proposed method could completely differentiate different types of tidal creeks, with good extraction accuracy and stability. The method could provide scientific reference for real-time dynamic monitoring of tidal creek and its development and evolution.

Characterization of Complex Image Spatial Structures Based on Symmetrical Weibull Distribution Model for Texture Pattern Classification

Texture pattern classification has long been an essential issue in computer vision (CV). However, texture is a kind of perceptual concept of human beings in scene observation or content understanding, which cannot be defined or described clearly in CV. Visually, the visual appearance of the complex spatial structure (CSS) of texture pattern (TP) generally depends on the random organization (or layout) of local homogeneous fragments (LHFs) in the imaged surface. Hence, it is essential to investigate the latent statistical distribution (LSD) behavior of LHFs for distinctive CSS feature characterization to achieve good classification performance. This work presents an image statistical modeling-based TP identification (ISM-TPI) method. It firstly makes a theoretical explanation of the Weibull distribution (WD) behavior of the LHFs of the imaged surface in the imaging process based on the sequential fragmentation theory (SFT), which consequently derives a symmetrical WD model (SWDM) to characterize the LSD of the TP’s SS. Multidirectional and multiscale TP features are then characterized by the SWDM parameters based on the oriented differential operators; in other words, texture images are convolved with multiscale and multidirectional Gaussian derivative filters (GDFs), including the steerable isotropic GDFs (SIGDFs) and the oriented anisotropic GDFs (OAGDFs), for the omnidirectional and multiscale SS detail exhibition with low computational complexity. Finally, SWDM-based TP feature parameters, demonstrated to be directly related to the human vision perception system with significant physical perception meaning, are extracted and used to TP classification with a partial least squares-discriminant analysis- (PLS-DA-) based classifier. The effectiveness of the proposed ISM-TPI method is verified by extensive experiments on three texture image databases. The classification results demonstrate the superiority of the proposed methods over several state-of-the-art TP classification methods.

Analysis of Lung Tumour Detection and Segmentation Using Level Set Method of Active Contour Model

Lung cancer is the most common leading cancer in both men and women all over the world. Accurate image segmentation is an essential image analysis tool that is responsible for partitioning an image into several sub-regions. Active contour model have been widely used for effective image segmentation methods as this model produce sub-regions with continuous boundaries. It is used in the applications such as image analysis, deep learning, computer vision and machine learning. Advanced level set method helps to implement active contours for image segmentation with good boundary detection accuracy. This paper proposes a model based on active contour using level set methods for segmentation of such lung CT images and focusing 3D lesion refinement. The features were determined by applying a multi-scale Gaussian filter. This proposed method is able to detect lung tumors in CT images with intensity, homogeneity and noise. The proposed method uses LIDC-IDRI dataset images to segment accurate 3D lesion of lung tumor CT images.

Multi-Scale Fusion Algorithm Based on Structure Similarity Index Constraint for Infrared Polarization and Intensity Images

At present, infrared polarization and intensity image fusion algorithms often cause fused images to appear fuzzy, making the fused image unable to be processed further. In this paper, a new infrared polarization and intensity image fusion algorithm is proposed, and the fused image is divided into base layer image and detail layer image. The infrared intensity image is used as the base layer image, and the infrared polarization image is decomposed by a multi-scale Gaussian filter and residual method. Next, a structural similarity index is introduced as the constraint of the multi-scale decomposition layers, and the detail layer image is obtained by summing of feature images of infrared polarization image. Finally, the fused image is obtained by the superimposition of the base layer image and detail layer image. The fused image retains all the features of the infrared intensity image and the majority of the polarization image features. The experimental results demonstrated that the fused image obtained by the proposed method performed better in both subjective and objective qualities.

Application of statistical modeling of image spatial structures to automated visual inspection of product quality

Automated visual inspection (AVI) attracts increasing interest in product quality control both academic and industrial communities, particularly on mass production processes, because product qualities of most types can be characterized with their corresponding surface visual attributes. However, many product images in AVI systems are comprised of stochastically accumulative fragmentations (particles) of local homogeneity, without distinctive foregrounds and backgrounds, which brings great challenges in computer analysis, e.g., rice images, fabric images, and consequently, in the intelligent identification of the product qualities. A method of Weibull distribution (WD)-based statistical modeling of image spatial structures (ISSs) to inspect automatically the product quality is presented. The ISS, obtained with multi-scale and omnidirectional Gaussian derivative filters (OGDFs), was demonstrated to be subject to a representative WD model of integral form based on the theory of sequential fragmentation in advance. The WD-model parameters (WD-MPs) of the ISS, with essential human perceptual significance, were extracted as the visual features for product quality identification. The classification performance of the proposed product quality inspection method, namely, the proposed WD-MP features integrated with an introduced spline regression (SR) classifier in this study, was verified on two case studies in the field of the AVI of product quality, namely, automated rice quality classification, and intelligent fabric quality assessment in the corresponding assembly lines of industrial scale. Experimental results indicate that the proposed WD-MP features can effectively characterize the statistical distribution profiles of ISS of complex grain images, piled with a large number of stochastically accumulative fragmentations. The proposed method provides an effective tool for grain image modeling and analysis and consequently lays a foundation for the intelligent perception of product qualities on assembly lines.

Perceptual fusion of infrared and visible images through a hybrid multi-scale decomposition with Gaussian and bilateral filters

In order to achieve perceptually better fusion of infrared (IR) and visible images than conventional pixel-level fusion algorithms based on multi-scale decomposition (MSD), we present a novel multi-scale fusion method based on a hybrid multi-scale decomposition (hybrid-MSD). The proposed hybrid-MSD transform decomposes the source images into multi-scale texture details and edge features by jointly using multi-scale Gaussian and bilateral filters. This transform enables to better capture important multi-scale IR spectral features and separate fine-scale texture details from large-scale edge features. As a result, we can use it to achieve better fusion result for human visual perception than those obtained from conventional multi-scale fusion methods, by injecting the multi-scale IR spectral features into the visible image, while preserving (or properly enhancing) important perceptual cues of the background scenery and details from the visible image. In the decomposed information fusion process, three different combination algorithms are adaptively used in accordance to different scale levels (i.e., the small-scale levels, the large-scale levels and the base level). A regularization parameter is introduced to control the relative amount of IR spectral information injected into the visible image in a soft manner, which can be adjusted further depending on user preferences. Moreover, by testing different settings of the parameter, we demonstrate that injecting a moderate amount of IR spectral information with this parameter can actually make the fused images visually better for some infrared and visible source images. Experimental results of both objective assessment and subjective evaluation by human observers also prove the superiority of the proposed method compared with conventional MSD-based fusion methods.

Cardiac Multi-detector CT Segmentation Based on Multiscale Directional Edge Detector and 3D Level Set.

Extraction of the cardiac surfaces of interest from multi-detector computed tomographic (MDCT) data is a pre-requisite step for cardiac analysis, as well as for image guidance procedures. Most of the existing methods need manual corrections, which is time-consuming. We present a fully automatic segmentation technique for the extraction of the right ventricle, left ventricular endocardium and epicardium from MDCT images. The method consists in a 3D level set surface evolution approach coupled to a new stopping function based on a multiscale directional second derivative Gaussian filter, which is able to stop propagation precisely on the real boundary of the structures of interest. We validated the segmentation method on 18 MDCT volumes from healthy and pathologic subjects using manual segmentation performed by a team of expert radiologists as gold standard. Segmentation errors were assessed for each structure resulting in a surface-to-surface mean error below 0.5 mm and a percentage of surface distance with errors less than 1 mm above 80%. Moreover, in comparison to other segmentation approaches, already proposed in previous work, our method presented an improved accuracy (with surface distance errors less than 1 mm increased of 8-20% for all structures). The obtained results suggest that our approach is accurate and effective for the segmentation of ventricular cavities and myocardium from MDCT images.

A fast color image enhancement algorithm based on Max Intensity Channel

In this paper, we extend image enhancement techniques based on the retinex theory imitating human visual perception of scenes containing high illumination variations. This extension achieves simultaneous dynamic range modification, color consistency, and lightness rendition without multi-scale Gaussian filtering which has a certain halo effect. The reflection component is analyzed based on the illumination and reflection imaging model. A new prior named Max Intensity Channel (MIC) is implemented assuming that the reflections of some points in the scene are very high in at least one color channel. Using this prior, the illumination of the scene is obtained directly by performing a gray-scale closing operation and a fast cross-bilateral filtering on the MIC of the input color image. Consequently, the reflection component of each RGB color channel can be determined from the illumination and reflection imaging model. The proposed algorithm estimates the illumination component which is relatively smooth and maintains the edge details in different regions. A satisfactory color rendition is achieved for a class of images that do not satisfy the gray-world assumption implicit to the theoretical foundation of the retinex. Experiments are carried out to compare the new method with several spatial and transform domain methods. Our results indicate that the new method is superior in enhancement applications, improves computation speed, and performs well for images with high illumination variations than other methods. Further comparisons of images from National Aeronautics and Space Administration and a wearable camera eButton have shown a high performance of the new method with better color restoration and preservation of image details.

선형 MSR을 이용한 역광 영상의 명암비 향상 알고리즘

In this paper, we propose a new algorithm to improve the contrast ratio, to preserve information of bright regions and to maintain the color of backlight image that appears with a great relative contrast. Backlight images of the natural environment have characteristics for difference of local brightness; the overall image contrast improvement is not easy. To improve the contrast of the backlight images, MSR (Multi-Scale Retinex) algorithm using the existing multi-scale Gaussian filter is applied. However, existing multi-scale Gaussian filter involves color distortion and information loss of bright regions due to excessive contrast enhancement and noise because of the brightness improvement of dark regions. Moreover, it also increases computational complexity due to the use of multi-scale Gaussian filter. In order to solve these problems, a linear MSR is performed that reduces the amount of computation from the HSV color space preventing the color distortion and information loss due to excessive contrast enhancement. It can also remove the noise of the dark regions which is occurred due to the improved contrast through edge preserving filter. Through experimental evaluation of the average color difference comparison of CIELAB color space and the visual assessment, we have confirmed excellent performance of the proposed algorithm compared to conventional MSR algorithm.

Detecting optic disc on asians by multiscale gaussian filtering.

The optic disc (OD) is an important anatomical feature in retinal images, and its detection is vital for developing automated screening programs. Currently, there is no algorithm designed to automatically detect the OD in fundus images captured from Asians which are larger and have thicker vessels compared to Caucasians. In this paper, we propose such a method to complement current algorithms using two steps: OD vessel candidate detection and OD vessel candidate matching. The first step is achieved with multiscale Gaussian filtering, scale production, and double thresholding to initially extract the vessels' directional map of various thicknesses. The map is then thinned before another threshold is applied to remove pixels with low intensities. This result forms the OD vessel candidates. In the second step, a Vessels' Directional Matched Filter (VDMF) of various dimensions is applied to the candidates to be matched, and the pixel with the smallest difference designated the OD center. We tested the proposed method on a new database consisting of 402 images from a diabetic retinopathy (DR) screening programme consisting of Asians. The OD center was successfully detected with an accuracy of 99.25% (399/402).

基于色调恒定的MSR图像增强算法

Because of the traditional Retinex enhancement algorithms suffering from the loss of details and color distortion in the enhanced image,a hue preserving image enhancement algorithm is proposed in this work.Firstly,illuminant component estimated using multi-scale Gaussian filter is removed from input image.Then,a new adaptive non-linear function is introduced to modify illumination.Finally,hue is preserved according to the theroy of hue invariant.Experimental results show that the proposed algorithm is more effective in terms of visual effects,and the enhanced image is not only more detail preserving,but the colour is also more natural and without distortion,compared with other methods such as MSRCR.

Pixel-level singular point detection from multi-scale Gaussian filtered orientation field

Singular point, as a global feature, plays an important role in fingerprint recognition. Inconsistent detection of singular points apparently gives an affect to fingerprint alignment, classification, and verification accuracy. This paper proposes a novel approach to pixel-level singular point detection from the orientation field obtained by multi-scale Gaussian filters. Initially, a robust pixel-level orientation field is estimated by a multi-scale averaging framework. Then, candidate singular points in pixel-level are extracted from the complex angular gradient plane derived directly from the pixel-level orientation field. The candidate singular points are finally validated via a cascade framework comprised of nested Poincare indices and local feature-based classification. Experimental results over the FVC 2000 DB2 confirm that the proposed method achieves robust and accurate orientation field estimation and consistent pixel-level singular point detection. The experimental results exhibit a low computational cost with better performance. Thus, the proposed method can be employed in real-time fingerprint recognition.

High-resolution orientation field estimation based on multi-scale Gaussian filter

Orientation field plays the most important role in fingerprint recognition. Proposed in this paper is a novel approach of pixel-wise orientation field estimation using multi-scale Gaussian filter. A three-stage averaging framework in pixel-scale, block-scale, and orientation-scale is developed for handling gradient vectors, coherence data, and orientation vectors, respectively. Experimental results on various FVC datasets show the proposed algorithm achieves accurate orientation field estimation which is robust to local defects, such as scar, low contrast, ridge discontinuity, smudged area, etc. with a low computational cost.

Computer‐aided detection of interstitial abnormalities in chest radiographs using a reference standard based on computed tomography

A computer-aided detection (CAD) system is presented for the localization of interstitial lesions in chest radiographs. The system analyzes the complete lung fields using a two-class supervised pattern classification approach to distinguish between normal texture and texture affected by interstitial lung disease. Analysis is done pixel-wise and produces a probability map for an image where each pixel in the lung fields is assigned a probability of being abnormal. Interstitial lesions are often subtle and ill defined on x-rays and hence difficult to detect, even for expert radiologists. Therefore a new, semiautomatic method is proposed for setting a reference standard for training and evaluating the CAD system. The proposed method employs the fact that interstitial lesions are more distinct on a computed tomography (CT) scan than on a radiograph. Lesion outlines, manually drawn on coronal slices of a CT scan of the same patient, are automatically transformed to corresponding outlines on the chest x-ray, using manually indicated correspondences for a small set of anatomical landmarks. For the texture analysis, local structures are described by means of the multiscale Gaussian filter bank. The system performance is evaluated with ROC analysis on a database of digital chest radiographs containing 44 abnormal and 8 normal cases. The best performance is achieved for the linear discriminant and support vector machine classifiers, with an area under the ROC curve (A(z)) of 0.78. Separate ROC curves are built for classification of abnormalities of different degrees of subtlety versus normal class. Here the best performance in terms of A(z) is 0.90 for differentiation between obviously abnormal and normal pixels. The system is compared with two human observers, an expert chest radiologist and a chest radiologist in training, on evaluation of regions. Each lung field is divided in four regions, and the reference standard and the probability maps are converted into region scores. The system performance does not significantly differ from that of the observers, when the perihilar regions are excluded from evaluation, and reaches A(z) = 0.85 for the system, with A(z) = 0.88 for both observers.