Local Pixel Values Research Articles

A Method for Sorting High-Quality Fresh Sichuan Pepper Based on a Multi-Domain Multi-Scale Feature Fusion Algorithm.

Post-harvest selection of high-quality Sichuan pepper is a critical step in the production process. To achieve this, a visual system needs to analyze Sichuan pepper with varying postures and maturity levels. To quickly and accurately sort high-quality fresh Sichuan pepper, this study proposes a multi-scale frequency domain feature fusion module (MSF3M) and a multi-scale dual-domain feature fusion module (MS-DFFM) to construct a multi-scale, multi-domain fusion algorithm for feature fusion of Sichuan pepper images. The MultiDomain YOLOv8 Model network is then built to segment and classify the target Sichuan pepper, distinguishing the maturity level of individual Sichuan peppercorns. A selection method based on the average local pixel value difference is proposed for sorting high-quality fresh Sichuan pepper. Experimental results show that the MultiDomain YOLOv8-seg achieves an mAP50 of 88.8% for the segmentation of fresh Sichuan pepper, with a model size of only 5.84 MB. The MultiDomain YOLOv8-cls excels in Sichuan pepper maturity classification, with an accuracy of 98.34%. Compared to the YOLOv8 baseline model, the MultiDomain YOLOv8 model offers higher accuracy and a more lightweight structure, making it highly effective in reducing misjudgments and enhancing post-harvest processing efficiency in agricultural applications, ultimately increasing producer profits.

Application of machine learning standardized integral area algorithm in measuring the scoliosis

This study was to develop a computer vision evaluation method to automatically measure the degree of scoliosis based on the machine learning algorithm. For the X-ray images of 204 patients with idiopathic scoliosis who underwent full-spine radiography, histogram equalization of original image was performed before a flipping method was used to magnify asymmetric elements, search for the global maximum pixel value in each line, and scan local maximal pixel value, with the intersection set of two point sets being regarded as candidate anchor points. All fine anchors were fitted with cubic spline algorithm to obtain the approximate curve of the spine, and the degree of scoliosis was measured by the standardized integral area. All measured data were analyzed. In manual measurement, the Cobb angle was 11.70–25.00 (20.15 ± 3.60), 25.20–44.70 (33.89 ± 5.41), and 45.10–49.40 (46.98 ± 1.25) in the mild, moderate and severe scoliosis group, respectively, whereas the value for the standardized integral area algorithm was 0.072–0.298 (0.185 ± 0.040), 0.100–0.399 (0.245 ± 0.050), and 0.246–0.901 (0.349 ± 0.181) in the mild, moderate and severe scoliosis group, respectively. Correlation analysis between the manual measurement of the Cobb angle and the evaluation of the standardized integral area algorithm demonstrated the Spearman correlation coefficient r = 0.643 (P < 0.001). There was a positive correlation between the manual measurement of the Cobb angle and the measurement of the standardized integral area value. Two methods had good consistency in evaluating the degree of scoliosis. ROC curve analysis of the standardized integral area algorithm to measure the degree of scoliosis showed he cutoff value of the standardized integral area algorithm was 0.20 for the moderate scoliosis with an AUC of 0.865, sensitivity 0.907, specificity 0.635, accuracy 0.779, positive prediction value 0.737 and negative prediction value 0.859, and the cutoff value of the standardized integral area algorithm was 0.40 for the severe scoliosis with an AUC of 0.873, sensitivity 0.188, specificity 1.00, accuracy 0.936, positive prediction value 1 and a negative prediction value 0.935. Using the standardized integral area as an independent variable and the Cobb angle as a dependent variable, a linear regression equation was established as Cobb angle = 13.36 + 70.54 × Standardized area, the model has statistical significance. In conclusion, the integrated area algorithm method of machine learning can quickly and efficiently assess the degree of scoliosis and is suitable for screening the degree of scoliosis in a large dataset as a useful supplement to the fine measurement of scoliosis Cobb angle.

A novel feature descriptor based coral image classification using extreme learning machine with ameliorated chimp optimization algorithm

Coral reefs are one of the most biodiverse and productive ecosystems on earth, which acts as a habitat and provides food to a wide range of organisms. The coral reefs protect the coasts from storms, waves, and erosion. Unfortunately, this ecosystem is under threat by various natural and manmade factors, including pollution, ocean acidification, sedimentation, and climate change. The marine ecosystems need to be monitored regularly in order to minimize the aforementioned threats. Hence, an automated classification system is necessary for the classification of coral images. In this paper, a novel method called “Systematic Local Directional Encoded Derivative Binary Pattern” (SLDEDBP) is proposed to extract the coral reef feature values. In this descriptor, the feature values are derived using two phases: Local Directional Derivative Binary Pattern (LDDBP) and Systematic Local Discriminate Binary pattern (SLDBP). In the LDDBP phase, the eight directional kirsch mask is employed in each 3 × 3 neighbourhood window to extract the directional edge response of an image. Then, in the SLDBP phase, the local neighbourhood pixel values are divided into four non-overlapping groups of Z, M, TZ (Tilted Z), and TM (Tilted M) to extract unique features values by considering the centre pixel value in a 3 × 3 neighbourhood window. Finally, the derived feature values of LDDBP and SLDBP are concatenated to procedure final discriminate feature values. The extracted feature values of coral images are applied to a hybridized method called Ameliorated Chimp Optimization Algorithm with Extreme Learning Machine Classifier (AChOA-ELM) to optimize the relative weight of the input and biases of neural networks. This avoids overfitting and makes the model more generalized and robust. The proposed AChOA-ELM method performance is evaluated using different databases of coral and standard images. The reliability of the proposed model has been evaluated utilizing the model performance metrics, accuracy (ACC), true positive rate (TPR), true negative rate (TNR), false-positive rate (FPR), precision (PRC), positive predictive value (PPV), and F1 score. The findings reveal that the proposed hybrid AChOA-ELM achieves greater classification accuracy with a faster coverage rate than other existing methods. In the presence of the image data augmentation technique, the EILAT2 dataset achieves the highest classification accuracy of 99%, whereas MLC dataset achieves the lowest classification accuracy of 94.86%.

Block-Greedy and CNN Based Underwater Image Dehazing for Novel Depth Estimation and Optimal Ambient Light

A lack of adequate consideration of underwater image enhancement gives room for more research into the field. The global background light has not been adequately addressed amid the presence of backscattering. This paper presents a technique based on pixel differences between global and local patches in scene depth estimation. The pixel variance is based on green and red, green and blue, and red and blue channels besides the absolute mean intensity functions. The global background light is extracted based on a moving average of the impact of suspended light and the brightest pixels within the image color channels. We introduce the block-greedy algorithm in a novel Convolutional Neural Network (CNN) proposed to normalize different color channels’ attenuation ratios and select regions with the lowest variance. We address the discontinuity associated with underwater images by transforming both local and global pixel values. We minimize energy in the proposed CNN via a novel Markov random field to smooth edges and improve the final underwater image features. A comparison of the performance of the proposed technique against existing state-of-the-art algorithms using entropy, Underwater Color Image Quality Evaluation (UCIQE), Underwater Image Quality Measure (UIQM), Underwater Image Colorfulness Measure (UICM), and Underwater Image Sharpness Measure (UISM) indicate better performance of the proposed approach in terms of average and consistency. As it concerns to averagely, UICM has higher values in the technique than the reference methods, which explainsits higher color balance. The μ values of UCIQE, UISM, and UICM of the proposed method supersede those of the existing techniques. The proposed noted a percent improvement of 0.4%, 4.8%, 9.7%, 5.1% and 7.2% in entropy, UCIQE, UIQM, UICM and UISM respectively compared to the best existing techniques. Consequently, dehazed images have sharp, colorful, and clear features in most images when compared to those resulting from the existing state-of-the-art methods. Stable σ values explain the consistency in visual analysis in terms of sharpness of color and clarity of features in most of the proposed image results when compared with reference methods. Our own assessment shows that only weakness of the proposed technique is that it only applies to underwater images. Future research could seek to establish edge strengthening without color saturation enhancement.

Cognitive vision inspired object segmentation metric and loss function

Object segmentation (OS) technology is a research hotspot in computer vision, and it has a wide range of applications in many fields. Cognitive vision studies have shown that human vision is highly sensitive to both global information and local details in scenes.To this end, we design a novel, efficient, and easy-to-use enhanced-alignment measure ($E_\\xi$) for evaluating the performance of the OS model.$E_\\xi$ combines local pixel values with the image-level mean value, jointly evaluates the image-/pixel-level similarity between a segmentation result and a ground-truth (GT) result.Extensive experiments on the four popular benchmarks via five meta-measures, i.e., application ranking, demoting generic, denying noise, human ranking, andrecognizing GT, show significant relative improvement compared with existing widely-adopted evaluation metrics such as IoU and $F_\\beta$.By using the weighted binary cross-entropy loss, the enhanced-alignment loss, and the weighted IoU loss, we further design a hybrid loss function (Hybrid-$E_{\\rm~loss}$) to guide the network to learn pixel-, object- and image-level features.Qualitative and quantitative results show further improvement in terms of accuracy when using our hybrid loss function in three different OS tasks.

Sugarcane stem nodes based on the maximum value points of the vertical projection function

ABSTRACT: In order to solve the problem that the stem nodes are difficult to identify in the process of sugarcane seed automatic cutting, a method of identifying the stem nodes of sugarcane based on the extreme points of vertical projection function is proposed in this paper. Firstly, in order to reduce the influence of light on image processing, the RGB color image is converted to HSI color image, and the S component image of the HSI color space is extracted as a research object. Then, the S component image is binarized by the Otsu method, the hole of the binary image is filled by morphology closing algorithm, and the sugarcane and the background are initially separated by the horizontal projection map of the binary image. Finally, the position of sugarcane stem is preliminarily determined by continuously taking the derivative of the vertical projection function of the binary image, and the sum of the local pixel value of the suspicious pixel column is compared to further determine the sugarcane stem node. The experimental results showed that the recognition rate of single stem node is 100%, and the standard deviation is less than 1.1 mm. The accuracy of simultaneous identification of double stem nodes is 98%, and the standard deviation is less than 1.7 mm. The accuracy of simultaneous identification of the three stem nodes is 95%, and the standard deviation is less than 2.2 mm. Compared with the other methods introduced in this paper, the proposed method has higher recognition and accuracy.

Learning multi-scale and multi-order features from 3D local differences for visual smoke recognition

To overcome shortages of conventional hand-crafted features, we propose a learning based feature extraction method for visual smoke recognition. We first slide a 3D sampling window in the scale space of images to densely compute 3D local differences across scales, and learn a projection matrix from all 3D local differences of training images. Then the projection matrix is used to transform 3D local differences of each image to generate feature maps, which naturally contain both local and holistic information. To further generate robust descriptors, we process these feature maps in two encoding ways: within-map and between-map encodings. The within-map encoding way generates an Local Binary Pattern (LBP) map for each feature map, while the between-map way encodes pixel-wise values across different feature maps to generate only one LBP map, denoted as a cross-sign map, for every eight feature maps. To make the two encoding ways have the same contributions, we weight the histograms of cross-sign maps and LBP maps with different coefficients. Each computational layer includes calculation of 3D local differences, learning of projection matrices, and encoding of projected features. Several computational layers can be stacked on top of each other to present a hierarchical structure to extract multi-order and high-level features. Subsequent layers carry higher order information on variations of local pixel values, which is more discriminative but also more sensitive to noise. To make a tradeoff between discriminative ability and noise suppression, Taylor-like coefficients are proposed to weight histograms computed from different computational layers. Experimental results demonstrate that the proposed method achieves better performance than most existing handcrafted methods and learning based feature extraction methods on both smoke recognition and texture classification.

Bubble Behaviors of Large Cohesive Particles in a 2D Fluidized Bed

Fluidization hydrodynamics is greatly influenced by interparticle cohesive forces. In this paper, we study the bubbling behaviors of cohesive Geldart B particles in a 2D fluidized bed, using the “polymer coating” approach to introduce cohesive force. The effect of cohesive force on bubbles can be differentiated into two regimes: (i) by increasing the cohesive force within a low level, the bubble number increases, while the bubble fraction and bubble diameter decrease; (ii) when the force is large enough to cause the particles to adhere to the side walls of the bed, the bubble numbers and the bed expansion sharply decrease. With the increasing cohesive force, the bubble shape changes from roughly circular shape, to oblong shape, leading to the “short pass” of fluidizing gas through the bed. Finally, we analyzed the switching frequency and standard deviation of local pixel values to characterize the bubble dynamics.

Automatic Classification Of Medical X-Ray Images

Image representation is one of the major aspects of automatic classification algorithms. In this paper, different feature extraction techniques have been utilized to represent medical X-ray images. They are categorized into two groups; (i) low-level image representation such as Gray Level Co-occurrence Matrix(GLCM), Canny Edge Operator, Local Binary Pattern(LBP) , pixel value, and (ii) local patch-based image representation such as Bag of Words (BoW). These features have been exploited in different algorithms for automatic classification of medical Xray images. We then analyzed the classification performance obtained with regard to the image representation techniques used. These experiments were evaluated on ImageCLEF 2007 database consists of 11000 medical X-ray images with 116 classes. Experimental results showed the classification performance obtained by exploiting LBP and BoW outperformed the other algorithms with respect to the image representation techniques used.

A Local Pixel Distribution Based Self-adaptive Median Filter for Removal of Pepper and Salt Noise

As we know, for any image, the intensive function varies distinctly in the whole domain and fluctuates little in a small area or a special direction. We name this local pixel value distribution information as priori knowledge. After detecting the salt and pepper noise pixels, the self-adaptive median filter is use to find a suitable window containing more non-noise pixels. By applying the priori knowledge to these non-noise pixels, we deduce maximum likelihood value of the target pixel. Simulations with the restoring attention and peak signal-noise ratio are carried out to demonstrate that the proposed algorithm have superior performance to the existing classical methods.

Bilateral mammographic density asymmetry and breast cancer risk: A preliminary assessment

To improve efficacy of breast cancer screening and prevention programs, it requires a risk assessment model with high discriminatory power. This study aimed to assess classification performance of using computed bilateral mammographic density asymmetry to predict risk of individual women developing breast cancer in near-term. The database includes 451 cases with multiple screening mammography examinations. The first (baseline) examinations of all case were interpreted negative. In the next sequential examinations, 187 cases developed cancer or surgically excised high-risk lesions, 155 remained negative (not-recalled), and 109 were recalled benign cases. From each of two bilateral cranio-caudal view images acquired from the baseline examination, we computed two features of average pixel value and local pixel value fluctuation. We then computed mean and difference of each feature computed from two images. When applying the computed features and other two risk factors (woman's age and subjectively rated mammographic density) to predict risk of cancer development, areas under receiver operating characteristic curves (AUC) were computed to evaluate the discriminatory/classification performance. The AUCs are 0.633±0.030, 0.535±0.036, 0.567±0.031, and 0.719±0.027 when using woman's age, subjectively rated, computed mean and asymmetry of mammographic density, to classify between two groups of cancer-verified and negative cases, respectively. When using an equal-weighted fusion method to combine woman's age and computed density asymmetry, AUC increased to 0.761±0.025 (p<0.05). The study demonstrated that bilateral mammographic density asymmetry could be a significantly stronger risk factor associated to the risk of women developing breast cancer in near-term than woman's age and assessed mean mammographic density.

Comparison analysis of nonlinear segmentation methods for selected wood features in sugar maple

Two classification methods, a feed-forward neural network and a fuzzy logic algorithm, were used for the automatic identification of CT images for selected wood features in sugar maple, one of the most important hardwoods in eastern Canada. Three wood characteristics were selected for automatic identification together with the background as a default. Local features, such as position and local pixel values were used as the neural networks inputs. The fuzzy sets consisted of four different possible pixel values and four possible distances from the center of the log. The fuzzy method used in this study was of the Mamdani type. Five sugar maple logs were randomly selected for this study. One of the logs is used for the training of the neural network and the others for validation and comparison. The structure of the neural network was optimized and was used for the segmentation of the other logs. An efficiency function, consisting of the number of pixels correctly labeled, was defined for the evaluation of the segmentation process. This study shows that a segmentation based on a fuzzy method has better capabilities for generalization than one based on a feed-forward method.

Properties and Effective Extensions of Local Similarity-Based Pixel Value Restoration for Impulse Noise Removal

Properties and Effective Extensions of Local Similarity-Based Pixel Value Restoration for Impulse Noise Removal

51.3: An Ultra‐Low‐Cost 2‐D/3‐D Video‐Conversion System

AbstractIn this paper, we propose an ultra low cost 2D‐to‐3D conversion system which generates depth maps using the human visual perception characteristics of luminance and color. The proposed method has two major parts, edge feature‐based global scene depth gradient and texture‐based local depth refinement. The near‐to‐far global scene depth is generated by analyzing the edge complexity on each row. Then the local pixel value, Y, Cb, and Cr component of the video content is used to refine the detail depth value by enhance the texture lighting gradient on object surface. Combining the global depth gradient and local depth refinement, the depth map has a comfortable and vivid quality with very low computational complexity. The algorithm can be easily implemented by only line‐based architecture and integrated into the display chip.

Local Pixel Value Collection Algorithm for Spot Segmentation in Two-Dimensional Gel Electrophoresis Research

Two-dimensional gel-electrophoresis (2-DE) images show the expression levels of several hundreds of proteins where each protein is represented as a blob-shaped spot of grey level values. The spot detection, that is, the segmentation process has to be efficient as it is the first step in the gel processing. Such extraction of information is a very complex task. In this paper, we propose a novel spot detector that is basically a morphology-based method with the use of a seeded region growing as a central paradigm and which relies on the spot correlation information. The method is tested on our synthetic as well as on real gels with human samples from SWISS-2DPAGE (two-dimensional polyacrylamide gel electrophoresis) database. A comparison of results is done with a method called pixel value collection (PVC). Since our algorithm efficiently uses local spot information, segments the spot by collecting pixel values and its affinity with PVC, we named it local pixel value collection (LPVC). The results show that LPVC achieves similar segmentation results as PVC, but is much faster than PVC.