Grayscale Image Features Research Articles

Attention-enhanced multimodal feature fusion network for clothes-changing person re-identification

Clothes-Changing Person Re-Identification is a challenging problem in computer vision, primarily due to the appearance variations caused by clothing changes across different camera views. This poses significant challenges to traditional person re-identification techniques that rely on clothing features. These challenges include the inconsistency of clothing and the difficulty in learning reliable clothing-irrelevant local features. To address this issue, we propose a novel network architecture called the Attention-Enhanced Multimodal Feature Fusion Network (AE-Net). AE-Net effectively mitigates the impact of clothing changes on recognition accuracy by integrating RGB global features, grayscale image features, and clothing-irrelevant features obtained through semantic segmentation. Specifically, global features capture the overall appearance of the person; grayscale image features help eliminate the interference of color in recognition; and clothing-irrelevant features derived from semantic segmentation enforce the model to learn features independent of the person’s clothing. Additionally, we introduce a multi-scale fusion attention mechanism that further enhances the model’s ability to capture both detailed and global structures, thereby improving recognition accuracy and robustness. Extensive experimental results demonstrate that AE-Net outperforms several state-of-the-art methods on the PRCC and LTCC datasets, particularly in scenarios with significant clothing changes. On the PRCC and LTCC datasets, AE-Net achieves Top-1 accuracy rates of 60.4% and 42.9%, respectively.

Investigation of the impact of local properties of 3D data on the accuracy of block matching-based speckle tracking echocardiography

Abstract Introduction: Due to its simplicity, block-matching is a popular motion-tracking method used in speckle-tracking echocardiography. Improvement of its robustness and accuracy is thus of prime interest. Although it seems plausible that the quality of block matching-based tracking depends on the local properties of image data, and thus, it should be possible to assess in advance how well certain portions of the image data are suited for displacement estimation, the potential relationship has not been studied extensively. Material and methods: This study aimed to search for a relationship between selected features of echocardiographic data and the quality of local displacement estimation. The study used a 3D synthetic B-mode imaging sequence data with known ground truth. Frame-to-frame displacements were estimated for 9856 points in five different frame pairs with mean inter-frame displacements of 0.15, 0.87, 2, 3.02, and 3.84 mm. In each case, tracking errors were evaluated against thirteen grayscale image features, the displacement’s magnitudes, and the normalized cross-correlation (NCX) values. Additionally, a multi-variable regression model was applied to test the combined ability of the proposed features to predict tracking quality. Results: Median tracking error magnitudes were 0.06, 0.13, 0.28, 0.74, and 1.5 mm for each image pair. Weak correlation between errors and individual data features was found only in the case of 3 features: NCX (Pearson’s correlation coefficients in the range of −0.366 to −0.223), number of speckles within the kernel (−0.283, −0.282, and −0.214 for three lowest deformations) and mean of the 3D gradient (−0.252, −0.237 and −0.25). The regression model, however, provided significant prediction improvement with R2 exceeding 0.5. Conclusions: In conclusion, only a weak relationship between the individual investigated kernel features and tracking accuracy has been established, but their combined strength can be assessed as at least moderate.

Transforming Color: A Novel Image Colorization Method

This paper introduces a novel method for image colorization that utilizes a color transformer and generative adversarial networks (GANs) to address the challenge of generating visually appealing colorized images. Conventional approaches often struggle with capturing long-range dependencies and producing realistic colorizations. The proposed method integrates a transformer architecture to capture global information and a GAN framework to improve visual quality. In this study, a color encoder that utilizes a random normal distribution to generate color features is applied. These features are then integrated with grayscale image features to enhance the overall representation of the images. Our method demonstrates superior performance compared with existing approaches by utilizing the capacity of the transformer, which can capture long-range dependencies and generate a realistic colorization of the GAN. Experimental results show that the proposed network significantly outperforms other state-of-the-art colorization techniques, highlighting its potential for image colorization. This research opens new possibilities for precise and visually compelling image colorization in domains such as digital restoration and historical image analysis.

Deep ensemble model-based moving object detection and classification using SAR images

In recent decades, image processing and computer vision models have played a vital role in moving object detection on the synthetic aperture radar (SAR) images. Capturing of moving objects in the SAR images is a difficult task. In this study, a new automated model for detecting moving objects is proposed using SAR images. The proposed model has four main steps, namely, preprocessing, segmentation, feature extraction, and classification. Initially, the input SAR image is pre-processed using a histogram equalization technique. Then, the weighted Otsu-based segmentation algorithm is applied for segmenting the object regions from the pre-processed images. When using the weighted Otsu, the segmented grayscale images are not only clear but also retain the detailed features of grayscale images. Next, feature extraction is carried out by gray-level co-occurrence matrix (GLCM), median binary patterns (MBPs), and additive harmonic mean estimated local Gabor binary pattern (AHME-LGBP). The final step is classification using deep ensemble models, where the objects are classified by employing the ensemble deep learning technique, combining the models like the bidirectional long short-term memory (Bi-LSTM), recurrent neural network (RNN), and improved deep belief network (IDBN), which is trained with the features extracted previously. The combined models increase the accuracy of the results significantly. Furthermore, ensemble modeling reduces the variance and modeling method bias, which decreases the chances of overfitting. Compared to a single contributing model, ensemble models perform better and make better predictions. Additionally, an ensemble lessens the spread or dispersion of the model performance and prediction accuracy. Finally, the performance of the proposed model is related to the conventional models with respect to different measures. In the mean-case scenario, the proposed ensemble model has a minimum error value of 0.032, which is better related to other models. In both median- and best-case scenario studies, the ensemble model has a lower error value of 0.029 and 0.015.

Time-Frequency Image-based Speech Emotion Recognition using Artificial Neural Network

Automatic Speech Emotion Recognition (ASER) is a state-of-the-art application in artificial intelligence. Speech recognition intelligence is employed in various applications such as digital assistance, security, and other human-machine interactive products. In the present work, three open-source acoustic datasets, namely SAVEE, RAVDESS, and EmoDB, have been utilized (Haq et al., 2008, Livingstone et al., 2005, Burkhardt et al., 2005). From these datasets, six emotions namely anger, disgust, fear, happy, neutral, and sad, are selected for automatic speech emotion recognition. Various types of algorithms are already reported for extracting emotional content from acoustic signals. This work proposes a time-frequency (t-f) image-based multiclass speech emotion classification model for the six emotions mentioned above. The proposed model extracts 472 grayscale image features from the t-f images of speech signals. The t-f image is a visual representation of the time component and frequency component at that time in the two-dimensional space, and differing colors show its amplitude. An artificial neural network-based multiclass machine learning approach is used to classify selected emotions. The experimental results show that the above-mentioned emotions' average classification accuracy (CA) of 88.6%, 85.5%, and 93.56% is achieved using SAVEE, RAVDESS, and EmoDB datasets, respectively. Also, an average CA of 83.44% has been achieved for the combination of all three datasets. The maximum reported average classification accuracy (CA) using spectrogram for SAVEE, RAVDESS, and EmoDB dataset is 87.8%, 79.5 %, and 83.4%, respectively (Wani et al., 2020, Mustaqeem and Kwon, 2019, Badshah et al., 2017). The proposed t-f image-based classification model shows improvement in average CA by 0.91%, 7.54%, and 12.18 % for SAVEE, RAVDESS, and EmoDB datasets, respectively. This study can be helpful in human-computer interface applications to detect emotions precisely from acoustic signals.

An Enhanced Machine Learning Approach for Brain MRI Classification.

Magnetic Resonance Imaging (MRI) is a noninvasive technique used in medical imaging to diagnose a variety of disorders. The majority of previous systems performed well on MRI datasets with a small number of images, but their performance deteriorated when applied to large MRI datasets. Therefore, the objective is to develop a quick and trustworthy classification system that can sustain the best performance over a comprehensive MRI dataset. This paper presents a robust approach that has the ability to analyze and classify different types of brain diseases using MRI images. In this paper, global histogram equalization is utilized to remove unwanted details from the MRI images. After the picture has been enhanced, a symlet wavelet transform-based technique has been suggested that can extract the best features from the MRI images for feature extraction. On gray scale images, the suggested feature extraction approach is a compactly supported wavelet with the lowest asymmetry and the most vanishing moments for a given support width. Because the symlet wavelet can accommodate the orthogonal, biorthogonal, and reverse biorthogonal features of gray scale images, it delivers higher classification results. Following the extraction of the best feature, the linear discriminant analysis (LDA) is employed to minimize the feature space's dimensions. The model was trained and evaluated using logistic regression, and it correctly classified several types of brain illnesses based on MRI pictures. To illustrate the importance of the proposed strategy, a standard dataset from Harvard Medical School and the Open Access Series of Imaging Studies (OASIS), which encompasses 24 different brain disorders (including normal), is used. The proposed technique achieved the best classification accuracy of 96.6% when measured against current cutting-edge systems.

A Malicious Code Detection Method Based on FF-MICNN in the Internet of Things.

It is critical to detect malicious code for the security of the Internet of Things (IoT). Therefore, this work proposes a malicious code detection algorithm based on the novel feature fusion-malware image convolutional neural network (FF-MICNN). This method combines a feature fusion algorithm with deep learning. First, the malicious code is transformed into grayscale image features by image technology, after which the opcode sequence features of the malicious code are extracted by the n-gram technique, and the global and local features are fused by feature fusion technology. The fused features are input into FF-MICNN for training, and an appropriate classifier is selected for detection. The results of experiments show that the proposed algorithm exhibits improvements in its detection speed, the comprehensiveness of features, and accuracy as compared with other algorithms. The accuracy rate of the proposed algorithm is also 0.2% better than that of a detection algorithm based on a single feature.

Otsu’s Image Segmentation Algorithm with Memory-Based Fruit Fly Optimization Algorithm

In this paper, the most common pepper noise in grayscale image noise is investigated in depth in the median filtering algorithm, and the improved median filtering algorithm, adaptive switching median filtering algorithm, and adaptive polar median filtering algorithm are applied to the OTSU algorithm. Two improved OTSU algorithms such as the adaptive switched median filter-based OTSU algorithm and the polar adaptive median filter-based OTSU algorithm are obtained. The experimental results show that the algorithm can better cope with grayscale images contaminated by pretzel noise, and the segmented grayscale images are not only clear but also can better retain the detailed features of grayscale images. A genetic algorithm is a kind of search algorithm with high adaptive, fast operation speed, and good global space finding ability, and it will have a good effect when applied to the threshold finding of the OTSU algorithm. However, the traditional genetic algorithm will fall into the local optimal solution in different degrees when finding the optimal threshold. The advantages of the two interpolation methods proposed in this paper are that one is the edge grayscale image interpolation algorithm using OTSU threshold adaptive segmentation and the other is the edge grayscale image interpolation algorithm using local adaptive threshold segmentation, which can accurately divide the grayscale image region according to the characteristics of different grayscale images and effectively improve the loss of grayscale image edge detail information and jagged blur caused by the classical interpolation algorithm. The visual effect of grayscale images is enhanced by selecting grayscale images from the standard grayscale image test set and interpolating them with bilinear interpolation, bucolic interpolation, NEDI interpolation, and FEOI interpolation for interpolation simulation validation. The subjective evaluation and objective evaluation, as well as the running time, are compared, respectively, showing that the method of this paper can effectively improve the quality of grayscale image interpolation.

Support Vector Machine (SVM) for Colorization the Grayscale Image

Recently, there have been several automatic approaches to color grayscale images, which depend on the internal features of the grayscale images. There are several scales which are considered as a prominent key to extract the corresponding chromatic value of the gray level. In this aspect, colorizing methods that rely on automatic algorithms are still under investigation, especially after the development of neural networks used to recognize the features of images. This paper develops a new model to obtain a color image from an original grayscale image through the use of the Support Vector Machine to recognize the features of grayscale images which are extracted from two stages: the first stage is Haar Discrete Wavelets Transform used to configure the vector that combines with six of Statistical Measurements: (Mean, Variance, Skewness, Kurtosis, Energy and Standard Deviation) extracts from the grayscales image in the second stage. After the Support Vector Machine recognition has been done, the colorization process uses the result of Support Vector Machine to recover the color to greyscale images by using YCbCr color system then it converts the color to default color system (RGB) to be more clear. The proposed model will be able to move away from relying on the user to identify the source image which matches in color levels and it exceeds the network determinants of image types with similar color levels. In addition, Support Vector Machine is considered to be more reliable than neural networks in classification algorithms. The model performance is evaluated by using the Root Mean Squared Error (RMSE) in measuring the success of the assumed modal of matching the coloring (resulting) images and the original color images. So, a reality-related result has been obtained at a good rate for all the tested images. This model has proved to be successful in the process of recognizing the chromatic values of greyscale images then retrieving it. It takes less time complexity in trained data, and it isn’t complex in working.

Human action recognition with bag of visual words using different machine learning methods and hyperparameter optimization

Human activity recognition (HAR) has quite a wide range of applications. Due to its widespread use, new studies have been developed to improve the HAR performance. In this study, HAR is carried out using the commonly preferred KTH and Weizmann dataset, as well as a dataset which we created. Speeded up robust features (SURF) are used to extract features from these datasets. These features are reinforced with bag of visual words (BoVW). Different from the studies in the literature that use similar methods, SURF descriptors are extracted from binary images as well as grayscale images. Moreover, four different machine learning (ML) methods such as k-nearest neighbors, decision tree, support vector machine and naive Bayes are used for classification of BoVW features. Hyperparameter optimization is used to set the hyperparameters of these ML methods. As a result, ML methods are compared with each other through a comparison with the activity recognition performances of binary and grayscale image features. The results show that if the contrast of the environment decreases when a human enters the frame, the SURF of the binary image are more effective than the SURF of the gray image for HAR.

A novel adaptive LBP-based descriptor for color image retrieval

In this paper, we present two approaches to extract discriminative features for color image retrieval. The proposed local texture descriptors, based on Radial Mean Local Binary Pattern (RMLBP), are called Color RMCLBP (CRMCLBP) and Prototype Data Model (PDM). RMLBP is a robust to noise descriptor which has been proposed to extract texture features of gray scale images for texture classification.For the first descriptor, the Radial Mean Completed Local Binary Pattern is applied to channels of the color space, independently. Then, the final descriptor is achieved by concatenating the histogram of the CRMCLBP_S/M/C component of each channel. Moreover, to enhance the performance of the proposed method, the Particle Swarm Optimization (PSO) algorithm is used for feature weighting.The second proposed descriptor, PDM, uses the three outputs of CRMCLBP (CRMCLBP_S, CRMCLBP_M, CRMCLBP_C) as discriminative features for each pixel of a color image. Then, a set of representative feature vectors are selected from each image by applying k-means clustering algorithm. This set of selected prototypes are compared by means of a new similarity measure to find the most relevant images. Finally, the weighted versions of PDM is constructed using PSO algorithm.Our proposed methods are tested on Wang, Corel-5k, Corel-10k and Holidays datasets. The results show that our proposed methods makes an admissible tradeoff between speed and retrieval accuracy. The first descriptor enhances the state-of-the-art color texture descriptors in both aspects. The second one is a very fast retrieval algorithm which extracts discriminative features.

Dynamic Weights Equations for Converting Grayscale Image to RGB Image

The method of converting color images from the RGB color system to grayscale images is a simple operation by using the fixed weights method of conversion, but using the same weights to restore the color of the same images is not an effective operation of all types of images because the grayscale image contains little information and it isn't worthy of conversion operation.
 The basic idea in this paper is to employ the mathematics equations which extracted from the grayscale image in conversion operation, this paper presents the method of coloring the grayscale image by using the weights derived from the characteristics of the grayscale image. Skewness, Mean and Standard deviation moments have been extracted from the features of grayscale images and its adoption the determine weights of the RGB color system. This method proved its success in coloring images compared to the traditional method adoption of fixed weights for coloring images because it relies on fixed weights for converting all grayscale images.

Grayscale ultrasonic and shear wave elastographic characteristics of the Achilles’ tendon in patients with familial hypercholesterolemia: A pilot study

ObjectiveTo investigate the feasibility of grayscale ultrasound and quantitative shear wave elastography (SWE) for assessing the image features and stiffness of the Achilles tendon in patients with familial hypercholesterolemia (FH) compared with healthy controls. MethodsA total of 38 Achilles tendons from healthy control participants and 94 from patients with FH were examined with grayscale ultrasound and SWE. Each Achilles tendon examination was performed on 3 different segments (proximal, middle, and distal). The thickness, grayscale image features and elasticity modulus of each segment was measured on longitudinal views. ResultsIn Achilles tendons of healthy control participants, the thicknesses of the proximal, middle, and distal segments were (4.46 ± 0.68) mm, (5.41 ± 1.01) mm, and (4.41 ± 0.57) mm, respectively. The grayscale features were diffusely hypoechoic with parallel linear hyperechoic striations. The mean elasticity modulus of the proximal, middle, and distal sites was (418.08 ± 43.13) kPa, (425.78 ± 47.14) kPa, and (407.79 ± 38.74) kPa, respectively. In the FH group, the thicknesses of the proximal, middle, and distal segments were (7.65 ± 3.09) mm, (11.46 ± 4.84) mm, and (8.14 ± 2.90) mm, respectively. The grayscale features were hypoechoic with linear hyperechoic disordered fibre distribution (92/94). Two of 94 Achilles tendons had considerable focal hypoechogenicity. Seventeen of 94 Achilles tendons had calcifications. In the FH group, the mean elasticity modulus of the proximal, middle, and distal segments were (294.86 ± 58.13) kPa, (280.93 ± 63.58) kPa, and (282.41 ± 56.47) kPa, respectively. Statistically significant differences were found between the Achilles tendons of healthy control participants and FH patients in the thicknesses and mean elasticity modulus at the proximal, middle and distal segments of the Achilles tendons (all P < 0.001). ConclusionsOur results suggest that the grayscale features and SWE characteristics of the Achilles tendon provided complementary biomechanical information for quantitative assessment the Achilles tendon in patients with FH.

A novel approach to multiclass psoriasis disease risk stratification: Machine learning paradigm

Abstract The stage and grade of psoriasis severity is clinically relevant and important for dermatologists as it aids them lead to a reliable and an accurate decision making process for better therapy. This paper proposes a novel psoriasis risk assessment system (pRAS) for stratification of psoriasis severity from colored psoriasis skin images having Asian Indian ethnicity. Machine learning paradigm is adapted for risk stratification of psoriasis disease grades utilizing offline training and online testing images. We design four kinds of pRAS systems. It uses two kinds of classifiers (support vector machines (SVM) and decision tree (DT)) during training and testing phases and two kinds of feature selection criteria (Principal Component Analysis (PCA) and Fisher Discriminant Ratio (FDR)), thus, leading to an exhaustive comparison between these four systems. Our database consisted of 848 psoriasis images with five severity grades: healthy, mild, moderate, severe and very severe, consisting of 383, 47, 245, 145, and 28 images respectively. The pRAS system computes 859 colored and grayscale image features. Using cross-validation protocol with K-fold procedure, the pRAS system utilizing the SVM with FDR combination with combined color and grayscale feature set gives an accuracy of 99.92%. Several performance evaluation parameters such as: feature retaining power, aggregated feature effect and system reliability is computed meeting our assumptions and hypothesis. Our results demonstrate promising results and pRAS system is able to stratify the psoriasis disease.

Contrast Enhancement Using Brightness Preserving Histogram Equalization Technique for Classification of Date Varieties

Computer vision technique is becoming popular for quality assessment of many products in food industries. Image enhancement is the first step in analyzing the images in order to obtain detailed information for the determination of quality. In this study, Brightness preserving histogram equalization technique was used to enhance the features of gray scale images to classify three date varieties (Khalas, Fard and Madina). Mean, entropy, kurtosis and skewness features were extracted from the original and enhanced images. Mean and entropy from original images and kurtosis from the enhanced images were selected based on Lukka's feature selection approach. An overall classification efficiency of 93.72% was achieved with just three features. Brightness preserving histogram equalization technique has great potential to improve the classification in various quality attributes of food and agricultural products with minimum features.

Edge Detection for Objects in the Upper Triangle Gray Scale Image by Cholesky Decomposition and Unsharp Masking (USM)

In this paper , we propose an efficient and effective method for Edge detection for objects in the upper triangle Gray Scale Image . The optimal Edge detection discriminative features of gray scale images are obtained by performing Cholesky decomposition , which could be implemented using the edge existing algorithm. We approach also yields the size of the symmetry region without additional computational effort . Experiments showed that the proposed algorithm could generate a path one pixel wide with continuous edges, and the proposed algorithm had a better edge-detection accuracy than others techniques. Therefore, the proposed edge-detection algorithm is feasible for use in automatic visual inspection systems . General Terms Digital Image Processing, Algorithms, Image segmentation .

Supervised Classification of Basaltic Aggregate Particles Based on Texture Properties

AbstractThe strength and durability of materials produced from aggregates (e.g., concrete bricks, concrete, and ballast) are critically affected by the weathering of the particles, which is closely related to their mineral composition. It is possible to infer the degree of weathering from visual features derived from the surface of the aggregates. By using sound pattern recognition methods, this study shows that the characterization of the visual texture of particles, performed by using texture-related features of gray scale images, allows the effective differentiation between weathered and nonweathered aggregates. The selection of the most discriminative features is also performed by taking into account a feature ranking method. The evaluation of the methodology in the presence of noise suggests that it can be used in stone quarries for automatic detection of weathered materials.

Affine-invariant recognition of gray-scale characters using global affine transformation correlation

Describes a technique of gray-scale character recognition that offers both noise tolerance and affine-invariance. The key ideas are twofold. First is the use of normalized cross-correlation as a matching measure to realize noise tolerance. Second is the application of global affine transformation (GAT) to the input image so as to achieve affine-invariant correlation with the target image. In particular, optimal GAT is efficiently determined by the successive iteration method using topographic features of gray-scale images as matching constraints. We demonstrate the high matching ability of the proposed GAT correlation method using gray-scale images of numerals subjected to random Gaussian noise and a wide range of affine transformation. Moreover, extensive recognition experiments show that the achieved recognition rate of 94.3 percent against rotation within 30 degrees, scale change within 30 percent, and translation within 20 percent of the character width along with random Gaussian noise is sufficiently high compared to the 42.8 percent offered by simple correlation.