Search

In response to the low efficiency and poor quality of current seed optimization algorithms for multi-threshold image segmentation, this paper proposes the utilization of the normal distribution in the cluster distribution mathematical model, the Levy flight mechanism, and the differential evolution algorithm to address the deficiencies of the seed optimization algorithm. The main innovation lies in applying the BBO algorithm to image multi threshold segmentation, providing a new perspective and method for image segmentation tasks. The second significant progress is the combination of Levy flight dynamics and differential evolution algorithm (DEA) to improve the BBO algorithm, thereby enhancing its performance and image segmentation quality. Therefore, a multi-threshold image segmentation model based on the optimized seed optimization algorithm is developed. The experimental results showed that on the function f1, the iteration of the improved seed optimization algorithm was 53, the Generational Distance value was 0.0020, the Inverted Generational Distance value was 0.098, and the Spacing value was 0.051. Compared with the other two algorithms, the improved seed optimization algorithm has better image segmentation performance and clearer image segmentation details. In summary, compared with existing multi-threshold image segmentation methods, the proposed multi-threshold image segmentation model based on the improved seed optimization algorithm has a better image segmentation effect and higher efficiency, can significantly improve the quality of image segmentation, has positive significance for the development of image processing technology, and also provides references for the improvement and application of optimization algorithms. [ABSTRACT FROM AUTHOR]

In recent years, UNet and its derivative networks have gained widespread recognition as major methods of medical image segmentation. However, networks like UNet often struggle with Point-of-Care (POC) healthcare applications due to their high number of parameters and computational complexity. To tackle these challenges, this paper introduces an efficient network designed for medical image segmentation called MCU-Net, which leverages ConvNeXt to enhance UNet. 1) Based on ConvNeXt, MCU-Net proposes the MCU Block, which employs techniques such as large kernel convolution, depth-wise separable convolution, and an inverted bottleneck design. To ensure stable segmentation performance, it also integrates global response normalization (GRN) layers and Gaussian Error Linear Unit (GELU) activation functions. 2) Additionally, MCU-Net introduces an enhanced Multi-Scale Convolution Attention (MSCA) module after the original UNet's skip connections, emphasizing medical image features and capturing semantic insights across multiple scales. 3)The downsampling process replaces pooling layers with convolutions, and both upsampling and downsampling stages incorporate batch normalization (BN) layers to enhance model stability during training. The experimental results demonstrate that MCU-Net, with a parameter count of 2.19 million and computational complexity of 19.73 FLOPs, outperforms other segmentation models. The overall performance of MCU-Net in medical image segmentation surpasses that of other models, achieving a Dice score of 91.8% and mIoU of 84.7% on the GlaS dataset. When compared to UNet on the BUSI dataset, MCU-Net shows an improvement of 2% in Dice and 2.9% in mIoU. [ABSTRACT FROM AUTHOR]

The key step in the intelligence of tongue diagnosis is the segmentation of the tongue image, and the accuracy of the segmented edges has a significant impact on the subsequent medical judgment. Deep learning can predict the class of pixel points to achieve pixel-level segmentation of images, so it can be used to handle tongue segmentation tasks. However, different models have different segmentation effects, and they did not learn the connection between space and channels, resulting in inaccurate tongue segmentation. This paper first discussed the choice of model and loss function and then compared the results of different options to find the better model. Associating the red feature of the tongue is very conducive to segmentation as a feature, this paper tested many methods to try to get the color features of the original image to be paid attention to. Finally, this paper proposed an improved Encoder-Decoder network model to solve the problem based on the results. Start with Resnet as the backbone network, then introduce the U-Net model, and then we fused the attention layer, obtained from the source image through convolution and CBAM attention mechanism, and the feature layer obtained from the last upsampling in U-Net. Experimental results show that: The new, improved algorithm results are 2-3 percentage points higher than the popular algorithm, making it more suitable for tongue segmentation tasks. [ABSTRACT FROM AUTHOR]

The traditional fuzzy C-means clustering technology only considers one performance Angle of image segmentation process when processing data, resulting in low accuracy of image segmentation. In this paper, the traditional FCM algorithm is analyzed, and the low clustering accuracy, noise interference and lack of flexibility and other problems are fully considered from the relationship between parameter components, non-local spatial information elements and noise sensitivity. Firstly, a distance calculation method based on robust statistics theory is proposed, which can deal with abnormal noise stably. Secondly, based on the extreme learning machine theory, the non-local spatial information coefficient is introduced to improve the identification ability of the influence factors. This method not only guarantees the anti-noise performance of the algorithm, but also preserves the image data, improving the iteration efficiency and segmentation accuracy of the algorithm. The test results show that the accuracy of the improved C-means clustering algorithm for image segmentation is 95.5%, which is compared with the traditional C-means clustering technique and other optimization algorithms. [ABSTRACT FROM AUTHOR]

Multilevel thresholding segmentation of color images plays an important role in many fields. The pivotal procedure of this technique is determining the specific threshold of the images. In this paper, an improved mayfly algorithm (IMA)-based color image segmentation method is proposed. Tent mapping initializes the female mayfly population to increase population diversity. Lévy flight is introduced in the wedding dance iterative formulation to make IMA jump from the local optimal solution quickly. Two nonlinear coefficients were designed to speed up the convergence of the algorithm. To better verify the effectiveness, eight benchmark functions are used to test the performance of IMA. The average fitness value, standard deviation, and Wilcoxon rank sum test are used as evaluation metrics. The results show that IMA outperforms the comparison algorithm in terms of search accuracy. Furthermore, Kapur entropy is used as the fitness function of IMA to determine the segmentation threshold. 10 Berkeley images are segmented. The best fitness value, peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and other indexes are used to evaluate the effect of segmented images. The results show that the IMA segmentation method improves the segmentation accuracy of color images and obtains higher quality segmented images. [ABSTRACT FROM AUTHOR]

The application of video and image segmentation is carried out from the aspects of improving the accuracy of segmentation and reducing the calculation time, but the segmentation result is affected by the initial curve position, so this paper proposes a new method. As an important part of the Internet, pictures are usually used to help visitors understand. The image contains a lot of deep-level video information, which is an important basis for video content retrieval and data analysis. In this paper, combining the texture and edge features of the image in the process of text location, a multi-scale Gabor filter bank is proposed to transform the original image, and a priori knowledge of the text region is used to process the non-text object in the transform result. In the part of extracting text from pictures, and improved TF-IDF algorithm, BC-TF-IDF algorithm, is proposed to extract text from pictures. To ensure the integrity of the extracted image, the Sobel algorithm is used to process the image in the edge extraction step. Finally, the above method is applied to the Weibo network, and a system of collecting and recognizing the character content of the Weibo image is set up, which completes the function of collecting and gradually recognizing the Weibo image, and verifies the proposed localization method. [ABSTRACT FROM AUTHOR]

The purpose of image segmentation is to select the target region from the existing image, which is the core technology for image understanding, description and analysis. When faced with some complicated problems, the image segmentation effect of the traditional method is often unsatisfactory. As a branch of the swarm intelligence optimization algorithm, Particle Swarm Optimization (PSO) provides a new power and direction for the development of image segmentation. However, the algorithm has a large probability of loss of particle diversity in the late stage, which makes the algorithm converge prematurely. Therefore, the purpose of this paper is to improve the problem existing in the PSO algorithm and apply the improved algorithm in image segmentation. In this paper, the whole population of PSO algorithm is divided into multiple sub-populations and co-evolution. The mutation operation from the genetic algorithm is introduced at the same time. The worst sub-population is mutated according to the mutation probability. The larger inertia factor is selected to speed the particles. Update, and then carry out simulation experiments on some classical test functions. Finally, combined with the improved PSO algorithm and fuzzy C-means clustering algorithm (FCM), the fuzzy clustering validity index is introduced, and the blood cell image is segmented by the algorithm. The experimental results show that the algorithm can find a reasonable number of cluster center segmentation categories and efficiently perform adaptive segmentation of images. [ABSTRACT FROM AUTHOR]

Adding spatial penalty to fuzzy C-means (FCM) model is an important way to reduce the influence of noise in image segmentation. However, these improved algorithms easily cause segmentation failures when the image has the characteristics of unequal cluster sizes. Besides, they often fall into local optimal solutions if the initial cluster centers are improper. This paper presents a noise robust hybrid algorithm for segmenting image with unequal cluster sizes based on chaotic crow search algorithm and improved fuzzy c-means to overcome the above defects. Firstly, each size of clusters is integrated into the objective function of noise detecting fuzzy c-means algorithm (NDFCM), which can reduces the contribution of larger clusters to objective function and then the new membership degree and cluster centers are deduced. Secondly, a new expression called compactness, representing the pixel distribution of each cluster, is introduced into the iteration process of clustering. Thirdly, we use two- paths to seek the optimal solutions in each step of iteration: one path is produced by the chaotic crow search algorithm and the other is originated by gradient method. Furthermore, the better solutions of the two-paths go to next generation until the end of the iteration. Finally, the experiments on the synthetic and non–destructive testing (NDT) images show that the proposed algorithm behaves well in noise robustness and segmentation performance. [ABSTRACT FROM AUTHOR]

Image segmentation plays an important role in many fields such as computer vision, pattern recognition, machine learning and so on. In recent years, many variants of standard fuzzy C-means (FCM) algorithm have been proposed to explore how to remove noise and reduce uncertainty. In fact, there are uncertainty on the boundary between different patches in images. Considering that hesitant fuzzy set is a useful tool to deal with uncertainty, in this paper, we merge hesitant fuzzy set with fuzzy C-means algorithm, introduce a new kind of method of fuzzification and defuzzification of image and the distance measure between hesitant fuzzy elements of pixels, present a method to establish hesitant membership degree of hesitant fuzzy element, and propose hesitant fuzzy C-means (HFCM) algorithm. Finally, we compare our proposed HFCM algorithm with some existing fuzzy C-means (FCM) algorithms, and apply HFCM algorithm in natural image, BSDS dataset image, different size images and multi-attribute decision making. These numerical examples illustrate the validity and applicability of our proposed algorithm including its comprehensive performance, reducing running time and almost without loss of accuracy. [ABSTRACT FROM AUTHOR]

Multi-view subspace clustering arises in many computer visional tasks such as object recognition and image segmentation. The basic idea is to measure the same instance with multiple views. In this paper, we proposed two centralized joint sparse representation models, namely, Centralized Global Joint Sparse Representation (CGJSR) and Centralized Local Joint Sparse Representation (CLJSR) for multi-view subspace clustering. CGJSR and CLJSR force the concatenated representation matrix of all views and the representation matrix of each view to be sparse respectively. Both CGJSR and CLJSR allow the sparse coefficient matrix to approach a unified latent structure with an acceptable error. Noises and outliers regularization terms are included in CGJSR and CLJSR to reduce the influence of noises and outliers. Related optimization problems are solved using the alternating direction method of multipliers. Compared with seven state-of-the-art multi-view clustering algorithms, our proposed algorithms can achieve better or comparable results on four real-world datasets. [ABSTRACT FROM AUTHOR]

In brain medical imaging, magnetic resonance is an important and effective means to support the computer aided diagnosis. Notwithstanding, inherent conditions such as atypical information, artifacts and vaguely delimited boundaries between existing tissues can hinder the segmentation task. A popular method to carry out this process is through Fuzzy C-Means algorithm, as well as its variants. These include the Intuitionistic Fuzzy C-Means algorithm, which is found suitable for brain magnetic resonance image segmentation, since it incorporates the advantage of intuitionistic fuzzy sets theory to handle the uncertainty. Most clustering algorithms depend of customized hand-crafted features as well as an appropriate initialization process; this last aspect is a mandatory pre-requisite for convergence of the algorithm. In order to develop the brain image segmentation, in this paper we enhance the Intuitionistic Fuzzy C-Means performance by means of Robust Statistics. Explicitly, a non-parametric German-McClure Redescending M-Estimator is used at the initialization and clustering stages, it behaves such as a robust location estimator when the centroid vector is computed, and as a weighting when the membership matrix is updated. The fusion of both paradigms allows us to propose a clustering algorithm that develops efficiently the segmentation of magnetic resonance images, with the important merit of reduce the iteration required to converge. The robustness and effectiveness of this proposal is verified by experiments on simulated and real brain images. [ABSTRACT FROM AUTHOR]

As one of the most popular image segmentation techniques, multi-level thresholding is widely used. Much work has been done to improve the efficiency of multi-level thresholding, but satisfied affect is hard to achieve. In this paper, a multi-level image segmentation method using between-class variance (Otsu) based on improved bat algorithm (DWBA) with dynamically adjusting inertia weight and velocity stratification theory is proposed. DWBA algorithm has strong global search ability at the beginning. Then, the local search capability is enhanced with numbers increasing of iterations. More importantly, the performance of DWBA further improved, because bats with different fitness values have diverse velocities. Furthermore, an improved local search strategy is proposed to avoid the current best solution being replaced during iterations. The experimental results established that the proposed DWBA algorithm obtains better outcome than other algorithms. [ABSTRACT FROM AUTHOR]

Interval valued fuzzy c-means (IVFCM) clustering algorithm is one of effective clustering algorithms. When applied to image segmentation, IVFCM includes three problems as follows: (1) It is sensitive to the initial values of algorithm and may easily fall into the local optimal. (2) The algorithm is sensitive to the image noise and cannot obtain the satisfying performance on images corrupted by noise. (3) It always performs image segmentation under one objective function, therefore it cannot meet multiple practical needs. In order to address these problems, a multi-objective interval valued fuzzy clustering algorithm is proposed in this paper. This method constructs two novel interval valued fuzzy fitness functions which utilize the non-local spatial information of the image. Then a new mutation operator combining the interval valued fuzzy information of image is designed. Furthermore, an effective interval valued fuzzy cluster validity index using the non-local spatial information of image is presented to select a single solution from the non-dominated solution set. Experimental results show that the proposed method behaves well in noisy image segmentation. [ABSTRACT FROM AUTHOR]

Fuzzy c-means (FCM) has been considered as an effective algorithm for image segmentation. However, it still suffers from two problems: one is insufficient robustness to image noise, and the other is the Euclidean distance in FCM, which is sensitive to outliers. In this paper, we propose two new algorithms, generalized FCM (GFCM) and hierarchical FCM (HFCM), to solve these two problems. Traditional FCM can be considered as a linear combination of membership and distance from the expression of its mathematical formula. GFCM is generated by applying generalized mean on these two items. We impose generalized mean on membership to incorporate local spatial information and cluster information, and on distance function to incorporate local spatial information and image intensity value. Thus, our GFCM is more robust to image noise with the spatial constraints: the generalized mean. To solve the second problem caused by Euclidean distance (l2 norm), we introduce a more flexibility function which considers the distance function itself as a sub-FCM. Furthermore, the sub-FCM distance function in HFCM is general and flexible enough to deal with non-Euclidean data. Finally, we combine these two algorithms to introduce a new generalized hierarchical FCM (GHFCM). Experimental results demonstrate the improved robustness and effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Compression and transmission of compound images are essential processes in real time applications where there is a necessity that the compression technique should attain high compression ratio, low complexity, high PSNR value and a required level of security. This paper proposes a novel method for block-based compound image compression. The pictorial blocks and text/graphics blocks are separated from the compound image. The pictorial blocks are compressed using discrete Haar wavelet transformation and text/graphics colors are mapped to primary colors using color quantization algorithm and the resulting index values are then compressed using the lossless Huffman coding technique. The compressed image is then encrypted using an Advanced Encryption Standard algorithm which ensures that the transmission is fast and highly secured. Experimental results conclude that the proposed algorithm provides better results like low complexity, high compression ratio and a high PSNR value than most of the other image compression techniques. [ABSTRACT FROM AUTHOR]