Marked Pixels Research Articles

Error-tolerant label prior for interactive image segmentation

User interactions are generally utilized to impose the hard constraint and estimate the label prior probability in the interactive image segmentation methods. The conventional interactive approaches cannot work well when the user inputs contain incorrect marks. The existing error tolerance methods mainly focus on the interaction itself and try to eliminate the influence of incorrect hard constraint, which however ignore the label prior estimation. This paper mainly focuses on solving the label prior estimation problem when error marks appear. The prior probability is generally defined as the matching degree between pixels and the cluster centers of marked pixels. Incorrect interaction leads to the formation of incorrect clusters. Therefore, a reliability learning model is constructed in this paper by 1) assigning smaller weighting factors to incorrect clusters, 2) assigning larger weighting factors to correct clusters with higher matching degree. Accurate label prior probability can be obtained by the weighted averaging. Then referring to the existing methods, an error-tolerant segmentation model is designed as a ratio energy function, which can both overcome the hard constraint and the label prior limitation with error marks. Experiments on the challenging Berkeley segmentation data set and Microsoft GrabCut database demonstrate the effectiveness of the proposed method.

Image Marketing Methods for Submarine Manganese Nodule Statistics

In order to improve statistics speed and accuracy of submarine manganese nodule particles, two image marking methods are discussed in this paper. One method is based on binary morphological segmentation depending on corrosion and expansion algorithms, where it marks edge pixels of the particle and regards the area enclosed by these marked pixels as that of manganese nodule particles. The other method is based on substitution-circle segmentation where the crude round nucleus shape feature of a manganese nodule particle is utilized, i.e. a so-called substitution circle is needed to replace a real particle approximately and its area is regarded as that of the manganese nodule particle. Finally Matlab software simulation is used to compare the two methods’ effectiveness. It is shown that statistics accuracy of both the methods is similar, while the second method is more feasible owing to its another advantage of less calculation amount.

A deep learning framework for road marking extraction, classification and completion from mobile laser scanning point clouds

Road markings play a critical role in road traffic safety and are one of the most important elements for guiding autonomous vehicles (AVs). High-Definition (HD) maps with accurate road marking information are very useful for many applications ranging from road maintenance, improving navigation, and prediction of upcoming road situations within AVs. This paper presents a deep learning-based framework for road marking extraction, classification and completion from three-dimensional (3D) mobile laser scanning (MLS) point clouds. Compared with existing road marking extraction methods, which are mostly based on intensity thresholds, our method is less sensitive to data quality. We added the step of road marking completion to further optimize the results. At the extraction stage, a modified U-net model was used to segment road marking pixels to overcome the intensity variation, low contrast and other issues. At the classification stage, a hierarchical classification method by integrating multi-scale clustering with Convolutional Neural Networks (CNN) was developed to classify different types of road markings with considerable differences. At the completion stage, a method based on a Generative Adversarial Network (GAN) was developed to complete small-size road markings first, then followed by completing broken lane lines and adding missing markings using a context-based method. In addition, we built a point cloud road marking dataset to train the deep network model and evaluate our method. The dataset contains urban road and highway MLS data and underground parking lot data acquired by our own assembled backpacked laser scanning system. Our experimental results obtained using the point clouds of different scenes demonstrated that our method is very promising for road marking extraction, classification and completion.

Interactive Stereo Image Segmentation With RGB-D Hybrid Constraints

This letter presents an approach to extracting a target object interactively from a given pair of stereo images. First, a user marks a few parts of the object and background in either of the two views with strokes. The marked pixels are used to generate the prior models of the foreground and background. Second, a graph is constructed with constraints formulated by the priors of foreground/background, similarities between intraview neighbor pixels and correspondences between interview pixels. Third, two segments of the foreground are extracted from the two views by optimization of the graph via graph cut. Traditional methods generally define the priors and neighbor similarities in RGB space. Differently, the proposed method integrates disparity distributions of foreground/background to enrich the priors and defines the similarity metric between neighbor pixels in RGB-D space. The proposed method that utilizes RGB-D hybrid constraints generates stereo segments with accuracies higher than those obtained by state-of-the-art methods.

Kinect depth image enhancement with adaptive joint multi-lateral discrete filters

One of the major problems of Kinect depth image is the existence of noise and holes. Thus, it is necessary to enhance depth images for post processing. In this paper, we propose an adaptive joint bilateral/trilateral filter, considering both the depth image and the aligned colour image, to refine the depth edges and remove the noise. Specifically, the pixels around the common boundary of depth edges and colour edges are taken as unreliable pixels due to the perturbations around the depth edges, then a support region and kernel-width adaptive joint bilateral filter considering the colour edge is applied to refine the marked unreliable pixels and the depth edges. For the depth pixels except unreliable pixels, we apply a kernel-width adaptive joint trilateral filter to remove the noise. Experimental results show that our approach outperforms the compared methods in terms of finer depth edges and noise removal.

Detection of Aβ plaque deposition in MR images based on pixel feature selection and class information in image level.

BackgroundAmyloid β-protein (Aβ) plaque deposition is an important prevention and treatment target for Alzheimer’s disease (AD). As a noninvasive, nonradioactive and highly cost-effective clinical imaging method, magnetic resonance imaging (MRI) is the perfect imaging technology for the clinical diagnosis of AD, but it cannot display the plaque deposition directly. This paper resolves this problem based on pixel feature selection algorithms at the image level.Methods and resultsFirstly, the brain region was segmented from mouse model brain MR images. Secondly, the pixels in the segmented brain region were extracted as a feature vector (features). Thirdly, feature selection was conducted on the extracted features, and the optimal feature subset was obtained. Fourthly, the various optimal feature subsets were obtained by repeating the same processing above. Fifthly, based on the optimal feature subsets, the final optimal feature subset was obtained by voting mechanism. Finally, using the final optimal selected features, the corresponding pixels on the MR images could be found and marked to show the information about Aβ plaque deposition. The MR images and brain histological image slices of twenty-two model mice were used in the experiments. Four feature selection algorithms were used on the MR images and six kinds of classification experiments are conducted, thereby choosing a pixel feature selection algorithm for further study. The experimental results showed that by using the pixel features selected by the algorithms in this paper, the best classification accuracy between early AD and control slides could be as high as 80 %. The selected and marked MR pixels could show information of Aβ plaque deposition without missing most of the Aβ plaque deposition compared with brain histological slice images. The hit rate is over than 90 %.ConclusionsAccording to the experimental results, the proposed detection algorithm of the Aβ plaque deposition based on MR pixel feature selection algorithm is effective. The proposed algorithm can detect the information of the Aβ plaque deposition on MR images and the information can be useful for improving the classification accuracy as assistant MR biomarker. Besides, these findings firstly show the feasibility of detection of the Aβ plaque deposition on MR images and provide reference method for interested relevant researchers in public.

High capacity reversible image watermarking using error expansion and context‐dependent embedding

A novel prediction error expansion-based reversible image watermarking technique is proposed. The proposed approach exploits the variance of neighbouring pixels in a way that the embedding of information bits in each pixel of an image depends on the scale of variation present in its eight neighbouring pixel values. A rhombus predictor is employed in the proposed scheme for its efficacy. In contrast to existing prediction-error expansion based reversible watermarking techniques, the embedding phase of the proposed approach depends only on the context of the pixel to be watermarked. Exploiting the neighbourhood information of each pixel in this way, avoids the need of a location map (LM) or histogram shifting (HS) to distinguish marked pixels from unmarked pixels. Consequently, the proposed approach does not require a large amount of auxiliary information in the form of a LM or HS of unmarked pixels, and thus introduces less distortion, yielding good embedding performance, especially at high capacity.

Ligand-Induced 5-HT3 Receptor Internalization in Enteric Neurons in Rat Ileum

Release of 5-hydroxytryptamine (5-HT) from mucosal enterochromaffin cells and activation of 5-HT(3) receptors (5-HT(3)Rs) on neurons in the gut wall is important in the response of the gut to the luminal environment. Intestinal inflammation is associated with increased levels of mucosal 5-HT. The aims of the study were to determine the following: (1) if 5-HT(3)R undergoes ligand-induced internalization in myenteric neurons, and (2) the effect of long-term increase of mucosal 5-HT on 5-HT(3)Rs. Acute effects of exogenous 5-HT or endogenous release of 5-HT by luminal glucose on cellular localization of 5-HT(3)Rs was determined by immunohistochemistry and confocal microscopy. Treatment with the serotonin re-uptake inhibitor, fluoxetine, for 6 days (20 mg/kg daily orally) was used to increase mucosal 5-HT chronically in rats. Net ileal fluid movement was measured in anesthetized rats by the weight change of a 2.5% agarose cylinder. Acute increases in 5-HT induced by exogenous or endogenous 5-HT decreased 5-HT(3)R immunoreactivity at the neuronal cell membrane by 70% and 60%, respectively. Chronic fluoxetine treatment increased mucosal levels of 5-HT and decreased membrane 5-HT(3)R immunoreactivity by 27%. Net fluid absorption was decreased by a 5-HT(3)R agonist or by luminal glucose; this was attenuated 88% and 99%, respectively, by fluoxetine treatment. Long-term increase in 5-HT in the intestinal mucosa results in increased 5-HT(3)R internalization in myenteric neurons. Chronic changes in mucosal 5-HT may alter gastrointestinal secretory and motor function via ongoing loss of receptor from neuronal membrane, causing a mismatch between luminal content and absorption.

New connected components algorithms and invariant transformations of digital images

In the paper, using the concept of invariant transformation of a digital picture (transformation which preserves topology) an algorithm for calculation of the number of components, the number of holes and Euler characteristics of an (8, 4) digital picture, and an algorithm for determing whether two marked pixels belong to the same black component are considered. By methods of digital simulation and non-parametric statistics some comparative evaluation of the productivity of the proposed algorithm for the calculation of Euler characteristics with similar algorithms is realized.

Robust image watermarking in the spatial domain

The rapid evolution of digital image manipulation and transmission techniques has created a pressing need for the protection of the intellectual property rights on images. A copyright protection method that is based on hiding an ‘invisible’ signal, known as digital watermark, in the image is presented in this paper. Watermark casting is performed in the spatial domain by slightly modifying the intensity of randomly selected image pixels. Watermark detection does not require the existence of the original image and is carried out by comparing the mean intensity value of the marked pixels against that of the pixels not marked. Statistical hypothesis testing is used for this purpose. Pixel modifications can be done in such a way that the watermark is resistant to JPEG compression and lowpass filtering. This is achieved by minimizing the energy content of the watermark signal at higher frequencies while taking into account properties of the human visual system. A variation that generates image dependent watermarks as well as a method to handle geometrical distortions are presented. An extension to color images is also pursued. Experiments on real images verify the effectiveness of the proposed techniques.