General Adaptive Neighborhood Mathematical Morphology

This paper aims to outline the General Adaptive Neighborhood Image Processing (GANIP) approach [1–3], which has been recently introduced. An intensity image is represented with a set of local neighborhoods defined for each point of the image to be studied. These so-called General Adaptive Neighborhoods (GANs) are simultaneously adaptive with the spatial structures, the analyzing scales and the physical settings of the image to be addressed and/or the human visual system. After a brief theoretical introductory survey, the GANIP approach will be successfully applied on real application examples in image restoration, enhancement and segmentation.

This chapter is focused on spatially adaptive image processing for color images in the context of the General Adaptive Neighborhood Image Processing (GANIP) approach. The GANIP was first defined for gray-tone images and is here extended to color images. A set of local adaptive neighborhoods is defined for each image point, depending on the color intensity function of the image. These adaptive neighborhoods are then used as spatially adaptive operational windows for defining adaptive Choquet filters and adaptive morphological filters. The resulting adaptive operators are successfully applied and compared with the classical operators for image restoration, enhancement and segmentation of color images.

In this paper, we present a general theory of adaptive mathematical morphology (AMM) in the Euclidean space. The proposed theory preserves the notion of a structuring element, which is crucial in the design of geometrical signal and image processing applications. Moreover, we demonstrate the theoretical and practical distinctions between adaptive and spatially-variant mathematical morphology. We provide examples of the use of AMM in various image processing applications, and show the power of the proposed framework in image denoising and segmentation.

A morphological image enhancement method based on the GAN (General Adaptive Neighborhood) structuring elements is proposed for some problems such as low overall contrast, noise and inter-target edge of some remote sensing images. Firstly, a pixel to be processed is selected as a seed point, and an adaptive neighborhood is defined according to the image pixel characteristic and the neighborhood constraint relation to obtain the self-adaptive structuring elements set. A corresponding self-adaptive morphological operation based on the self-adaptive structuring elements set is constructed with reference to the classical morphological operation definition, and the self-adaptive alternative filter is constructed by using the adaptive morphological operation combination so as to realize the enhancement of the remote sensing image. The experimental results show that the method can preserve the accurate positioning of the objects edge while enhancing the image, avoid the loss of information, has better noise removing performance. Compared with the classical morphological filter operator, the single-scale Retinex algorithm and bi-histogram equalization (BHE) algorithm, the contrast ratio and the signal-to-noise ratio of the enhanced image are improved.

Adaptive mathematical morphology – A survey of the field

This paper proposes new adaptive structuring elements in the framework of mathematical morphology. These structuring elements (SEs) have a fixed size but they adapt their shape to the image content by choosing, recursively, similar pixels in gray-scale, with regard to the seed pixel. These new SEs are called region growing structuring elements (REGSEs). Then, we introduce an original method to obtain some features by analyzing the shape of each REGSE. We get a powerful set of operators, which is able to enhance efficiently thin structures in an image. We illustrate the performance of the proposed filters with an application: the detection of cracks in the framework of non-destructive testing. We compare these methods with others, including morphological amoebas and general adaptive neighborhood structuring elements and we see that these operators, based on REGSE, yield the best detection for our application.

The paper presents an adaptive preprocessing method for infrared image sequence. Firstly an adaptive structuring element (SE) construction algorithm is proposed. Secondly, based on morphological top-hat operation, the adaptive background suppression of image sequence is taken. Finally, the image sequence adaptive segmentation is achieved by using morphological opening operation. Some experimental results demonstrate that our proposed method is effective and adaptive for infrared image sequence preprocessing.

In this paper, a novel image denoising method with a morphological opening is proposed. In many image recovery, the regularization has been introduced to prevent overfitting between a recovered image and a noisy observation. In the regularization of an image, the smoothness of the image is assumed. The cost function, which is minimized during the regularization, is defined as a sum of the approximation error term and the smoothness penalty of the image. In morphological image processing, an image is approximated as a union of structuring elements (SEs) by the morphological image opening. In the approximation with the opening, the SE represents the local intensity surface of the image. We hence impose the smoothness penalty on the SE, instead of the recovered image itself, and propose an image opening method with the regularization penalty for the SE. In denoising, the approximation error is minimized under the constraint of the penalty for the SE. In experiments, we show that the proposed filtering method has ability to remove impulsive noises from degraded texture images.

Recovering hyperspectral image (HSI) from mixed noise degradation is a challenging and promising theme in remote sensing, particularly when stripes and deadlines exist in several contiguous bands. This paper proposes a HSI's restoration method making use of adaptive morphological filtering (AMF) and fusing structure information of an auxiliary color image. An adaptive structuring element (ASE) indicating morphological features of each pixel is generated through information fusion, to simultaneously remove the mixed noise and preserve fine spatial structures. This key technology contains three main steps. First, edges are extracted from the auxiliary image exploiting its color information; then, an edge-constraint growing algorithm is used to generate the clustering kernel; finally, the ASE is obtained via goal-guided k-means clustering. The ASE has extensive application value, for it can be an enhancing module for most filters-based restoration methods, to mitigate the structural damage due to the fixed mask. Among these methods, Gaussian filter for preprocessing and majority voting for postprocessing are introduced in this paper as representatives. In addition, the auxiliary image can be both visible image of multisensor and false RGB component of the undamaged bands of the HSI, so it is relatively available. Experiments on simulated and real data sets show obvious effects on denoising and destriping both subjectively and objectively. The advantage of ASE on structure details preserving, compared to conventional approaches, is clearly demonstrated. The application value of the proposed restoration frame and ASE is further proved through the decision-level postprocessing experiments.

The mathematical morphology was applied to high-speed automaton fault diagnosis in this paper, which a new method was proposed to diagnosis high-speed automaton fault based on mathematical morphology and the combination of fuzzy clustering. Take a high-speed automaton fault data in laboratory tests for example; various types were analyzed for the fault signal. The results demonstrated that the combination of mathematical morphology and fuzzy clustering applied on a high-speed automaton can effectively diagnose faults, providing a new way for high-speed automata fault diagnosis.

Mathematical morphology on l-images

An automated mathematical morphology driven algorithm for water body extraction from remotely sensed images

Skull striping is a crucial pre-processing step incorporated in several brain image processing applications. It deals with the removal of non-brain tissues from the brain Magnetic Resonance Imaging (MRI). The skull striping of brain MRI is not a trivial task due to the complex structure of the brain and presence of intensity in homogeneity artifact in MRI. In this paper a novel approach of skull stripping has been presented. The method is composed of adaptive iterative thresholding in addition to Otsu's global thresholding. The global thresholding is followed by analysis and removal of connected components. Finally morphological operations are carried out to obtain the brain mask. The method has been validated using 20 T1w normal coronal brain MRI images of Internet Brain Segmentation Repository (IBSR) dataset, 40 T1w MRI scans of LONI Probabilistic Brain Atlas project (LPBA40) dataset and 77 T1w MRI images from Open Access Series of Imaging Studies (OASIS) dataset. The comparative analysis using standard metrices (such as Dice Similarity Coefficient (DSC), Jacard Index (JI), sensitivity, and specificity) shows that the proposed method performs better than existing skull striping methods for brain MRI.

Accurate visualization of retinal vasculature is essential for the diagnosis of the severity of various vascular diseases. Therefore blood vessel segmentation becomes an indispensable part of computer-based retinal image analysis systems. Retinal fundus images of premature infants are of relatively low contrast, and hence difficult to segment, when compared to adult retina images. An efficient segmentation method to extract the blood vessel network of infant retina images by the fusion of guided filter and mathematical morphology is developed and implemented in this work. It utilizes a novel post-processing technique using modified morphological closing operation which will preserve the thinner vessels in the segmented output. The segmented result can be used for the extraction of relevant features for the diagnosis of Retinopathy of Prematurity.

A novel intelligent denoising method of ecg signals based on wavelet adaptive threshold and mathematical morphology