Search

Loop closure is the key to eliminate the cumulative error in simultaneous localization and mapping (SLAM) system. When the illumination conditions or the viewing angle change greatly, the traditional appearance-based loop closure methods often fail. Aiming at this situation, an object-level loop closure method is proposed based on ORBSLAM2 framework. Firstly, semantic information obtained by object detection and the feature point information are used to construct object-level semantic map. Then semantic map is abstracted into topological map and landmarks into nodes, node information is described by color histogram, and combined geometric relationship between nodes, a graph matching method is proposed to realize loop detection based on semantic and geometric consistency constraints. When a loop is detected, the loop is corrected by object alignment. Finally, experiments are carried out on the published TUM and USTC data sets, and the results show that the accuracy of the proposed system is 49.58% higher than that of ORBSLAM2 on average, and the constructed semantic map shows a good positioning effect. [ABSTRACT FROM AUTHOR]

In agriculture, as precision farming increasingly employs robots to monitor crops, the use of weeding and harvesting robots is expanding the need for computer vision. Currently, most researchers and companies address these computer vision tasks with CNN-based deep learning. This technology requires large datasets of plant and weed images labeled by experts, as well as substantial computational resources. However, traditional feature-based approaches to computer vision can extract meaningful parameters and achieve comparably good classification results with only a tenth of the dataset size. This study presents these methods and seeks to determine the minimum number of training images required to achieve reliable classification. We tested the classification results with 5, 10, 20, 40, 80, and 160 images per weed type in a four-class classification system. We extracted shape features, distance transformation features, color histograms, and texture features. Each type of feature was tested individually and in various combinations to determine the best results. Using six types of classifiers, we achieved a 94.56% recall rate with 160 images per weed. Better results were obtained with more training images and a greater variety of features. [ABSTRACT FROM AUTHOR]

Globally, lung and colon cancers are among the most prevalent and lethal tumors. Early cancer identification is essential to increase the likelihood of survival. Histopathological images are considered an appropriate tool for diagnosing cancer, which is tedious and error-prone if done manually. Recently, machine learning methods based on feature engineering have gained prominence in automatic histopathological image classification. Furthermore, these methods are more interpretable than deep learning, which operates in a "black box" manner. In the medical profession, the interpretability of a technique is critical to gaining the trust of end users to adopt it. In view of the above, this work aims to create an accurate and interpretable machine-learning technique for the automated classification of lung and colon cancers from histopathology images. In the proposed approach, following the preprocessing steps, texture and color features are retrieved by utilizing the Haralick and Color histogram feature extraction algorithms, respectively. The obtained features are concatenated to form a single feature set. The three feature sets (texture, color, and combined features) are passed into the Light Gradient Boosting Machine (LightGBM) classifier for classification. And their performance is evaluated on the LC25000 dataset using hold-out and stratified 10-fold cross-validation (Stratified 10-FCV) techniques. With a test/hold-out set, the LightGBM with texture, color, and combined features classifies the lung and colon cancer images with 97.72%, 99.92%, and 100% accuracy respectively. In addition, a stratified 10-fold cross-validation method also revealed that LightGBM's combined or color features performed well, with an excellent mean auc_mu score and a low mean multi_logloss value. Thus, this proposed technique can help histologists detect and classify lung and colon histopathology images more efficiently, effectively, and economically, resulting in more productivity. [ABSTRACT FROM AUTHOR]

In the current trend, the image retrieval (IR) system has also been shifted from traditional text-based to content-based with the advancement in technology. Many issues have been resolved by content-based IR. In a particular case of information retrieval/image retrieval (IR) systems, the number of images on the web and the usage of images are growing exponentially. Therefore, IR system needs to be scalable, flexible, modularizable and promotes reusability so that it becomes easy to deploy, develop and maintain the system. In this paper, we have presented a CBIR model using Color Histogram and Local Binary Pattern (LBP) where both are built with Microservices architecture using docker platform. The framework used in this model is logic independent therefore any CBIR system can be run using this framework. The CBIR using Color Histogram uses chi-squared distance as a similarity measure while CBIR model using LBP is implemented using Linear Support Vector Machines for image classification. In our experiments, we have achieved the average recall, precision, and F-measure using Color Histogram 22.25%, 63.12%, and 32.67%, respectively. Though, we have achieved the average recall, precision, and F-measure using LBP 77.15%, 79.90%, and 76.17%, respectively. It has been observed that LBP model is more accurate than Color Histogram for detecting different weather conditions. It has also been found that the use of Microservices architecture leads to improve the non-functional qualities of a CBIR system as compared to traditional architecture styles by a great margin. [ABSTRACT FROM AUTHOR]

The advancement of digital microscopic scanning has made the study of image processing as well as categorization an exciting field of diagnostic studies. The literature describes a number of methods for detecting acute lymphocytic leukemia (ALL) using blood smear pictures. The goal of this research is to create an efficient approach for segmenting and detecting leukemia. This research has created a leukemia diagnosis module predicated on deep learning (DL) using blood smear pictures. Pre-processing, segmentation, extraction of features, and classification are performed here by the identification scheme. The presented hybrid model of African Buffalo and African Vulture Optimization (AB-AVO) performs the segmentation process, in which cytoplasm and nucleus regions are segmented. The Local Directional Pattern (LDP) and color histogram characteristics have been then retrieved from the segmented pictures and given into the presented Recurrent Neural Network (RNN) for categorization. The ALL-IDB1 and ALL-IDB2 databases' blood smear pictures are taken into account for the investigation and assessed using metrics including F1-score, sensitivity, dice coefficient, precision, specificity, recall, and accuracy. The presented AB-AVO-RNN approach exhibits 100% accuracy, according to simulation data. Modern methodologies are used to compare the effectiveness of the suggested AB-AVO-RNN methodology. The investigation demonstrates that the suggested classifier performs comparably better and can identify leukemia from blood smear pictures. [ABSTRACT FROM AUTHOR]

Multiple microbes can alter a plant's development and agricultural productivity, which has significant implications for the ecosystem and human life. As a result, timely identification, prevention, and prompt treatment are required. Fundamental methods have some drawbacks to plant disease identification like more time-consuming, accuracy, doesn't support multiple plant detection. This paper introduces a hybrid model that uses a random forest classifier combined with the AdaBoost Classifier to classify plant diseases to overcome the above-said drawbacks. So as to individualize normal and abnormal leaves from data sets, the suggested methodology employs the Random Forest with AdaBoost algorithm. The operational processes in our suggested study are preprocessing, segmentation, feature extraction, training the classifier, and classification. The produced datasets of infected and uninfected leaves are combined and processed using the Random Forest classifier to categorize the infected and uninfected photos. Color Histogram is used to gather features from imagery. KNN, Naive Bayes, and SVM are all used to evaluate our suggested technique. [ABSTRACT FROM AUTHOR]

In agriculture, as precision farming increasingly employs robots to monitor crops, the use of weeding and harvesting robots is expanding the need for computer vision. Currently, most researchers and companies address these computer vision tasks with CNN-based deep learning. This technology requires large datasets of plant and weed images labeled by experts, as well as substantial computational resources. However, traditional feature-based approaches to computer vision can extract meaningful parameters and achieve comparably good classification results with only a tenth of the dataset size. This study presents these methods and seeks to determine the minimum number of training images required to achieve reliable classification. We tested the classification results with 5, 10, 20, 40, 80, and 160 images per weed type in a four-class classification system. We extracted shape features, distance transformation features, color histograms, and texture features. Each type of feature was tested individually and in various combinations to determine the best results. Using six types of classifiers, we achieved a 94.56% recall rate with 160 images per weed. Better results were obtained with more training images and a greater variety of features.

The need for information is gradually shifting from text to images due to the technology’s growth and increase in digital images. It is quite challenging for people to find similar color images. To obtain similarity matching, the color of the image needs to be identified. This paper aims at various clustering techniques to identify the color of the digital image. Though many clustering techniques exist, this paper focuses on Fuzzy c-Means, Mean-Shift, and a hybrid technique that amalgamates the agglomerative hierarchies and k-Means, known as hKmeans to cluster the intensity of the image. Applying evaluation metrics of Mean Squared Error, Root Mean Squared Error, Mean Absolute Error, Homogeneity, Completeness, V-Score, and Peak signal-to-noise ratio it is proven that the results obtained demonstrate the good performance of the proposed technique. Then the color histogram is applied to identify the color and differentiate the color distribution on the original and clustered image.

Education informatization is an important means to improve the quality of education and teaching as well as a basic condition for the innovative reform and application of education and teaching, which also means that education informatization cannot be separated from the construction of digital learning resources. This paper utilizes the advantage of Flash technology’s integration of multiple media elements to design physics animation courseware. Then, it combines the color histogram and edge density analysis algorithm to segment the animated visual scene of physics courseware, optimize the production process of Flash physics animated courseware, and establish a scientific evaluation standard for courseware quality. The average scores of the four dimensions of manipulability, stability, aesthetics, and compatibility in the evaluation results of physics animated courseware in this paper are all higher than 4 points. The students who apply physics animated courseware to teach improve their learning attitudes, learning behaviors, and learning effects by 11.61, 7.33, and 6.54, respectively, compared with the traditional physics teaching, and all of them are significantly different (P

The digital world is developing more quickly than ever. Multimedia processing and distribution, however become vulnerable issues due to the enormous quantity and significance of vital information. Therefore, extensive technologies and algorithms are required for the safe transmission of messages, images, and video files. This paper proposes a secure framework by acute integration of video summarization and image encryption. Three parts comprise the proposed cryptosystem framework. The informative frames are first extracted using an efficient and lightweight technique that make use of the color histogram-clustering (RGB-HSV) approach's processing capabilities. Each frame of a video is represented by deep features, which are based on an enhanced pre-trained Inception-v3 network. After that summary is obtain using the K-means optimal clustering algorithm. The representative keyframes then extracted using the clusters highest possible entropy nodes. Experimental validation on two well-known standard datasets demonstrates the proposed methods superiority to numerous state-of-the-art approaches. Finally, the proposed framework performs an efficient image encryption and decryption algorithm by employing a general linear group function GLn (F). The analysis and testing outcomes prove the superiority of the proposed adaptive RSA.

Chickpea is one of the most important legumes in the world, however, it is prone to various diseases that can significantly reduce its yield and quality. Hence, the accurate classification of these diseases are crucial for effective disease management. In this study, we propose a combined approach for chickpea disease classification using GLCM-Color Histogram features with Bilateral filtering and non-local means filtering. Our research comprises three phases: image preprocessing, feature extraction, and classification. To enhance the model's robustness and reduce noise, we applied Bilateral filtering, non-local means filtering, and data augmentation techniques. We utilized a combination of gray-level co-occurrence matrix (GLCM) and Color Histogram for feature extraction, which can capture the texture and color features important for image classification tasks. The extracted features were then classified using Multi-Layer Perceptrons (MLPs), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Random Forest (RF). The experimental results indicate that the combined features extracted using GLCM and Color Histogram with the SVM classifier outperformed individual feature extractors and classifiers, achieving a testing accuracy of 95.49 %. Our study demonstrates that proper image preprocessing, data augmentation, and feature extraction provide an efficient classification method for identifying and classifying chickpea disease.

Person re-identification (PRID) has been thoroughly researched in typical surveillance scenarios where various scenes are monitored by side-mounted, rectilinear-lens cameras. To date, few methods have been proposed for fisheye cameras mounted overhead and their performance is lacking. In order to close this performance gap, we propose a multi-feature framework for fisheye PRID where we combine deep-learning, color-based and location-based features by means of novel feature fusion. We evaluate the performance of our framework for various feature combinations on FRIDA, a public fisheye PRID dataset. The results demonstrate that our multi-feature approach outperforms recent appearance-based deep-learning methods by almost 18% points and location-based methods by almost 3% points in matching accuracy. We also demonstrate the potential application of the proposed PRID framework to people counting in large, crowded indoor spaces.

The video retrieval system refers to the task of retrieving the most relevant video collection, given a user query. By applying some feature extraction models the contents of the video can be extracted. With the exponential increase in video data in online and offline databases as well as a huge implementation of multiple applications in health, military, social media, and art, the Content-Based Video Retrieval (CBVR) system has emerged. The CBVR system takes the inner contents of the video frame and analyses features of each frame, through which similar videos are retrieved from the database. However, searching and retrieving the same clips from huge video collection is a hard job because of the presence of complex properties of visual data. Video clips have many frames and every frame has multiple properties that have many visual properties like color, shape, and texture. In this research, an efficient content-based video retrieval system using the AlexNet model of Convolutional Neural Network (CNN) on the keyframes system has been proposed. Firstly, select the keyframes from the video. Secondly, the color histogram is then calculated. Then the features of the color histogram are compared and analyzed for CBVR. The proposed system is based on the AlexNet model of CNN and color histogram, and extracted features from the frames are together to store in the feature vector. From MATLAB simulation results, the proposed method has been evaluated on benchmark dataset UCF101 which has 13320 videos from 101 action categories. The experiments of our system give a better performance as compared to the other state-of-the-art techniques. In contrast to the existing work, the proposed video retrieval system has shown a dramatic and outstanding performance by using accuracy and loss as performance evaluation parameters.

Copyright of Chinese Journal of Inorganic Analytical Chemistry / Zhongguo Wuji Fenxi Huaxue is the property of Beijing Research Institute of Mining & Metallurgy Technology Group and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This article presents a new approach based on deep learning to automatically extract colormaps from visualizations. After summarizing colors in an input visualization image as a Lab color histogram, we pass the histogram to a pre-trained deep neural network, which learns to predict the colormap that produces the visualization. To train the network, we create a new dataset of $\sim$ ∼ 64K visualizations that cover a wide variety of data distributions, chart types, and colormaps. The network adopts an atrous spatial pyramid pooling module to capture color features at multiple scales in the input color histograms. We then classify the predicted colormap as discrete or continuous, and refine the predicted colormap based on its color histogram. Quantitative comparisons to existing methods show the superior performance of our approach on both synthetic and real-world visualizations. We further demonstrate the utility of our method with two use cases, i.e., color transfer and color remapping. [ABSTRACT FROM AUTHOR]

Due to the posteriori knowledge provided by the Human-Computer Interaction algorithms, interactive segmentation based on Graph Cuts can successfully extract the foreground in an image, which will, however, limit the scope of their application. Inspired by recent years of research on computer vision with fully convolutional neural networks, a fully automated image segmentation method based on FCN and Graph Cuts has been proposed. First, FCN is employed to obtain an original mask for the input image, but its boundary is poor. Second, we generate seed regions heuristically using color histograms and mathematical morphological operations on the original mask. Finally, iterative segmentation is performed using generative seeds and superpixel-level Graph Cuts. Experimental results show that our method has higher segmentation accuracy compared to other representative methods including interactive and automatic segmentation. [ABSTRACT FROM AUTHOR]

Copyright of Laser Technology is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Content based image retrieval (CBIR) systems enable a quick retrieval of similar images from a large digital repository. However, the performance of the system is heavily reliant on the feature definition of images. The challenge lies in extracting suitable features that can work across a variety of datasets. In this paper, Haar-like local ternary co-occurrence pattern (HLTCoP) is designed as a feature for image retrieval applications. In HLTCoP, four different Haar-like filters are deployed to capture directional information of the image and two different local neighborhoods are considered to obtain the local patterns around every pixel. Thereafter, co-occurrence between two filtered images is computed to construct the HLTCoP feature. Additionally, color information is extracted using histograms of hue and saturation planes. Image retrieval performance is verified on diversified benchmark datasets, Corel 10k, CMU-PIE and MIT VisTex. Significant improvement is achieved in comparison to the existing techniques. [ABSTRACT FROM AUTHOR]

Emotions can be evoked in humans by images. Previous reports on Recognition of Emotions induced by Visual Content of images (REVC) mainly focused on numerous features to improve recognition performance. To devise a more robust REVC system, this paper examines the performance of a wide range of classifiers using color histogram as a single feature. Different numbers of color histogram bins in both RGB (red, green, blue) and HSV (hue, saturation, value) color spaces are considered in the examination and the overall classification performance is compared across the bin sizes. This investigation shows that features are not the only important factors affecting the performance of REVC systems, but also the type of classifiers and their parameters. This study shows that the HSV color space is better suited than the RGB color space for REVC systems. This paper proposes a new optimization algorithm called Optimizing Parameters of Ensemble RUSboosted Tree (OPERT) to boost the performance of the REVC system. Furthermore, a novel REVC system called Color histogram with Optimized RUSboosted Tree (CORT) is introduced. It is shown that our method is simpler, faster, and more efficient than the state-of-the-art, while providing comparable recognition performance. The robustness of the CORT system is validated over three different image datasets.

Correlation filter-based trackers have gained more and more attention because of their great performances and relative high tracking speeds. However, this kind of trackers may suffer model drifting due to learning limited background information during filter training. This may lead to tracking failures in some complex scenes, such as background clutter, deformation, illumination variation and so on. In this article, we propose an adaptive and complementary correlation filter with dynamic contextual constraints. First, we introduce contextual information around the target as a dynamic constrained term to alleviate model drifting in complex scenes, the optimal function of which can be solved by an iterative method. Then, we integrate a color histogram-based tracker to compensate the inaccurate tracking of correlation filtering. In addition, we present metrics to combine the two complementary trackers with adaptive fusion coefficients. Finally, extensive experiments on OTB2013, OTB2015, VOT2016 and UAV123 benchmark datasets demonstrate that our tracker can improve the performance of our baseline and can perform favorably against some state-of-the-art trackers.

In the paper, we propose color content descriptors of images by vector quantization in RGB color space in order to obtain a much more accurate discrete representation of this space using our algorithm for optimization of vector quantizers compared to scalar ones. We introduce several modifications of these descriptors such as global, structural as well as of dominant color. We consider a different number of bins and evaluated the similarity of the color content of images using mean square error of color histograms of a reference image and a searched image. Then, the color content of the image with the minimum error was the most similar to the reference image. We also used a parameter of variance, if the color content of several searched images was very similar based on the mean quadratic error for the structural descriptor.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Wireless capsule endoscope allows painless endoscopic imaging of the gastrointestinal track of humans. However, the whole procedure will generate a large number of capsule endoscopy images (CEIs) for reading and recognizing. In order to save the time and energy of physicians, computer-aided analysis methods are imperatively needed. Due to the influence of air bubble, illumination, and shooting angle, however, it is difficult to classify CEIs into healthy and diseased categories correctly for a conventional classification method. To this end, in the paper, a new feature extraction method is proposed based on color histogram, wavelet transform, and co-occurrence matrix. First, an improved color histogram is calculated in the HSV (hue, saturation, value) space. Meanwhile, by using the wavelet transform, the low-frequency parts of the CEIs are filtered out, and then, the characteristic values of the reconstructed CEIs’ co-occurrence matrix are calculated. Next, by employing the proposed feature extraction method and the BPNN (back propagation neural network), a novel computer-aided classification algorithm is developed, where the feature values of color histogram and co-occurrence matrix are normalized as the inputs of the BPNN for training and classification. Experimental results show that the accuracy of the proposed algorithm is up to 99.12% which is much better than the compared conventional methods.

Numerous object-tracking and multiple-person-tracking algorithms have been developed in the field of computer vision, but few trackers can properly address the issue of when a pedestrian is partially or fully occluded by other objects or persons. In order to achieve efficient pedestrian tracking in various occlusion conditions, a pedestrian tracking framework is proposed and developed based on the deep learning networks. First, a pedestrian detector is trained as a tracking mechanism based on the Faster R-CNN, which narrows the search range and efficiently improves accuracy, as compared with the traditional gradient descent algorithm. Second, in the process of target matching, a color histogram and scale-invariant feature transform are combined to provide the target model expression, and a full convolution network (FCN) is trained to extract the pedestrian information in the target model, based on an FCN image semantic segmentation algorithm that can remove background noise effectively. Finally, the extensive experiments on a commonly used tracking benchmark show that the proposed method achieves better performance than the other state-of-the-art trackers in various occlusion situations.