Image Segmentation Analysis based on Maximum Entropy Algorithm

The maximum fuzzy entropy algorithm is one of the effective methods of image segmentation, researchers often combine maximum fuzzy entropy and genetic algorithm (GA), but the algorithms have the defects of complexity encoding and unstable search, etc. To improve the algorithms, artificial fish school algorithm (AFSA) is introduced to more rapid optimization of maximum fuzzy entropy, this paper proposes a novel maximum fuzzy entropy image segmentation algorithm based on AFSA (AFSA-based MFEISA). Firstly, the histogram of the image and the probability of each gray level are counted up, and then the multiple threshold integer coding is designed and the maximum fuzzy entropy is converted to the objective function of coding, finally, the maximum fuzzy entropy and its corresponding thresholds are obtained by the improved AFSA and the image is segmented. The experimental results show that the proposed algorithm can achieve better segmentation effect than OTSU algorithm and maximum entropy algorithms, at the same time, it not only has more simple and effective coding scheme and better segmentation effect than the algorithms based on fuzzy entropy and GA, etc, but also it shows better stability and convergence.

This paper focuses on a concrete image segmentation application, which aims at extracting cell regions from cell images taken by the video camera on an auto microscope platform. The segmented results are further used for cancer diagnosis. The application requires that the segmentation method has the ability to fast and accurately extract cell regions from high resolution images. The proposed method is a combination of auto-thresholding method, watershed and morphological method. Furthermore, a novel gradient operator is proposed to improve the accuracy of edge locating. The experimental results demonstrate that our method is robust and efficient. Moreover, for any images with homogeneous background distribution, the proposed method is well applicable.

Image segmentation is the technique of dividing an image into one of kind regions (segments) following some homogeneous criteria. It is an important technique in any image analysis process. Segmentation of medical images like magnetic resonance images, mammogram, cardiac Magnetic resonance (MRIs) images helps in detection and diagnosis of breast tumor, brain tumor, etc. We need a strong and efficient image segmentation method, as most segmentation methods are computationally high priced, and the amount of medical imaging information is growing and very sensitive. In this paper, we delve into different methods available for medical image segmentation with their standpoints. We also compare the two authors’ results based on the parameters True Positive Factor (TPF), True Negative Factor (TNF), and Sum of True Volume Factor (SVTF).

Segmentation task plays an important role in image processing. In this paper, we attempt to extract information from images using texture analysis. Moreover, we propose characterization of pixels in images to define the similarity relation between them. These are based on textural information and findings of shortest paths in the graph representation of images. To reflect effectiveness of our method, we apply it to the benchmark Berkeley image database and we compare it to well-established image segmentation methods (sum and difference histograms for texture classification method, Mean-Shift method and mixture of Gaussian distributions method). The proposed approach achieves the best segmentation results measured by distance-based metrics. The experimental results show that our approach is efficient method for texture analysis and image segmentation.

The hidden Markov random field (HMRF) model is an efficient method for image segmentation. However, it may not accurately segment a poorly defined image like Magnetic Resonance (MR) brain image. The HMRF model uses an initial estimation for tissue segmentation of MR brain image. The initial estimation of an input image has a large role to play to obtain a robust HMRF model. In general, a hard clustering method is used for initial estimation. However, it is not an efficient technique for the segmentation of a complex and irregular shape image like MR brain image. The method of clustering acts as a preprocessing step in improving the performance of HMRF. It aims at producing a set of concise data in the segmentation of brain tissues. In this paper, we propose a new approach to HMRF model, which incorporates the fuzzy C-means (FCM) clustering for the initial estimation of the brain image, which is not found in the literature. This results in efficient segmentation of brain tissues. The results are compared with the spatial FCM clustering algorithm and HMRF model with K-means clustering, using different segmentation evaluation indices. It is seen that the results are better than the other methods.

Synthetic aperture radar (SAR) image segmentation usually involves two crucial issues: suitable speckle noise removing technique and effective image segmentation methodology. Here, an efficient SAR image segmentation method considering both of the two aspects is presented. As for the first issue, the famous nonlocal mean (NLM) filter is introduced in this study to suppress the multiplicative speckle noise in SAR image. Furthermore, to achieve a higher denoising accuracy, the local neighboring pixels in the searching window are projected into a lower dimensional subspace by principal component analysis (PCA). Thus, the nonlocal mean filter is implemented in the subspace. Afterwards, a multi-objective clustering algorithm is proposed using the principals of artificial immune system (AIS) and kernel-induced distance measures. The multi-objective clustering has been shown to discover the data distribution with different characteristics and the kernel methods can improve its robustness to noise and outliers. Experiments demonstrate that the proposed method is able to partition the SAR image robustly and accurately than the conventional approaches.

Image segmentation using modified SLIC and Nyström based spectral clustering

Lettuce image segmentation which based on computer image processing is the premise of non-destructive testing of lettuce quality. The traditional 2-D maximum entropy algorithm has some faults, such as low accuracy of segmentation, slow speed, and poor anti-noise ability. As a result, it leads to the problems of poor image segmentation and low efficiency. An improved 2-D maximum entropy algorithm is presented in this paper. It redistricts segmented regions and furtherly classifies the segmented image pixels with the method of the minimum fuzzy entropy, and reduces the impact of noise points, as a result the image segmentation accuracy is improved. The improved algorithm is used to lettuce object segmentation, and the experimental results show that the improved segmentation algorithm has many advantages compared with the traditional 2-D maximum entropy algorithm, such as less false interference, strong anti-noise ability, good robustness and validity.

Statistical shape modelling is an efficient and robust method for medical image segmentation in computer-aided diagnosis. The key step in building a statistical shape model is to find corresponding landmarks in each instance of a training set. In this paper, a novel landmark correspondence estimation method that uses edge collapse surface simplification and the sphere registration is proposed. All the landmarks are selected and transformed by spherical conformal mapping from the instances of the training set and the associated correspondence are automatically found on the spheres. We applied our method on 21 cases of 3-D right lung shapes. The results of image segmentation experiment indicate that our method has a positive influence on the accuracy of segmentation result.

Antinuclear antibodies (ANAs) testing is the main serological diagnosis screening test for autoimmune diseases. ANAs testing is conducted principally by the indirect immunofluorescence (IIF) on human epithelial cell-substrate (HEp-2) protocol. However, due to its high variability and human subjectivity, there is an insistent need to develop an efficient method for automatic image segmentation and classification. This article develops an automatic segmentation and classification framework based on artificial intelligence (AI) on the ANA images. The Otsu thresholding method and watershed segmentation algorithm are adopted to segment IIF images of cells. Moreover, multiple texture features such as scale-invariant feature transform (SIFT), local binary pattern (LBP), cooccurrence among adjacent LBPs (CoALBP), and rotation invariant cooccurrence among adjacent LBPs (RIC-LBP) are utilized. Firstly, this article adopts traditional machine learning methods such as support vector machine (SVM), k-nearest neighbor algorithm (KNN), and random forest (RF) and then uses ensemble classifier (ECLF) combined with soft voting rules to merge these machine learning methods for classification. The deep learning method InceptionResNetV2 is also utilized to train on the classification of cell images. Eventually, the best accuracy of 0.9269 on the Changsha dataset and 0.9635 on the ICPR 2016 dataset for the traditional methods is obtained by a combination of SIFT and RIC-LBP with the ECLF classifier, and the best accuracy obtained by the InceptionResNetV2 is 0.9465 and 0.9836 separately, which outperforms other schemes.

The digital image segmentation is an open problem that is growing day by day and is attracting the attention of researchers from last few years. Image resolution and their speed has led to the use of thresholding approaches. Image thresholding is simple, easy and effective method for image segmentation. Multi-level image thresholding is a key perspective in several real-time pattern recognition and image processing-based applications. It identifies pixels quickly and effectively in different groups indicating multiple regions in an image. Segmentation of images based on thresholding by using various intelligent optimization techniques with fuzzy entropy is widely utilized for defining thresholds in a better way to use them precisely. In this research, a novel technique for multi-level thresholding is proposed by combining Fuzzy Entropy Type II (FE-TII) with recently developed meta-heuristics named Marine Predators Algorithm (MPA). For achieving optimal thresholds of an image, the maximization of entropy is tedious and consumes a lot of time with an increasing number of thresholds. The MPA method presented is analyzed in context with image segmentation, particularly on thresholds with TII-FE. For this reason, proposed methodology is evaluated using several images along with the distribution of histograms. For analyzing the performance efficiency of the proposed methodology, the results are compared and robustness is tested with efficiency of proposed technique to multi-level image segmentation, several images are used randomly from datasets.

Semantic segmentation, as one of the important branches in the field of computer vision, has made significant progress in recent years. However, in the field of shale exploration, the use of such computer vision techniques has not been widely explored. This study aims to fill this gap by proposing a novel visual base model for shale fracture porosity. Aiming at the unique characteristics of shale electron microscope scanning images (SEM), we introduced a fast Fourier transform module (FFT) into the feature extraction network to effectively suppress the high-frequency noise during the imaging process. By collecting and annotating 91 SEM scan images of voids and cracks in marine shale and marine-continental transitional shale, and conducting comparative experiments between our proposed model and seven classical semantic segmentation models, the results show that our method exhibits obvious advantages in both visual and quantitative metrics(4.99%, 4.35% and 5.46% improvements on the marine shale SEM image dataset and 1.90%, 0.96%, 4.81% improvements on the marine-continental transitional shale SEM image dataset). Notably, our method not only performs well in processing raw images but also maintains high segmentation accuracy after random Gaussian noise and pixel loss processing. This feature provides a new technical approach and solution in the field of shale exploration. In summary, this study has made impressive progress by combining advanced computer vision technology with the field of shale exploration. Our work not only provides an efficient and accurate image segmentation method for shale exploration but also brings useful insights and guidance for research and practice in related fields.

Crop disease leaf image segmentation is a key step in crop disease recognition. In the paper, a segmentation method of crop disease leaf image is proposed to segment leaf image with non-uniform illumination based on maximum entropy and genetic algorithm (GA). The information entropy is regarded as the fitness function of GA, the maximum entropy as convergence criterion of GA. After genetic operation, the optimal threshold is obtained to segment the image of disease leaf. The experimental results of the maize disease leaf image show that the proposed method can select the threshold automatically and efficiently, and has an advantage over the other three algorithms, and also can reserve the main spot features of the original disease leaf image.

In this paper, Maximum Entropy (ME) framework is used to classify text documents. The ME framework has a lot of advantages when compared with other supervised learning algorithms, such as naive Bayes classifier. For example, it makes no inherent conditional independence assumptions between terms. With four labeled data sets, extensive experiments are made to compare the accuracy of ME algorithm with those of naive Bayes and Support Vector Machine (SVM), which are two popular and accurate algorithms in the domain of text classification. The final result is that ME method consistently outperforms naive Bayes and SVM algorithms in accuracy. On the WebKB and Industry Vector data sets, the accuracy of ME algorithm increases from 81.38% to 85.52% and from 85.73% to 89.78% respectively. On the third 20 Newsgroups data set, our experimental result is opposite to that of Nigam et al. For the last Reuters-21578 data set, the accuracy of ME algorithm increases from 94.76% to 96.16%.

Cardiac MRI has experienced a crescent relevance in clinical investigations. The segmentation of myocardial walls is a prerequisite for assessment of cardiac viability. Manual or semi-automatic segmentation of all the images of a subject is tedious, as well as consuming much time from cardiologists. In this study, we selected 23 slices of simulated cardiac MR by MRXCAT and 30 real slices of CINE-MR from 15 patients with Chagas Disease. The proposed pipeline of the fully automatic segmentation consists of three steps: 1. Preprocessing; 2. Automatic Seeds Definition; and 3. Segmentation by Geodesic Active Contour. An experienced cardiologist provided the gold standard annotations of apical, mid-ventricular and basal LV myocardium. We use the following three metrics to validate the proposed pipeline with different signal to noise ratio: Dice similarity (DS), Precision (Pr) and Volumetric Similarity (VS). DS show good agreement between manual segmentation and the automatic segmentation in simulated images with SNR 200, 25, 15 and 5, i.e., 0.98, 0.93, 0.9 and 0.72, respectively. We found moderate agreements between manual segmentation and Snake segmentation in simulated images with SNR 200, 25, 15 and 5, i.e., 0.38, 0.42, 0.34 and 0.39, respectively. The DS, VS, and Pr obtained suggest substantial agreements between the manual and our proposed method segmentation in images of Chagas’s Disease, i.e., 0.8 [0.69–0.87], 0.89 [0.72–0.99] and 0.9 [0.76–0.98] (mean [min–max]), respectively. Our findings suggest that one can use the proposed method in the automatic myocardium segmentation with reliability similar to manual tracing, although completely free of human interaction.