Statistical Color Features Research Articles

Melanoma classification employing inter neighbor statistical color and mean order pattern texture feature

Automatic melanoma diagnosis is very important to lower the mortality rate by detecting the disease in earlier stages and accurate diagnosis. The main aim of this paper is to improve the classification accuracy of melanoma using a proposed novel color and texture feature descriptor. Initially, the skin lesion area of input dermoscopy image is segmented using a convolutional neural network-based U-Net algorithm. Then extract discriminate color, texture and combined color-texture features with the help of proposed Inter Neighbor Statistical Color Feature (INSCF), Inter Neighbor Mean Order Pattern (INMOP) and Inter Neighbor Statistical Color Mean Order Pattern (INSCMOP) by incorporating inter color channel values. This proposed feature descriptors are capable to discriminate the detailed information derived from spatial inter-chromatic texture patterns of different channels within a region. Finally, three classifiers namely, K-Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machine (SVM) are used to classify the skin lesion in a dermoscopic image as benign lesion or melanoma. Experimental results indicate that the proposed INSCMOP with Random Forest classifier achieves the highest classification performance based on accuracy of 93.27% for ISIC 2016 dataset, 86% for ISIC 2017 dataset and 92.31% for ISBI 2019 dataset. Moreover, comparing the proposed method with other systems shows that this approach has an excellent performance in melanoma classification. In this research, without any manual interaction, the classification process is performed in an automated way. It would set up a valuable assistance for dermatologist in clinical practice.

Colour Feature Extraction Techniques for Real Time System of Oil Palm Fresh Fruit Bunch Maturity Grading

According to the natural ripeness phenomena of oil palm fruit, the oil palm fresh fruit bunch (FFB) ripeness is divided into three different categories called, under ripe, ripe, and overripe. The current method in the mills for oil palm FFB grading is manually using human graders. However, the manual grading method is subjective and prone to human errors. Thus, accurate classification of oil palm FFB with fast and easy process is necessary in oil palm farms and in the palm oil industry to grade high-quality products, especially when classifying a large amount of fruits. In this paper, an image processing algorithm scenario represented by image acquisition, segmentation, and feature extraction is implemented in real time system for oil palm FFB maturity grading. This study presents an automated inspection for the oil palm FFB using an external grading system processing based on the colour feature extraction technologies; namely, color histogram and statistical color feature (mean and standard deviation), were used to extract the oil palm FFB image’s color features. An artificial neural network (ANN) classifier as supervised machine learning technique is applied to train and test the system performance accuracy based on area under curve (AUC) of the receiver operation characteristic (ROC) as classifier performance evaluation. The result show that the colour histogram technique based on the ANN classifier was observed to be a more robust and accurate classifier, with overall 94% correct ripeness classification accuracy, for oil palm FFB maturity grading compared to the other techniques applied and tested in this study.

Scale-adaptive Correlation Filter Tracking Algorithm Combined with Statistical Color Histogram Feature

The algorithm based on kernel correlation filtering shows excellent performance. Aiming at the problem that traditional correlation filtering algorithms are sensitive to deformation and cannot solve the tracking failure caused by scale changes, this paper proposes a scale-adaptive correlation filtering algorithm combining statistical color feature. Firstly, predict and train the HOG features of the correlation filter and the color histogram features to obtain the respective response values, namely the template response and the histogram response. Then adopt the block method, and perform scale prediction based on the position of each response point. Finally, the final fusion response is calculated. The experimental results demonstrate that compared with traditional KCF, when the target scale has large scale change and deformation, the improved algorithm in this paper performs better, and can still track stably.

Healthy Fruits Image Label Categorization through Color Shape and Texture Features Based on Machine Learning Algorithm

The fruit categorization according to their visual quality has recently experienced tremendous growth in the field of agriculture and food products. Due to post-harvest loses during handling and processing, there is an increasing demand for quality products in agro industry which requires accuracy to predict the fruit. Various techniques of machine learning have been successfully applied for classifying the fruit built on binary class. In this paper, machine leaning technique is used to automate the process of categorization and to improve the accuracy of different types of fruits by feature selection. To categorized images domain specific features such as color, shape and textual features are considered. Statistical color features are extracted from the image, bounding box feature for shape features and gray-level co-occurrence matrix (GLCM) is used to extract the textual feature of an image. These features are combined in a single feature fusion. A support vector machine (SVM) classification model is trained using training set features on fruit360 dataset which includes six fruit categories (classes) with two sub category (sub-classes) which builds multiclass classification task. We present one-vs-one coding design of Error correcting output codes (ECOC) and apply to SVM classifier; validation followed a fivefold cross validation strategy. The result shows that the textual features combined with color and shape feature improved fruit classification accuracy.

Actinobacterial strains recognition by Machine learning methods

Recognition of actinobacterial species on solid culture plates is an error-prone and time-consuming process which retard all the down-stream process after the isolation step. In this paper, we propose an optimized solution for the mentioned problem by using machine learning and image processing algorithms to diminish the cost and time and increase the accuracy of the detection. Three methods are compared in this paper for actinobacterial strains recognition. In the first method, two-level wavelet transform is applied on images of actinobacterial strains and statistical texture features are computed from wavelet subbands. Furthermore, some statistical color features are calculated from color information. In consequence, Principle Component Analysis (PCA) is employed for dimension reduction and finally, a Multi-Layer Perceptron (MLP) neural network was used for classification. In the second method, a Convolution Neural Network (CNN) is used to extract the features automatically. In the third method, transfer learning is employed for feature extraction and classfication. The first method is evaluated on two databases, UTMC.V1.DB and UTMC.V2.DB, and the accuracy obtained between 80.8% to 80.1%, respectively. Employing CNN as the feature extractor improved the accuracy about 4%. Transfer learnig results 85.96% accuracy on the UTMC.V2.DB and 91.90% on the subclasses of UTMC.V2.DB. The experiments have shown that using transfer learning of DCNN of type ResNet has better performance compared to the pervious methods. The proposed methods are universal and can be used for recognition of other circle-like colony-shape microorganisms. In particular, giving limited and unbalanced training data, which is a common failure in biological data sets, the proposed methods harbor remarkable accuracy. The data augmentation methods showed to be efficient and practical for the current purpose along with being easy to be implemented and integrated.

Adaptive Contour Feature and Color Feature Fusion for Monocular Textureless 3D Object Tracking

Contour-matching-based textureless 3-D object tracking algorithms commonly use 3-D–2-D correspondence between the 3-D object model and 2-D object contour in the image to track the 3-D object. However, this often fails in highly cluttered backgrounds or in presence of motion blur. To overcome this problem, we propose a monocular textureless 3-D object tracking method based on adaptive fusion of contour feature and color feature. First, contour matching and local color statistics are performed nearby the projection contour of 3-D model to extract contour feature and color feature. Then, the energy function is defined based on adaptively weighted contour feature and statistical color feature, and the differentials of this energy function with respect to pose parameters of the 3-D object are derived. Finally, the optimal pose is obtained via LM solver. To deal with fast motion of object and camera, a coarse-to-fine tracking strategy is applied iteratively for multi-scale video frames. Qualitative and quantitative experiments show that the proposed algorithm has a great advantage over other state-of-the-art algorithms in the case of cluttered background and motion blur, and can obtain more accurate and robust tracking results.

Hybrid Neural Network and Linear Model for Natural Produce Recognition Using Computer Vision

Natural produce recognition is a classification problem with various applications in the food industry. This paper proposes a natural produce recognition method using computer vision. The proposed method uses simple features consisting of statistical color features and the derivative of radius function. A hybrid neural network and linear model based on a Kalman filter (NN-LMKF) was employed as classifier. One thousand images from ten categories of natural produce were used to validate the proposed method by using 5-fold cross validation. The experimental result showed that the proposed method achieved classification accuracy of 98.40%. This means it performed better than the original neural network and k -nearest neighborhood.

MCLOUD: A Multiview Visual Feature Extraction Mechanism for Ground-Based Cloud Image Categorization

AbstractIn this paper, a novel Multiview CLOUD (mCLOUD) visual feature extraction mechanism is proposed for the task of categorizing clouds based on ground-based images. To completely characterize the different types of clouds, mCLOUD first extracts the raw visual descriptors from the views of texture, structure, and color simultaneously, in a densely sampled way—specifically, the scale invariant feature transform (SIFT), the census transform histogram (CENTRIST), and the statistical color features are extracted, respectively. To obtain a more descriptive cloud representation, the feature encoding of the raw descriptors is realized by using the Fisher vector. This is followed by the feature aggregation procedure. A linear support vector machine (SVM) is employed as the classifier to yield the final cloud image categorization result. The experiments on a challenging cloud dataset termed the six-class Huazhong University of Science and Technology (HUST) cloud demonstrate that mCLOUD consistently outperforms the state-of-the-art cloud classification approaches by large margins (at least 6.9%) under all the different experimental settings. It has also been verified that, compared to the single view, the multiview cloud representation generally enhances the performance.

Natural Produce Classification Using Computer Vision Based on Statistical Color Features and Derivative of Radius Function

In agriculture industry, natural produce classification is used in sorting, grading, measuring, and pricing. Currently, a lot of methods have been developed using computer vision to replace human expert in natural produce classification. However, some of the method used long features descriptor and complex classifier to obtain high classification rate. This paper proposes natural produce classification method using computer vision based on simple statistical color features and derivative of radius function. The k-nearest neighbors (k-NN) and artificial neural network (ANN) were used to classify the produce based on the extracted features. Preliminary experiment results show that the proposed method achieved best result with average classification accuracy of 99.875% using ANN classifier with nine nodes in hidden layer.

A Hierarchical Segmentation Approach towards Roads and Slopes for Collapse Recognition

Color image processing is widely used in Intelligent Transport System, but seldom used in recognition of roads and slopes collapse. The application can reduce time and efforts. And the roads and slopes segmentation is the first and key step of the recognition system, which is a challenging and difficult problem. One of the problems is the presence of different types of roads and slopes. In this paper, we propose a novel framework for segmenting road images in a hierarchical manner that can separate the following objects: road and slopes with or without collapse, sky, road signs, cars, buildings and vegetation from the images. Then the Region of Interests (ROIs), i.e. the roads and slopes, are obtained with the geometrical, location of the objects and statistical color features which are extracted based on L*a*b color space and Gabor filter. According to combination K-means clustering with region merging, connected-component algorithm and morphological operation, the roads and slopes are segmented. The hierarchical approach does not assume the roads are present in the same type and assume the road images can be captured from arbitrary angles. The experiments show that the approach in this paper can achieve a satisfied result on various road images.

Scene Classification Algorithm Based on Contextual Semantic Information Extended PLSA Model

In this paper, a novel scene classification algorithm based on contextual visual words combined with extended PLSA model is proposed in which the traditional visual words by contextual information are improved. First, the EICS-LBP (Edge Improved Center Symmetric Local Binary Pattern) and statistical domain color features are extracted from the edge dense sampling region and its 8 neighborhood followed by the computed normalized histogram intersection and the creation of the new feature by linear combination of local information and its contextual intersection information. The visual vocabulary is formed by clustering from dense sampling regions respectively. Then the Bag-Of-Words model is used to describe the image which gives us richer information of scene images and reduces ambiguities and errors. Finally, the potential semantics by extended PLSA model and the confusion table by KNN classifier are obtained. Experiment results show that this method could achieve a higher accuracy, especially performing well in multi-edge color images with contextual information. Besides, it does not require manual annotation on the scene.

A Novel Segmentation Method of Roads and Slopes for Collapse Recognition

Color image processing is seldom used in the recognition of roads and slopes collapse. And the application can bring great advantages to the traffic safety. Color image segmentation is the first and key step of the recognition system. By analyzing existing methods of color image segmentation, several drawbacks have been discovered. This paper proposed a novel and efficient segmentation approach which is suitable for the recognition of collapse. The Region of Interests (ROIs), i.e. the roads and slopes, was obtained with the ingenious use of the images characters. According to combine K-means clustering with region merging, connected-component algorithm and close operation, the roads and slopes are segmented with the statistical color features, geometrical features and the location of the objects. Experimental result shows feasibility and efficiency of the proposed approach.

Cloud detection and classification with the use of whole-sky ground-based images

A simple whole sky imaging system, based on a commercial digital camera with a fish-eye lens and a hemispheric dome, is used for the automatic estimation of total cloud coverage and classification. For the first time, a multi color criterion is applied on sky images, in order to improve the accuracy in detection of broken and overcast clouds under large solar zenith angles. The performance of the cloud detection algorithm is successfully compared with ground based weather observations. A simple method is presented for the detection of raindrops standing on the perimeter of hemispheric dome. Based on previous works on cloud classification, an improved k-Nearest-Neighbor algorithm is presented, based not only on statistical color and textural features, but taking also into account the solar zenith angle, the cloud coverage, the visible fraction of solar disk and the existence of raindrops in sky images. The successful detection percentage of the classifier ranges between 78 and 95% for seven cloud types.

Analysis and Comparison of Color Features for Content Based Image Retrieval

Creation of a content-based image retrieval system implies solving a number of difficult problems, including analysis of low-level image features and construction of feature vectors, multidimensional indexing, design of user interface, and data visualization. Color is one of the important features used in CBIR systems. The methods of characterizing color fall into two major categories:Â Histograms and Statistical. An experimental comparison of a number of different color features for content-based image retrieval presented in these paper. The primary goal is to determine which color feature is most efficient in representing the spatial distribution of images. In this paper, we analyze and evaluate both Statistical and Structural color features. For the experiments, publicly available image databases are used. Analysis and comparison of individual color features are presented