Contextual Information Of Images Research Articles

Plant Diseased Lesion Image Segmentation and Recognition Based on Improved Multi-Scale Attention Net

Fallen leaf disease can lead to a decrease in leaf area, a decrease in photosynthetic products, insufficient accumulation of fruit sugar, poor coloring and flavor, and a large number of fruits developing sunburn. To address the aforementioned issue, this article introduces a deep learning algorithm designed for the segmentation and recognition of agricultural disease images, particularly those involving leaf lesions. The essence of this algorithm lies in enhancing the Multi-scale Attention Net (MA-Net) encoder and attention mechanism to improve the model’s performance when processing agricultural disease images. Firstly, an analysis was conducted on MA-Net, and its limitations were identified. Compared to res-block, Mix Vision Transformer (MiT) consumes relatively less time during the training process, can better capture global and contextual information in images, and has better robustness and scalability. Then, the feature extraction parts of different networks were used as encoders to join the MA-Net network. Compared to a Position-wise Attention Block (PAB), which has higher computational complexity and requires a larger amount of computing resources, Effective Channel Attention net (ECANet) reduces the number of model parameters and computation by learning the correlation between channels, as well as having a better denoising ability. The experimental results show that the proposed solution has high accuracy and stability in agricultural disease image segmentation and recognition. The mean Intersection over Union (mIoU) is 98.1%, which is 0.2% higher than traditional MA-Net; Dice Loss is 0.9%, which is 0.1% lower than traditional MA-Net.

Swin-GA-RF: genetic algorithm-based Swin Transformer and random forest for enhancing cervical cancer classification.

Cervical cancer is a prevalent and concerning disease affecting women, with increasing incidence and mortality rates. Early detection plays a crucial role in improving outcomes. Recent advancements in computer vision, particularly the Swin transformer, have shown promising performance in image classification tasks, rivaling or surpassing traditional convolutional neural networks (CNNs). The Swin transformer adopts a hierarchical and efficient approach using shifted windows, enabling the capture of both local and global contextual information in images. In this paper, we propose a novel approach called Swin-GA-RF to enhance the classification performance of cervical cells in Pap smear images. Swin-GA-RF combines the strengths of the Swin transformer, genetic algorithm (GA) feature selection, and the replacement of the softmax layer with a random forest classifier. Our methodology involves extracting feature representations from the Swin transformer, utilizing GA to identify the optimal feature set, and employing random forest as the classification model. Additionally, data augmentation techniques are applied to augment the diversity and quantity of the SIPaKMeD1 cervical cancer image dataset. We compare the performance of the Swin-GA-RF Transformer with pre-trained CNN models using two classes and five classes of cervical cancer classification, employing both Adam and SGD optimizers. The experimental results demonstrate that Swin-GA-RF outperforms other Swin transformers and pre-trained CNN models. When utilizing the Adam optimizer, Swin-GA-RF achieves the highest performance in both binary and five-class classification tasks. Specifically, for binary classification, it achieves an accuracy, precision, recall, and F1-score of 99.012, 99.015, 99.012, and 99.011, respectively. In the five-class classification, it achieves an accuracy, precision, recall, and F1-score of 98.808, 98.812, 98.808, and 98.808, respectively. These results underscore the effectiveness of the Swin-GA-RF approach in cervical cancer classification, demonstrating its potential as a valuable tool for early diagnosis and screening programs.

MSCA-Net: Multi-scale contextual attention network for skin lesion segmentation

Lesion segmentation algorithms automatically outline lesion areas in medical images, facilitating more effective identification and assessment of the clinically relevant features, and improving the efficacy and diagnosis accuracy. However, most fully convolutional network based segmentation methods suffer from spatial and contextual information loss when decreasing image resolution. To overcome this shortcoming, this paper proposes a skin lesion segmentation model, namely, the Multi-Scale Contextual Attention Network (MSCA-Net), which can exploit the multi-scale contextual information in images. Inspired by the skip connection of U-Net, we design a multi-scale bridge (MSB) module which interacts with multi-scale features to effectively fuse the multi-scale contextual information of the encoder and decoder path features. We further propose a global-local channel spatial attention module (GL-CSAM), aiming at capturing global contextual information. In addition, to take full advantage of the multi-scale features of the decoder, we propose a scale-aware deep supervision (SADS) module to achieve hierarchical iterative deep supervision. Comprehensive experimental results on the public dataset of ISIC 2017, ISIC 2018, and PH2 show that our proposed method outperforms other state-of-the-art methods, demonstrating the efficacy of our method in skin lesion segmentation. Our code is available at https://github.com/YonghengSun1997/MSCA-Net.

Using Context-Guided data Augmentation, lightweight CNN, and proximity detection techniques to improve site safety monitoring under occlusion conditions

Automated recognition of image patterns in surveillance cameras is beneficial for safety monitoring. A representative application is visual proximity detection for accident prevention. However, existing deep learning (DL)-based proximity detection methods are likely to be inaccurate due to congestion, background clutter, and occlusion in construction sites. Another problem is that most of these methods cannot suffice computing capability, network training efficiency, and performance accuracy at the same time. This study first presents a novel context-guided data augmentation method that addresses the performance loss issue due to object occlusion. This method places new instances on images based on contextual image information rather than randomly erasing images to simulate occlusion circumstances. Next, a light-weight and less-costly DL model named YOLOv4-EFNB0 is formulated for multi-class construction resource detection in real-time. Moreover, this study presents a proactive proximity detection application by integrating YOLOv4-EFNB0 with homography transformation. Based on the experiment, YOLOv4-EFNB0 demonstrates a better object detection outcome when trained on the augmented dataset over the Moving Objects in Construction Sites (MOCS) baseline dataset. This study also conducts a feasibility test for the visual proximity detection application. The results indicate the application has a high accuracy rate and a fast speed, namely, 96.76% in 25 Frames Per Second (FPS), which can facilitate the automation of safety monitoring and inspection.

A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks

Land use is used to reflect the expression of human activities in space, and land use classification is a way to obtain accurate land use information. Obtaining high-precision land use classification from remote sensing images remains a significant challenge. Traditional machine learning methods and image semantic segmentation models are unable to make full use of the spatial and contextual information of images. This results in land use classification that does not meet high-precision requirements. In order to improve the accuracy of land use classification, we propose a land use classification model, called DADNet-CRFs, that integrates an attention mechanism and conditional random fields (CRFs). The model is divided into two modules: the Dual Attention Dense Network (DADNet) and CRFs. First, the convolution method in the UNet network is modified to Dense Convolution, and the band-hole pyramid pooling module, spatial location attention mechanism module, and channel attention mechanism module are fused at appropriate locations in the network, which together form DADNet. Second, the DADNet segmentation results are used as a priori conditions to guide the training of CRFs. The model is tested with the GID dataset, and the results show that the overall accuracy of land use classification obtained with this model is 7.36% and 1.61% higher than FCN-8s and BiSeNet in classification accuracy, 11.95% and 1.81% higher in MIoU accuracy, and with a 9.35% and 2.07% higher kappa coefficient, respectively. The proposed DADNet-CRFs model can fully use the spatial and contextual semantic information of high-resolution remote sensing images, and it effectively improves the accuracy of land use classification. The model can serve as a highly accurate automatic classification tool for land use classification and mapping high-resolution images.

Multiscale residual fusion network for image denoising

Deep-learning methods have been developed in recent years and have achieved dramatic improvements for image denoising. The existing deep-learning methods can be conducted using two major models: Encoder–decoder and high-resolution, where the high-resolution model has superior resolution ability for detail description and restoration. In this study, a high-resolution-based network called multiscale residual fusion network (MRF-Net) is proposed, which employed the spatial and contextual information of images. In detail, dilated convolution layers are used to enlarge the network's receptive field and learned sufficient features in a multiscale feature extracting module. The function of dilated convolution is reinterpreted here and it is viewed as a complex downsampling operation. Therefore, multiscale feature analysis could be performed in the proposed network by dilated convolution. Multilevel feature maps are sequentially obtained through a residual projection module, where considerable contextual and spatial information was collected from the multiscale features. In a residual fusion module, all maps were aggregated to generate a residual image effectively for noise removal. Experiments demonstrated that the MRF-Net outperformed several state-of-the-art model-based and deep-learning methods in both blind and non-blind image denoising tests. Meanwhile, ablation studies were executed to verify the denoising performance of each module. Moreover, this method exhibited high computational efficiency, thus demonstrating its practicability.

FUSIONET: A Hybrid Model Towards Image Classification

Image classification, a topic of pattern recognition in computer vision, is an approach of classification based on contextual information in images. Contextual here means this approach is focusing on the relationship of the nearby pixels also called neighborhood. An open topic of research in computer vision is to devise an effective means of transferring human’s informal knowledge into computers, such that computers can also perceive their environment. However, the occurrence of object with respect to image representation is usually associated with various features of variation causing noise in the image representation. Hence, it tends to be very difficult to actually disentangle these abstract factors of influence from the principal object. In this paper, we have proposed a hybrid model: FUSIONET, which has been modeled for studying and extracting meaning facts from images. Our proposition combines two distinct stack of convolution operation (3 × 3 and 1 × 1, respectively). Successively, these relatively low-feature maps from the above operation are fed as input to a downstream classifier for classification of the image in question.

Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and Tumors.

The liver is an irreplaceable organ in the human body, maintaining life activities and metabolism. Malignant tumors of the liver have a high mortality rate at present. Computer-aided segmentation of the liver and tumors has significant effects on clinical diagnosis and treatment. There are still many challenges in the segmentation of the liver and liver tumors simultaneously, such as, on the one hand, that convolutional kernels with fixed geometric structures do not match complex, irregularly shaped targets; on the other, pooling during convolution results in a loss of spatial contextual information of images. In this work, we designed a cascaded U-ADenseNet with coarse-to-fine processing for addressing the above issues of fully automatic segmentation. This work contributes multi-resolution input images and multi-layered channel attention combined with atrous spatial pyramid pooling densely connected in the fine segmentation. The proposed model was evaluated by a public dataset of the Liver Tumor Segmentation Challenge (LiTS). Our approach attained competitive liver and tumor segmentation scores that exceeded other methods across a wide range of metrics.

Pairwise Context Similarity for Image Retrieval System Using Variational Auto-Encoder

Deep-learning-to-hash models have recently achieved several breakthroughs enabling a fast and efficient image retrieval system. As supervision for deep-learning-to-hash models, pairwise label similarity which considers two images to be identical if their labels are identical plays a crucial role. However, models using only pairwise label similarity cannot incorporate rich contextual information in images because pairwise label similarity solely depends on labels. In this paper, we initially address two major limitations of using the pairwise label similarity as only supervision for the deep-learning-to-hash model. Then, we propose a novel pairwise context similarity to alleviate those limitations. The proposed pairwise context similarity is computed on the latent space of a Variational Auto-Encoder which is trained in an unsupervised fashion that does not utilize any label information. Moreover we propose the strategy of an auxiliary loss for deep-learning-to-hash models that can easily be combined with previous losses using pairwise label similarity without deteriorating the retrieval quality. In our experiments on three standard benchmark datasets, our proposed method achieved high retrieval quality for image retrieval tasks while also showing advantages with regard to the addressed limitations. Also, we empirically prove that our proposed method acts as a proper regularization term during training so that our loss term therefore helps to mitigate overfitting and stabilizes the training curves.

Improved High-Density Myoelectric Pattern Recognition Control Against Electrode Shift Using Data Augmentation and Dilated Convolutional Neural Network.

the objective of this work is to develop a robust method for myoelectric control towards alleviating the interference of electrode shift. M ethods: In the proposed method, a preprocessing approach was first performed to convert high-density surface electromyogram (HD-sEMG) signals into a series of images, and the electrode shift appeared as pixel shift in these images. Next, a data augmentation approach was applied to the training data from just one position (no shift), so as to simulate HD-sEMG images derived from fictitious shift positions. The dilated convolutional neural network (DCNN) was subsequently adopted for classification. Compared to common convolutional neural network, DCNN always contained a larger receptive field that was supposed to be adept at mining wider spatial contextual information in images. This property was further confirmed to facilitate the classification of myoelectric patterns using HD-sEMG. The performance of the proposed method was evaluated with HD-sEMG data recorded by a 10×10 electrode array placed over forearm extensors of ten subjects during their performance of six wrist and finger extension tasks. Under a variety of actual electrode shift conditions, the proposed method achieved a mean classification accuracy of 95.34%, and it outperformed other common methods. This work demonstrated feasibility and usability of combining data augmentation and DCNN in predicting myoelectric patterns in the context of electrode shifts. The proposed method is a practical solution for robust myoelectric control against electrode array shifts.

Contrast enhancement based on discriminative co-occurrence statistics

Despite recent advances in contrast enhancement, it remains difficult for existing methods to simultaneously achieve consistent improvements in image brightness and contrast in both low-light and normal-light images. To address this issue, we revisit 2D histogram equalization methods and extend them to accommodate more diversified and poor lighting conditions. The extension is based on the observation that the contrast needs to be improved by increasing the intensity difference between spatially neighboring pixels, while the degree of increase should be proportional to the difference in their reflectances. On the basis of this observation, we propose to embed the inter-pixel contextual information of image reflectance into the 2D histogram of intensity co-occurrence. An intensity mapping function can thus be derived by solving optimization problems formulated with the 2D histogram, leading to two novel contrast enhancement methods. Qualitative and quantitative evaluations on more than 600 images showed that the proposed methods are superior to state-of-the-art contrast enhancement methods. It was also shown that the reflectance of an image provides important visual information on the significance and objectness of local image areas. Using this reflectance as a clue, the degree of contrast enhancement can be adaptively derived to achieve sufficient brightness improvement in low-light images and to avoid excessive enhancement in normal-light images.

The Learning-based Automatic Segmentation Algorithm of Brain MR Images Based on 7T.

The learning-based algorithms provide an ability to automatically estimate and refine GM, WM and CSF. The ground truth manually achieved from the 3T MR image may not be accurate and reliable with poor image intensity contrast. It will seriously influence the classification performance because the supervised learning-based algorithms extremely rely on the ground truth. Recently, the 7T MR images brings about the excellent image intensity contrast, while Structured Random Forest (SRF) performs the pixel-level classification and achieves structural and contextual information in images. In this paper, a automatic segmentation algorithm is proposed based on ground truth achieved by the corresponding 7T subjects for segmenting the 3T&1.5T brain tissues using SRF classifiers. Through taking advantage of the 7T brain MR images, we can achieve the highly accuracy and reliable ground truth and then implement the training of SRF classifiers. Our proposed algorithm effectively integrates the T1-weighed images along with the probability maps to train the SRF classifiers for brain tissue segmentation. Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 95.14%±0.9%, 90.17%±1.83%, and 81.96%±4.32% for WM, GM, and CSF. With the experiment results, the proposed algorithm can achieve better performances than other automatic segmentation methods. Further experiments are performed on the 200 3T&1.5T brain MR images of ADNI dataset and our proposed method shows promised performances. The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation.

Fusing High-Spatial-Resolution Remotely Sensed Imagery and OpenStreetMap Data for Land Cover Classification Over Urban Areas

Land cover classification of urban areas is critical for understanding the urban environment. High-resolution remotely sensed imagery provides abundant, detailed spatial information for urban classification. In the meantime, OpenStreetMap (OSM) data, as typical crowd-sourced geographical information, have been an emerging data source for obtaining urban information. In this context, a land cover classification method that fuses high-resolution remotely sensed imagery and OSM data is proposed. Training samples were generated by integrating the OSM data and multiple information indexes. OSM data, which contain class attributes and location information of urban objects, served as the labels of initial training samples. Multiple information indexes that reflect spectral and spatial characteristics of different classes were utilized to improve the training set. Morphological attribute profiles were used because the structural and contextual information of images was effective in distinguishing the classes with similar spectral characteristics. Moreover, a road superimposition strategy that considers road hierarchy was developed because OSM data provide road information with high completeness in the urban area. Experiments were conducted on the data captured over Wuhan city, and three state-of-the-art approaches were adopted for comparison. Results show that the proposed approach obtains satisfactory results and outperforms the other comparative approaches.

Using contextual spaces for image re-ranking and rank aggregation

This article presents two novel re-ranking approaches that take into account contextual information defined by the K-Nearest Neighbours (KNN) of a query image for improving the effectiveness of CBIR systems. The main contributions of this article are the definition of the concept of contextual spaces for encoding contextual information of images; the definition of two new re-ranking algorithms that exploit contextual information encoded in contextual spaces; and the evaluation of the proposed algorithms in several CBIR tasks related to the combination of image descriptors; combination of visual and textual descriptors; and combination of post-processing (re-ranking) methods. We conducted a large evaluation protocol involving visual descriptors (considering shape, color, and texture) and textual descriptors, various datasets, and comparisons with other post-processing methods. Experimental results demonstrate the effectiveness of our approaches.

Combining Decision Trees with Hierarchical Object-oriented Image Analysis for Mapping Arid Rangelands

Decision tree analysis is a statistical approach for developing a rule base used for image classification. We developed a unique approach using object-based rather than pixelbased image information as input for a classification tree for mapping arid land vegetation. A QuickBird satellite image was segmented at four different scales, resulting in a hierarchical network of image objects representing the image information in different spatial resolutions. This allowed for differentiation of individual shrubs at a fine scale and delineation of broader vegetation classes at coarser scales. Input variables included spectral, textural and contextual image information, and the variables chosen by the decision tree included many features not available or as easily determined with pixel based image analysis. Spectral information was selected near the top of the classification trees, while contextual and textural variables were more common closer to the terminal nodes of the classification tree. The combination of multi-resolution image segmentation and decision tree analysis facilitated the selection of input variables and helped in determining the appropriate image analysis scale.

Toward robust analysis of satellite images using map information-application to urban area detection

With the rapid development of remote sensing, digital image processing has become an important tool for the quantitative and statistical analysis of remotely sensed images. These images most often contain complex natural scenes. The robust interpretation of such images requires the use of different sources of information about the scenes under consideration. This paper presents an integrated approach to robust analysis of SPOT images with the aid of map information as well as a priori knowledge about the contextual information of images. Markov random field theory and the Bayes formula are used to formulate the image analysis problem as a problem of optimization of an objective function, which in turn permits the application of various existing optimization algorithms to solve the problem. To increase the robustness of the result, several techniques are proposed to effectively use map information and image contextual information. The first one is concerned with the estimation of the parameters in the objective function with the help of these two sources of information. The second one is the integration of map information in Bayes image modeling using a Markov random field. The third one is a new optimization algorithm which takes into account map information and image contextual information by means of a feedback control scheme. The last technique proposed to increase the robustness of the result is concerned with the fusion of several (intermediate) analysis results by again using map knowledge and image contextual information for the estimation of the reliability of these results.

3D objects recognition by optimal matching search of multinary relations graphs

A new method for 3D object optimal recognition from 2D single images is described. It introduces an optimization approach to inexact graph matching implemented by ordered search algorithm. The search is conducted on homomorphic or monomorphic trees constructed in a combinatorial state space. A min-max structure of the search guiding cost function combines error criteria based on hypothesized multinary geometrical relations with non-geometrical featural and contextual image information. The geometrical error criterion reflects the disparity of the estimated observation vectors derived from partial matches. These vectors are calculated by a novel “area ratio” method based on points or planar region primitives that are preferred for practical image segmentation. The experimental results demonstrate a significant reduction in the complexity of the matching problem (usually exponential), and low sensitivity to large image data errors.