HSV Histogram Research Articles

Folk art classification using support vector machine

<p dir="ltr">Tremendous amounts of effort have been carried out every year by the governments of all the countries to preserve art and culture. Art in the form of paintings, artifacts, music, dance, and cuisines of every country has the utmost importance. The study of Tribal arts provides deep insight into our history and acts as a milestone in the roadmap of our future. This paper focuses on three popular folk arts namely: Gond, Manjusha, and Warli. 300 images of each artwork have been collected from various online repositories. To generate a robust system, data augmentation is applied which results in 7510 images. A feature vector based on a generalized co-occurrence matrix, local binary pattern, HSV histogram, and canny edge detector is constructed and classification is performed using a linear support vector machine. 10- fold cross-validation produces 99.8% accuracy.</p>

Multi-dimensional CNN Based Feature Extraction with Feature Fusion and SVM for Human Activity Recognition in Surveillance Videos

Background/Objectives: The accurate recognition of human activities from video sequences is very challenging due to low resolution, cluttered background, partial occlusion, and different viewpoints. Machine learning (ML) based automated HAR from surveillance videos is required with the fusion of various feature extraction techniques. Methods: In this paper, SVM with feature fusion is utilized for automatic recognition from surveillance videos. A Histogram of Oriented Gradient (HOG) is used to segment the frame to differentiate humans from other objects or background noise in the input video frames. The multi-feature extraction can be accomplished in terms of Gabor Wavelet Transform (GWT), Autocorrelogram, Gray-Level Co-Occurrence Matrix (GLCM), HSV histogram, and Multi-dimensional CNN. The proposed approach is implemented in MATLAB software and compared with existing approaches like Space-Time Interest Point (STIP) and Histogram of Optical Flow (HOF). Findings: The proposed approach outperforms the existing approaches in terms of reduced time consumption and high accuracy, 99.886% when using the UCF101 dataset and 99.538% when using the UTKinect dataset. Novelty: The most discriminative feature information is obtained with the feature-level fusion technique. From the feature information, various human actions are recognized with the classification algorithm. Keywords: Human activity recognition, Machine Learning, Surveillance Videos, Human detection algorithm, Feature extraction, SVM classifier

Comparison of color-based feature extraction methods in banana leaf diseases classification using SVM and K-NN

In Malaysia, banana is a top fruit production which contribute to the economy growth in agriculture field. Hence, it is significant to have a quality production of banana and important to detect the plant diseases at the early stage. There are many types of banana leaf diseases such as Banana Mosaic, Black Sigatoka and Yellow Sigatoka. These three diseases are related to color changes at banana. This research paper is an experiment based and need to identify the best color feature extraction method to classify banana leaf diseases. Total of 48 banana leaf images that are used in this research paper. Four types of color feature extraction methods which are color histogram, color moment, hue, saturation, and value (HSV) histogram and color auto correlogram are experimented to determine the best method for banana leaf diseases classification. While for the classifiers, support vector machine (SVM) and k-Nearest neighbors (k-NN) are used to evaluate the performance and accuracy of each color feature extraction methods. There are also preliminary experiments to identify accurate parameters to use during classification for both classifiers. Our experimental result express that HSV histogram is the best method to classify banana leaf diseases with 83.33% of accuracy and SVM classifier perform better compared to k-NN.

A 3D-printed robotic system for fully automated multiparameter analysis of drinkable water samples

This work describes a 3D-printed robotic system named RSAWA (robotic system for automatic water analysis) for fully automated water analysis. RSAWA consists of a robotic arm coupled to a syringe pump, temperature and conductivity sensors, a low-cost webcam as colorimetric detector, and a 96-well microplate placed on a 3D-printed platform. The robotic system is controlled by software and it performs all analytical procedures. RSAWA was applied to measure conductivity (CDT), pH, total alkalinity (TA), total hardness (TH), chloride (Cl−), nitrite (NO2−), total dissolved phosphorus (TP), and total iron (TI) in drinkable water samples. A simple circuit was designed for conductivity determinations, while colorimetric pH determinations were carried out using Hue values extracted from digital images and a pH universal indicator. HSV histograms were used to calculate Pearson's correlation coefficients, allowing the construction of accurate titration curves. In addition to achieving sample throughputs of 112 h−1 for TA and TH determinations and 92 h−1 for Cl− determinations, RSAWA produced 99.5% less waste than the corresponding reference methods during titrations. Colorimetric measurements were performed through RGB vector norms calculated from digital images were used as analytical signals. Limits of quantification (μg L−1) were 6.83, 13.0 and 1.5 mg L−1 for NO2−, TP, and TI determinations, respectively. Sample throughputs (samples h−1) were 83 for NO2− and TP and 72 for TI with a 98.5% reduction in waste generation. Thus, RSAWA is a low-cost, feasible, and environmentally friendly alternative to quickly and accurately determine several chemical and physicochemical parameters in aqueous samples.

Robust Magnification Independent Colon Biopsy Grading System over Multiple Data Sources

Automated grading of colon biopsy images across all magnifications is challenging because of tailored segmentation and dependent features on each magnification. This work presents a novel approach of robust magnification-independent colon cancer grading framework to distinguish colon biopsy images into four classes: normal, well, moderate, and poor. The contribution of this research is to develop a magnification invariant hybrid feature set comprising cartoon feature, Gabor wavelet, wavelet moments, HSV histogram, color auto-correlogram, color moments, and morphological features that can be used to characterize different grades. Besides, the classifier is modeled as a multiclass structure with six binary class Bayesian optimized random forest (BO-RF) classifiers. This study uses four datasets (two collected from Indian hospitals—Ishita Pathology Center (IPC) of 4X, 10X, and 40X and Aster Medcity (AMC) of 10X, 20X, and 40X—two benchmark datasets—gland segmentation (GlaS) of 20X and IMEDIATREAT of 10X) comprising multiple microscope magnifications. Experimental results demonstrate that the proposed method outperforms the other methods used for colon cancer grading in terms of accuracy (97.25%-IPC, 94.40%-AMC, 97.58%-GlaS, 99.16%-Imediatreat), sensitivity (0.9725-IPC, 0.9440-AMC, 0.9807-GlaS, 0.9923-Imediatreat), specificity (0.9908-IPC, 0.9813-AMC, 0.9907-GlaS, 0.9971-Imediatreat) and F-score (0.9725-IPC, 0.9441-AMC, 0.9780-GlaS, 0.9923-Imediatreat). The generalizability of the model to any magnified input image is validated by training in one dataset and testing in another dataset, highlighting strong concordance in multiclass classification and evidencing its effective use in the first level of automatic biopsy grading and second opinion.

A Framework for the Image Retrieval System Based on Histogram Normalization Technique with Python

The processing of multimedia content is used for real-world computer vision in various applications, and digital images make up a large part of multimedia data. The processing of multimedia content is used for real-computer vision in various applications, and digital images make up a large part of multimedia data. Content-based Retrieval of photographs (CBIR) is a system of picture recovery which utilizes the visual highlights of a picture, for example, shading, shape and surface so as to look through the client based inquiry pictures from the huge databases. CBIR relies upon highlight extraction of a picture which are the visual highlights and these highlights are extricated naturally i.e. without human collaboration. We intend in this paper to provide a detailed overview of recent developments related to CBIR and image representation. We researched the main aspects of various models of image recovery and image representation from low-level feature extraction to recent semantict ML approaches. And, for extraction of features, HSV, image segmentation and color histogram techniques are used, which effectively gives us the main point in an image that these techniques are used to minimize complexity, expense, and energy and time consumption. Then a machine learning model is trained for similarity test and the validation and texting phases are performed accordingly which leads to better performance as. Then a machine learning model is trained for similarity testing and then the validation and texting steps are performed accordingly, resulting in improved results compared to previously performed techniques. The precision values in the proposed technique are fairly excellent.

Privacy preserving search index for image databases based on SURF and order preserving encryption

Managing large personal image databases requires efficient privacy preserving indexing methods to allow for their outsourcing to possibly curious cloud servers. To construct a secure inverted index in this paper, first, visual words are extracted from stored images based on the Speeded-Up and Robust Features (SURF). Next, Order Preserving Encryption (OPE) is used to encipher the frequencies of occurrence of the extracted visual words. Another scale and rotation invariant feature, which is the local HSV histogram, is included for comparison. From the obtained results, it is apparent that SURF achieves more precise results. Aggregation of both features is considered to further improve the accuracy. The effects of the weighting scheme of the visual words and their number on the performance are investigated. Weighted term frequency inverse document frequency (tf-idf) together with the Jaccard similarity measure yield the best performance. OPE encryption is shown to have minor impact on the retrieval accuracy. To reduce encryption time, a lookup table is constructed. The inverted index reduces the search time significantly compared to a sequential search scheme as apparent from the results. A comparative study with recent related schemes demonstrates the competitiveness of the implemented system in terms of computational efficiency and accuracy.

A new encrypted image retrieval method based on feature fusion in cloud computing

The traditional image retrieval has high requirements on the computing power and storage capacity of the platform, so the cloud server has become the preferred choice for outsourcing image retrieval. However, the cloud server is not completely reliable, and outsourcing image retrieval may bring many security, low retrieval accuracy, and privacy problems. In this paper, an encrypted image retrieval method based on feature fusion is proposed. Firstly, the images are encrypted by the encryption operator. Then, the feature extractor is designed, and the enhanced RGB feature and HSV histogram feature are extracted. Finally, the feature extractor and encrypted images are uploaded to the cloud server. The computation of similarity between images is done in the cloud. The experiments and security analysis show that the proposed method has good security and accuracy.

Computer Vision Systems for Content-based Image Classification

In this paper, computer vision based Content-Based Image Classification systems have been described which are useful in various service and product industries. We have proposed Confidence Co-occurrence Matrix, which is a modification of Generalized Co-occurrence Matrix. The proposed framework merges properties of Confidence Co-occurrence Matrix along with other features such as RGB and HSV Histograms, Local Binary Pattern and Canny’s edge detection approach. Proposed approach creates a fixed- size descriptor of size 1632. Once a feature vector has been constructed, classification is performed using Linear Support Vector Machine. The System is tested on four different wellknown datasets namely, sport events Database, Flavia Leaf Dataset, Leeds Butterfly Dataset and Birds Dataset . The proposed system is implemented in MATLAB and achieves an average class accuracy of 96%, 99%,95% and 95% for the four datasets respectively

Determination of Color and Shape Features Based Image Retrieval with Hybrid Feature Descriptor Construction (HFDC)

Objectives: To implement a hybrid feature descriptor construction (HFDC) model to exercise the CBIR. Method/analysis: The model that combines color and shape features of visual content to produce a feature level fusion scheme is introduced. The RGB histogram, HSV histogram and the canny edge histogram features are extracted and fused to produce a hybrid feature vector. Then the determined feature vector through the fusion of the entire dataset is used to train the SVM using RBF kernel to retrieve relevant visual content through identifying the color distribution, and shape is focused here as the main objective. Since from the very beginning of the data usage to surf web information the classification of the similar related objects has been potentially provided a helpful contribution towards helping the users to identify and determine required knowledge from the large corpus of available digital information. Many algorithms and improvements have been in implementation, but the large quantity of available information provides complexity to these techniques to enhance computational hike. This feature level fusion contributes to reducing the overhead. Finding: The HFDC evolutions significantly contribute to achieving an accuracy of 84.60%. The experimental results have proven the efficiency of the HFDC by providing the maximum classification accuracy. Novelty: The results evidently show that (1) HDFC improve the performance by enhancing the feature level fusion process, (2) the fusion procedure produces increased solid and high indicative rendering and (3) by performing feature level fusion of data a core dictionary is provided for better CBIR performance. Improvement: In addition to color and shape feature fusion the texture features can also be combined to improve the performance significantly.Keywords: CBIR, HFDC, RGB, HSV, Canny

Hybrid Saliency-SVM Method Implementation for Automatic Data Training Selection in Image Segmentation

Image segmentation is one of the most important step in computer vision and image processing, which later will be used in image retrieval, object identifying and data classification. Image segmentation can be seen as classification problem, namely by marking each pixels according to certain characteristics. Support Vector Machine (SVM) is a classification method included in supervised learning. Supervised learning is a method which requires training and testing. Training sample used in training process isn’t always exist in few cases, especially in the image segmentation case. This particular research implemented SVM-based method which is Saliency-SVM for automatic data training selection in image segmentation. This method generates data training using SVM-based visual saliency detection where there is pre-segmentation step and trimap formation based on saliency information from visual saliency detection, HSV color space quantitation, histogram analysis and local homogeneity threshold. Data training produced is pixel belonging to positive (object) and negative (background). The step before segmentation done with SVM is feature extraction to create input vector in SVM. Object segmentation on the image is done by SVM based on SVM Trained Model. Test result from Saliency-SVM for this image segmentation has average accuracy value up to 94,84 % compared to the image ground truth

Classification of Mammograms using Various Feature Extraction Methods and Machine Learning

Breast cancer is an alarming disease which takes millions of lives every year. In 2018, it was anticipated that 627,000 women died due to breast cancer – which is around 15% of all deaths caused due to different types of cancers among women. Currently, risk factors of breast cancer cannot be avoided, and early detection is the only way of survival. Automated detection of breast cancer with the help of image processing methods and machine learning algorithms helps in giving more accurate results and less human power. In the proposed system, multiple features are extracted using HSV histogram, LBP, GLCM, 2-D DWT. Support vector machine and LIBSVM classifiers are used for the classification of mammogram images if it’s benign or malign in nature. For classification, the INbreast dataset have been used which includes 115 cases containing 410 images. The dataset is divided into benign and malign category based upon BI-RAIDS scale. According to this partition we have 243 benign images and 100 malign images present in this dataset and a feature matrix of 595 features in total is generated for balanced and unbalanced datasets respectively and fed into SVM and LIBSVM to distinguish the data. The balanced datasets on LIBSVM gave best results with 92% accuracy, 84% sensitivity, 100% specificity and 91.30% F1 score followed by SVM which gave 75% accuracy, 73.61% sensitivity, 76.66% specificity and 75.8% F1 score.

Content-Dependent Image Search System for Aggregation of Color, Shape and Texture Features

The existing image search system often faces difficulty to find a appropriate retrieved image corresponding to an image query. The difficulty is commonly caused by that the users’ intention for searching image is different with dominant information of the image collected from feature extraction. In this paper we present a new approach for content-dependent image search system. The system utilizes information of color distribution inside an image and detects a cloud of clustered colors as something - supposed as an object. We applies segmentation of image as content-dependent process before feature extraction in order to identify is there any object or not inside an image. The system extracts 3 features, which are color, shape, and texture features and aggregates these features for similarity measurement between an image query and image database. HSV histogram color is used to extract color feature of image. While the shape feature extraction used Connected Component Labeling (CCL) which is calculated the area value, equivalent diameter, extent, convex hull, solidity, eccentricity, and perimeter of each object. The texture feature extraction used Leung Malik (LM)’s approach with 15 kernels. For applicability of our proposed system, we applied the system with benchmark 1000 image SIMPLIcity dataset consisting of 10 categories namely Africans, beaches, buildings historians, buses, dinosaurs, elephants, roses, horses, mountains, and food. The experimental results performed 62% accuracy rate to detect objects by color feature, 71% by texture feature, 60% by shape feature, 72% by combined color-texture feature, 67% by combined color-shape feature, 72 % combined texture-shape features and 73% combined all features.

The study of security application of LOGO recognition technology in sports video

With the rapid development of information technology and network technology and the rapid popularization of computers and intelligent devices, network video media have gradually replaced traditional media and became the main carrier of information production, storage, dissemination, sharing, and use. However, digital information can be easily copied, modified, and disseminated, which leads to the problem of network video copyright theft which is very prominent. Aiming at the copyright problem of sports video, this paper proposes an idea of using LOGO to identify the copyright of sports video, which can automatically and effectively detect whether the video is genuine or not. Firstly, encrypted LOGO is added to the video by encryption technology, and then, LOGO recognition technology is used to distinguish whether the LOGO is missing in the video, so as to distinguish the legitimacy of the video. In addition, aiming at the shortcomings of traditional LOGO recognition technology, this paper proposes a LOGO detection and recognition technology based on convolution neural network. This method improves the traditional histogram algorithm, proposes an analysis algorithm based on non-uniform block HSV histogram, and introduces region weighting coefficients to extract key frames from the video. Then, the convolution neural network is used to extract the features of the key frames of the video. Finally, the features of the sample LOGO are matched to complete the LOGO detection and recognition. Simulation results show that the effect of feature extraction using convolution neural network is better. Compared with the traditional LOGO recognition technology, the LOGO detection and recognition technology based on convolution neural network proposed in this paper has better detection and recognition performance. It effectively detects the LOGO information in the video and realizes the recognition of whether the video is genuine or not.

Розробка пристрою для автоматичного фенотипування насіннєвого матеріалу соняшнику

Seed phenotyping is the process of typing, determining, identifying and dividing seeds, as a breeding material, according to its morphological and marker features. Technical and technological support of the process of automatic phenotyping of seeds is based on algorithms and methods for processing images of seeds. The aim of the research is to increase the efficiency of the sunflower breeding and seed process by developing and using a device for automatic phenotyping of seed material. An algorithm for identifying and calculating the geometric dimensions and color of seeds, on which the device for automatic phenotyping of sunflower seed is based, has been developed and experimentally verified. The specified algorithm is implemented in software that uses OpenCV libraries. The software allows identification of sunflower seeds by its geometric dimensions (length L, width B and their ratio) in the HSV color space and histograms of the distribution of colors of the RGB region of the seed. A device has been developed for automatic phenotyping of seeds, which preserves the accuracy of individual measurement of the geometric dimensions of sunflower seeds, determining their shape and color corresponding to modern measuring tools, and provides low labor intensity and high manufacturability of the implementation of the procedure of phenotyping seeds as a selection material, according to its morphological and marker features.

A Novel Real Time Visual Tracking Method Using Modified Flower Pollination Algorithm

This study presented a novel algorithm, namely, modified flower pollination algorithm (MFPA), for moving object tracking in real time video. Three variables, i.e., x-coordinate, y-coordinate and width, known as search window, were used to represent the features of the target object. The image within the search window was extracted, and used to calculate the Hue, Saturation, and Value (HSV) histogram. The HSV histogram was then used as a feature model of the target object. Subsequently, the MFPA will search for an optimal match of the target using Bhattacharyya distance as the fitness function. Simulation results demonstrated that the MFPA outperformed FPA in the aspect of higher accuracy, where 75.35% and 92.13% of improvements were observed in two considered case studies.

Image Retrieval Using CBIR Including Light Position Analysis

We propose a method for estimating the weight of the light source position to content-based image retrieval (CBIR) through retrieving image data. The image retrieval method makes use of a multi-dimensional descriptor expressing the features of the image. A multi-directional Gabor filter is then applied in order to extract the contour direction of the image, and a color correlation is applied in order to analyze the distribution of the position between the colors in the image. An HSV histogram and chromatic distribution information were obtained for the color composition analysis, and the light source position in the image was estimated for the main region extraction. The relative similarity between the images was measured through a relative comparison between each descriptor. In conventional image retrieval, there is a disadvantage in terms of the large computational intensity required, because the accuracy is degraded when simple information is used or when the result is estimated through a comparison of complex image components. However, the proposed method adds a light source location analysis element in order to ensure accurate retrieval. Image retrieval using the proposed method achieves an average retrieval accuracy of 85%, indicating that its reliability is superior to that of previously described methods.

Secure and Efficient Image Retrieval over Encrypted Cloud Data

This paper proposes a novel image retrieval scheme over encrypted cloud data, which achieves high efficiency and confidentiality. For the purpose of improving search efficiency, an index tree is often deployed in the image retrieval scheme. Meanwhile, the confidentiality of the sensitive cloud data, such as outsourced images, index tree, and query request, is also a key issue. Firstly, a balanced binary clustering algorithm is exploited over the integrated image features composed of basic features, such as HSV histogram and DCT histogram, yielding a balanced binary tree (BBT). In particular, due to the adoption of a balanced index tree, our scheme can achieve logarithmic search time. Secondly, the secure inner product is employed to encrypt the index vector and query feature. Finally, to resist the statistical attack of the frequency distribution of the retrieved results, we copy the database and merge the subtree of encrypted BBT to blind the search results. Security analysis and experimental results show that the proposed scheme is secure and efficient.

Content-based high-resolution satellite image classification

Content-based image classification has produced successful and automated applications in various service and product industries. In this paper, high-resolution satellite scene classification based on multiple feature combination is considered. We have proposed confidence co-occurrence matrix, which is a modification of the generalized co-occurrence matrix. The proposed framework combines RGB histogram, HSV histogram, local binary pattern, confidence co-occurrence matrix properties and Canny’s edge detection approach. The approach creates a fixed-size feature vector of size 1632. Once a feature vector has been constructed, classification is performed using linear support vector machine. The system is tested using widely popular benchmark Satellite Scene dataset and UC Merced land used dataset having 19 and 21 classes respectively. The proposed system also works well in agricultural science. The system is also tested on folio dataset having 32 species of leaf. The proposed system is implemented in MATLAB and achieves an average class classification accuracy of 99%.

Homogeneity patch search method for voting-based efficient vehicle color classification using front-of-vehicle image

Color classification plays a significant role in tracking crime vehicles. Color features can be used to classify vehicle color using a front-of-vehicle image acquired from CCTV. In this paper, we define a new color homogeneity patch and propose search method that focuses on improving the discernment of features by avoiding another color distribution, not a vehicle color, which is included in the vehicle color features. In addition, we could effectively improve this method by using a voting strategy. A region of interest (ROI) that includes a bonnet is detected using predefined information about the given car and the search method is applied to ROI for selecting color homogeneity patches. The proposed approach extracts an HSV histogram for each patch, and adopts the multi-class Adaboost algorithm to classify the color of each patch. We integrate the proposed method with the voting strategy to determine the color of the vehicle. To validate the feasibility of our approach, we compare the results with a sliding window without consideration of homogeneity. Results show that the search method for homogeneity patches can be efficiently applied to recognize vehicle color.