Search

The main aim of the presented research was to assess the possibility of utilizing geometric features in object classification.Studies were conducted using X-ray images of kernels belonging to three different wheat varieties: Kama, Canadian andRosa. As a part of the work, image processing methods were used to determine the main geometric grain parameters,including the kernel area, kernel perimeter, kernel length and kernel width. The results indicate significant differencesbetween wheat varieties, and demonstrates the importance of their size and shape parameters in the classification process.The percentage of correctness of classification was about 92% when the k-Means algorithm was used. A classificationrate of 93% was obtain using the K-Nearest Neighbour and Support Vector Machines. Herein, the Rosa variety was betterrecognized, whilst the Canadian and Kama varieties were less successfully differentiated.

A proper classification of 3D point clouds allows fully exploiting data potentiality in assessing and preserving cultural heritage. Point cloud classification workflow is commonly based on the selection and extraction of respective geometric features. Although several research activities have investigated the impact of geometric features on classification outcomes accuracy, only a few works focused on their accuracy and reliability. This paper investigates the accuracy of 3D point cloud geometric features through a statistical analysis based on their corresponding eigenvalues and covariance with the aim of exploiting their effectiveness for cultural heritage classification. The proposed approach was separately applied on two high-quality 3D point clouds of the All Saints’ Monastery of Cuti (Bari, Southern Italy), generated using two competing survey techniques: Remotely Piloted Aircraft System (RPAS) Structure from Motion (SfM) and Multi View Stereo (MVS) techniques and Terrestrial Laser Scanner (TLS). Point cloud compatibility was guaranteed through re-alignment and co-registration of data. The geometric features accuracy obtained by adopting the RPAS digital photogrammetric and TLS models was consequently analyzed and presented. Lastly, a discussion on convergences and divergences of these results is also provided.

The extraction of road information from high-resolution remotely-sensed images has important application value in many fields. Rural roads have the characteristics of relatively narrow widths and diversified pavement materials, these characteristics can easily lead to problems involving the similarity of the road texture with the texture of surrounding objects and make it difficult to improve the automation of traditional high-precision road extraction methods. Based on this background, a semi-automatic rural road extraction method constrained by a combination of geometric and texture features is proposed in this paper. First, an adaptive road width extraction model is proposed to improve the accuracy of the initial road centre point. Then, aiming at the continuous change of curvature of rural roads, a tracking direction prediction model is proposed. Finally, a matching model under geometric texture constraints is proposed, which solves the problem of similarity between road and neighbourhood texture to a certain extent. The experimental results show that by selecting different types of experimental scenes or remotely sensed image data, compared with other methods, the proposed method can not only guarantee the road extraction accuracy but also improve the degree of automation to a certain extent.

The aim of this study was to evaluate the usefulness of the texture and geometric parameters of endocarp (pit) for distinguishing different cultivars of sweet cherries using image analysis. The textures from images converted to color channels and the geometric parameters of the endocarp (pits) of sweet cherry &lsquo, Kordia&rsquo, &lsquo, Lapins&rsquo, and &lsquo, B&uuml, ttner&rsquo, s Red&rsquo, were calculated. For the set combining the selected textures from all color channels, the accuracy reached 100% when comparing &lsquo, vs. &lsquo, for all classifiers. The pits of &lsquo, as well as &lsquo, were also 100% correctly discriminated for discriminative models built separately for RGB, Lab and XYZ color spaces, G, L and Y color channels and for models combining selected textural and geometric features. For discrimination &lsquo, pits, slightly lower accuracies were determined&mdash, up to 93% for models built based on textures selected from all color channels, 91% for the RGB color space, 92% for the Lab and XYZ color spaces, 84% for the G and L color channels, 83% for the Y channel, 94% for geometric features, and 96% for combined textural and geometric features.

We present a deep learning framework for efficient large-scale 3D point cloud analysis and classification using the designed feature description matrix (FDM). As the 3D points are unordered in the large-scale scene, and no topology structure can be employed directly for classification and recognition, it is difficult to apply deep neural network directly on 3D point clouds as points cannot be arranged in a fixed order as 2D image pixels. We design a new pipeline for 3D data processing by combining the traditional features extraction method and deep learning method. Our FDM encapsulates the 3D features of the point and can be used as the input of the deep neural network for training and testing. The experiments demonstrate that our method can acquire higher classification accuracy compared with our previous work and other state-of-art works.

Continuous monitoring of frail individuals for detecting dangerous situations during their daily living at home can be a powerful tool toward their inclusion in the society by allowing living independently while safely. To this goal we developed a pose recognition system tailored to disabled students living in college dorms and based on skeleton tracking through four Kinect One devices independently recording the inhabitant with different viewpoints, while preserving the individual’s privacy. The system is intended to classify each data frame and provide the classification result to a further decision-making algorithm, which may trigger an alarm based on the classified pose and the location of the subject with respect to the furniture in the room. An extensive dataset was recorded on 12 individuals moving in a mockup room and undertaking four poses to be recognized: standing, sitting, lying down, and “dangerous sitting.” The latter consists of the subject slumped in a chair with his/her head lying forward or backward as if unconscious. Each skeleton frame was labeled and represented using 10 discriminative features: three skeletal joint vertical coordinates and seven relative and absolute angles describing articular joint positions and body segment orientation. In order to classify the pose of the subject in each skeleton frame we built a two hidden layers multi-layer perceptron neural network with a “SoftMax” output layer, which we trained on the data from 10 of the 12 subjects (495,728 frames), with the data from the two remaining subjects representing the test set (106,802 frames). The system achieved very promising results, with an average accuracy of 83.9% (ranging 82.7 and 94.3% in each of the four classes). Our work proves the usefulness of human pose recognition based on machine learning in the field of safety monitoring in assisted living conditions.

Neurons are the basic building and computational units of the nervous system, and have complex and diverse spatial geometric structures. By solving the neuronal classification problem, we can further understand the characteristics of neurons and the process of information transmission. This paper presents a neuronal morphology classification approach based on locally cumulative connected deep neural networks, where 43 geometric features were extracted from two different neuron datasets and applied to classify types of neurons. Then, the effects of different parameters of deep learning networks on the performance of neuron classification were analyzed including mini-batch size, number of intermediate layers, and number of building blocks. The accuracy of the approach was also compared with that of the other mainstream machine learning approaches. The experimental results showed that the proposed approach is effective for solving complex neuronal morphology classification problems.

Due to the close resemblance between overlapping and cancerous nuclei, the misinterpretation of overlapping nuclei can affect the final decision of cancer cell detection. Thus, it is essential to detect overlapping nuclei and distinguish them from single ones for subsequent quantitative analyses. This paper presents a method for the automated detection and classification of overlapping nuclei from single nuclei appearing in cytology pleural effusion (CPE) images. The proposed system is comprised of three steps: nuclei candidate extraction, dominant feature extraction, and classification of single and overlapping nuclei. A maximum entropy thresholding method complemented by image enhancement and post-processing was employed for nuclei candidate extraction. For feature extraction, a new combination of 16 geometrical and 10 textural features was extracted from each nucleus region. A double-strategy random forest was performed as an ensemble feature selector to select the most relevant features, and an ensemble classifier to differentiate between overlapping nuclei and single ones using selected features. The proposed method was evaluated on 4000 nuclei from CPE images using various performance metrics. The results were 96.6% sensitivity, 98.7% specificity, 92.7% precision, 94.6% F1 score, 98.4% accuracy, 97.6% G-mean, and 99% area under curve. The computation time required to run the entire algorithm was just 5.17 s. The experiment results demonstrate that the proposed algorithm yields a superior performance to previous studies and other classifiers. The proposed algorithm can serve as a new supportive tool in the automated diagnosis of cancer cells from cytology images.

During localization and mapping the success of point cloud registration can be compromised when there is an absence of geometric features or constraints in corridors or across doorways, or when the volumes scanned only partly overlap, due to occlusions or constrictions between subsequent observations. This work proposes a strategy to predict and prevent laser-based localization failure. Our solution relies on explicit analysis of the point cloud content prior to registration. A model predicting the risk of a failed alignment is learned by analysing the degree of spatial overlap between two input point clouds and the geometric constraints available within the region of overlap. We define a novel measure of alignability for these constraints. The method is evaluated against three real-world datasets and compared to baseline approaches. The experiments demonstrate how our approach can help improve the reliability of laser-based localization during exploration of unknown and cluttered man-made environments.

The Iterative Closest Points (ICP) algorithm is the mainstream algorithm used in the process of accurate registration of 3D point cloud data. The algorithm requires a proper initial value and the approximate registration of two point clouds to prevent the algorithm from falling into local extremes, but in the actual point cloud matching process, it is difficult to ensure compliance with this requirement. In this paper, we proposed the ICP algorithm based on point cloud features (GF-ICP). This method uses the geometrical features of the point cloud to be registered, such as curvature, surface normal and point cloud density, to search for the correspondence relationships between two point clouds and introduces the geometric features into the error function to realize the accurate registration of two point clouds. The experimental results showed that the algorithm can improve the convergence speed and the interval of convergence without setting a proper initial value.

Background: Melanoma is a type of threatening pigmented skin lesion, and as of now is among the most hazardous existing diseases. Suitable automated diagnosis of skin lesions and Melanoma classification can extraordinarily enhance early identification of melanomas. Methods: However, classification models based on deterministic skin lesion can influence multi-dimensional nonlinear problem which leads to inaccurate and inefficient classification. This paper presents a Deep Convolutional Neural Network (DCNN) classification approach for segmented skin lesions in dermoscopy images. As an initial step, the skin lesion is preprocessed by an automatic preprocessing algorithm together with a fusion hair detection and removal strategy. Also a new probability map based region growing and optimal thresholding algorithm is integrated in our system which yields tremendous accuracy. Results: For obtaining more prominent results a set of features containing ABCD features as well as geometric features are calculated in the feature extraction step to describe the malignancy of the lesion. Conclusions: The experimental result shows that the system is efficient and works well on dermoscopy images, achieving considerable accuracy.

Texture feature plays a predominant role in recognizing face images. However different persons can have similar texture features that may degrade the system performance. Hence in this paper, the problem of face similarity is addressed by proposing a solution which combines textural and geometrical features. An algorithm is proposed to combine these two features. Five texture descriptors and few geometrical features are considered to validate the proposed system. Performance evaluations of these features are carried out independently and jointly for three different issues such as expression variation, illumination variation and partial occlusion with objects. It is observed that the combination of textural and geometrical features enhance the accuracy of face recognition. Experimental results on Japanese Female Facial Expression (JAFFE) and ESSEX databases indicate that the texture descriptor Local Binary Pattern achieves better recognition accuracy for all the issues considered.

In the marketing area, new trends are emerging, as customers are not only interested in the quality of the products or delivered services, but also in a stimulating shopping experience. Creating and influencing customers' experiences has become a valuable differentiation strategy for retailers. Therefore, understanding and assessing the customers' emotional response in relation to products/services represents an important asset. The purpose of this paper consists of investigating whether the customer's facial expressions shown during product appreciation are positive or negative and also which types of emotions are related to product appreciation. We collected a database of emotional facial expressions, by presenting a set of forty product related pictures to a number of test subjects. Next, we analysed the obtained facial expressions, by extracting both geometric and appearance features. Furthermore, we modeled them both in an unsupervised and supervised manner. Clustering techniques proved to be efficient at differentiating between positive and negative facial expressions in 78% of the cases. Next, we performed more refined analysis of the different types of emotions, by employing different classification methods and we achieved 84% accuracy for seven emotional classes and 95% for the positive vs. negative.

In this paper, we propose a parking slot markings detection method based on the geometric features of parking slots. The proposed system mainly consists of two steps, namely, separating line detection and parking slot entrance detection. First, in the separating line detection stage, we propose a line-clustering method based on the line segment detection (LSD) algorithm. Our detecting and line-clustering algorithm can detect the separating lines that contain a pair of parallel lines with a fixed distance in a bird&rsquo, s eye view (BEV) image under diverse lighting and ground conditions. Consequently, parking slot candidates are generated by pairing the separating lines according to the width of the parking slots. In the parking slot entrance detection process, we propose a multiview fusion-based learning approach that can increase the number of training samples by performing a perspective transformation on the acquired BEV images. The proposed method was evaluated using 353 BEV images covering diverse parking slot markings. Experiments show that the proposed method can recognize typical perpendicular and parallel rectangular parking slots, and a precision of 97.4% and recall of 96.6% are achieved.

International audience; With the aim of elaborating a mobile application, accessible to anyone and with educational purposes, we present a method for tree species identification that relies on dedicated algorithms and explicit botany-inspired descriptors. Focusing on the analysis of leaves, we developed a working process to help recognize species, starting from a picture of a leaf in a complex natural background. A two-step active contour segmentation algorithm based on a polygonal leaf model processes the image to retrieve the contour of the leaf. Features we use afterwards are high-level geometrical descriptors that make a semantic interpretation possible, and prove to achieve better performance than more generic and statistical shape descriptors alone. We present the results, both in terms of segmentation and classification, considering a database of 50 European broad-leaved tree species, and an implementation of the system is available in the iPhone application Folia.

This paper proposes an automatic and real-time system for face analysis, usable in visual communication applications. In this approach, faces are represented with Curve Edge Maps, which are collections of polynomial segments with a convex region. The segments are extracted from edge pixels using an adaptive incremental linear-time fitting algorithm, which is based on constructive polynomial fitting. The face analysis system considers face tracking, face recognition and facial feature detection, using Curve Edge Maps driven by histograms of intensities and histograms of relative positions. When applied to different face databases and video sequences, the average face recognition rate is 95.51%, the average facial feature detection rate is 91.92% and the accuracy in location of the facial features is 2.18% in terms of the size of the face, which is comparable with or better than the results in literature. However, our method has the advantages of simplicity, real-time performance and extensibility to the different aspects of face analysis, such as recognition of facial expressions and talking.

In this chapter, we describe a novel algorithm called CALEXia (Completely Automated Layers EXtraction technique based on integrated approach) for the automated localization and segmentation of the carotid artery wall in longitudinal 2D B-Mode ultrasound images.

Premise of the study: One of the many advantages offered by automated palynology systems is the ability to vastly increase the number of observations made on a particular sample or samples. This is of particular benefit when attempting to fully quantify the degree of variation within or between closely related pollen types. Methods: An automated palynology system (Classifynder) has been used to further investigate the variation in pollen morphology between two New Zealand species of Myrtaceae (Leptospermum scoparium and Kunzea ericoides) that are of significance in the New Zealand honey industry. Seven geometric features extracted from automatically gathered digital images were used to characterize the range of shape and size of the two taxa, and to examine the extent of previously reported overlap in these variables. Results: Our results indicate a degree of overlap in all cases. The narrowest overlap was in measurements of maximum Feret diameter (MFD) in grains oriented in polar view. Multivariate statistical analysis using all seven factors provided the most robust discrimination between the two types. Discussion: Further work is required before this approach could be routinely applied to separating the two pollen types used in this study, most notably the development of comprehensive reference distributions for the types in question.

Artifact rejection is a central issue when dealing with electroencephalogram recordings. Although independent component analysis (ICA) separates data in linearly independent components (IC), the classification of these components as artifact or EEG signal still requires visual inspection by experts.In this paper, we achieve automated artifact elimination using linear discriminant analysis (LDA) for classification of feature vectors extracted from ICA components via image processing algorithms.We compare the performance of this automated classifier to visual classification by experts and identify range filtering as a feature extraction method with great potential for automated IC artifact recognition (accuracy rate 88%). We obtain almost the same level of recognition performance for geometric features and local binary pattern (LBP) features.Compared to the existing automated solutions the proposed method has two main advantages: First, it does not depend on direct recording of artifact signals, which then, e.g. have to be subtracted from the contaminated EEG. Second, it is not limited to a specific number or type of artifact.In summary, the present method is an automatic, reliable, real-time capable and practical tool that reduces the time intensive manual selection of ICs for artifact removal. The results are very promising despite the relatively small channel resolution of 25 electrodes.