Recognition Methodology Research Articles

Integrated data and knowledge driven methodology for human activity recognition

Human activity recognition has been a popular research area concerned with identifying the specific movement or action of a person based on variety of sensor data. Conventional human activity recognition approaches are mainly data driven, which are not working well for composite activity recognition due to the complexity and uncertainty of real scenarios. We propose in this paper a hierarchical structure-based framework and methodology for human activity recognition by an integration of data-driven approach and knowledge-based approach, which provides an interesting framework capable of bridging lower-level pattern recognition and higher-level knowledge for reasoning and explanation. More specifically, this approach constructs a hierarchical structure for representing the composite activity by a composition of lower-level actions and gestures according to its semantic meaning. This hierarchical structure is then transformed into formal syntactical logical formulas and rules, based on which the resolution based automated reasoning is applied to recognize the composite activity given the recognized lower-level actions by using data driven machine learning methods. The work is the validated using some open-source data about video based human activity recognition. The present work provides a promising framework and application illustration of integration of machine learning and symbolic reasoning.

Mean oriented Riesz features for micro expression classification

Micro-expressions are brief and subtle facial expressions that go on and off the face in a fraction of a second. This kind of facial expressions usually occurs in high stake situations and is considered to reflect a human’s real intent. There has been some interest in micro-expression analysis, however, a great majority of the methods are based on classically established computer vision methods such as local binary patterns, histogram of gradients and optical flow. A novel methodology for micro-expression recognition using the Riesz pyramid, a multi-scale steerable Hilbert transform is presented. In fact, an image sequence is transformed with this tool, then the image phase variations are extracted and filtered as proxies for motion. Furthermore, the dominant orientation constancy from the Riesz transform is exploited to average the micro-expression sequence into an image pair. Based on that, the Mean Oriented Riesz Feature description is introduced. Finally the performance of our methods are tested in two spontaneous micro-expressions databases and compared to state-of-the-art methods.

Expert knowledge for the recognition of leukemic cells.

This work shows the advantage of expert knowledge for leukemic cell recognition. In the medical area, visual analysis of microscopic images has regularly used biological samples to recognize hematological disorders. Nowadays, techniques of image recognition are needed to achieve an adequate identification of blood tissues. This paper presents a procedure to acquire expert knowledge from blood cell images. We apply Gaussian mixtures, evolutionary computing, and standard techniques of image processing to extract knowledge. This information feeds a support vector machine or multilayer perceptron to classify healthy or leukemic cells. Additionally, convolutional neural networks are used as a benchmark to compare our proposed method with the state of the art. We use a public database of 260 healthy and leukemic cell images. Results show that our traditional pattern recognition methodology matches deep learning accuracy since the recognition of blood cells achieves 99.63%, whereas the convolutional neural networks reach 97.74% on average. Moreover, the computational effort of our approach is minimal, while meeting the requirement of being explainable.

Automatic recognition of Colombian car license plates using convolutional neural networks and Chars74k database

A methodology for the automatic recognition of Colombian car license plates using convolutional neural networks is proposed. One of the biggest challenges when using onvolutional neural network is the demand for large amounts of samples for training. In this work, we show that if we do not have enough images of vehicle license plates to carry out the training, we can complement it with databases of letters and numbers that are not extracted from cars. The network was trained with the Chars74k database and images of characters extracted from plates of Colombian automobiles. The Chars74k contains approximately 74000 images of all the letters of the Spanish alphabet and all digits from 0 to 9. From chars74k database we have chosen 33849, because the Colombian plates have only uppercase letters and digits. Only 3549 (about 10% of the total) images of characters extracted manually from plates of Colombian automobiles were added. At the input of the convolutional neural network, 70% of the images were used for training, 20% for validation and 10% for testing and the resulting validation accuracy was above 99%. By making a preliminary test on Colombian plates never before used in training, a percentage of correctly recognized plates above 98% was achieved.

Object Recognition Through Artificial Intelligence Techniques

This paper describes a methodology for object recognition categorized as polyhedron and non-polyhedron. This recognition is achieved through digital image processing combined with artificial intelligence algorithms, such as Hopfield networks. The procedure consists of processing images in search of patterns to train the system. The process is carried out through three stages: i) Segmentation, ii) Smart recognition, and iii) Feature extraction; as a result, images of objects are obtained and trained in the designed neuronal network. Finally, Hopfield's network is used to establish the object type as soon as it receives one. The proposed methodology was evaluated in a real environment with a considerable number of detected images; the noisy images recognition uncertainty was 2.6%, an acceptable result considering variable light, shape and color. The results obtained from this experiment show a high recognition level, which represents 97.4%. Out of this procedure, we can assume that it is possible to train new patterns, and it is expected that the model will be able to recognize them. Potentially, the proposed methodology could be used in a vast range of applications, such as object identification in industrial environments, grasping objects using manipulators or robotic arms, tools for blind patients, among other applications.

Differentiation of Edible Oils by Type Using Raman Spectroscopy and Pattern Recognition Methods.

The application of Raman spectroscopy and pattern recognition methods to the problem of discriminating edible oils by type was investigated. Two-hundred and eighty-six Raman spectra obtained from 53 samples spanning 15 varieties of edible oils were collected for 90 s at 2 cm-1 resolution. Employing a Whittaker filter, all Raman spectra were baseline corrected after removing the high-intensity fluorescent background in each spectrum. The Raman spectral data were then examined using the three major types of pattern recognition methodology: mapping and display, discriminant development and clustering. The 15 varieties of edible oils could be partitioned into five distinct groups based on their degree of saturation and the ratio of polyunsaturated fatty acids to monounsaturated fatty acids. Edible oils assigned to one group could be readily differentiated from those assigned to other groups, whereas Raman spectra within the same group more closely resembled each other and therefore would be more difficult to classify by type.

PALM VEIN AUTHENTICATION TECHNOLOGY

Palm vein authentication has high level of accuracy because it is located inside the body and does not change over the life and cannot be stolen. These papers present an analysis of palm vein pattern recognition algorithms, techniques, methodologies and system. It discusses the technical aspects of recent approaches for the following processes; detection of region of interest (ROI), segment of palm vein pattern, features extraction, and matching. The results show that, there is no benchmark database exists for palm vein recognition. For all processes, there are many machine learning techniques with very high accuracy.

Optimization of deep learning features for age-invariant face recognition

This paper presents a methodology for Age-Invariant Face Recognition (AIFR), based on the optimization of deep learning features. The proposed method extracts deep learning features using transfer deep learning, extracted from the unprocessed face images. To optimize the extracted features, a Genetic Algorithm (GA) procedure is designed in order to select the most relevant features to the problem of identifying a person based on his/her facial images over different ages. For classification, K-Nearest Neighbor (KNN) classifiers with different distance metrics are investigated, i.e., Correlation, Euclidian, Cosine, and Manhattan distance metrics. Experimental results using a Manhattan distance KNN classifier achieves the best Rank-1 recognition rate of 86.2% and 96% on the standard FGNET and MORPH datasets, respectively. Compared to the state-of-the-art methods, our proposed method needs no preprocessing stages. In addition, the experiments show its privilege over other related methods.

RETRACTED ARTICLE: An efficient method for human hand gesture detection and recognition using deep learning convolutional neural networks

The physical movement of the human hand produces gestures, and hand gesture recognition leads to the advancement in automated vehicle movement system. In this paper, the human hand gestures are detected and recognized using convolutional neural networks (CNN) classification approach. This process flow consists of hand region of interest segmentation using mask image, fingers segmentation, normalization of segmented finger image and finger recognition using CNN classifier. The hand region of the image is segmented from the whole image using mask images. The adaptive histogram equalization method is used as enhancement method for improving the contrast of each pixel in an image. In this paper, connected component analysis algorithm is used in order to segment the finger tips from hand image. The segmented finger regions from hand image are given to the CNN classification algorithm which classifies the image into various classes. The proposed hand gesture detection and recognition methodology using CNN classification approach with enhancement technique stated in this paper achieves high performance with state-of-the-art methods.

Depth data and fusion of feature descriptors for static gesture recognition

In this study, the authors propose a novel methodology for static gesture recognition in a complex background using only depth map from Microsoft's Kinect camera. Four different types of features are extracted and analysed on two public static gesture datasets. The features extracted from the segmented hand are geometrical, local binary patterns, number of fingers (Num) raised in a gesture and distance of hand palm centre from the fingertips and the valley between the fingers. The hand region is first segmented from the image using depth data followed by the forearm removal. Four multi-class support vector machine (SVM) kernels are also compared and used for recognition of gestures with extracted feature vector as an input. The experimental results achieved recognition accuracy of 99 and 95.7 % on two public complex static gesture datasets using Gaussian SVM kernel function as a classifier. The proposed approach is found to be comparable and even outperforms some of the state-of-the-art techniques in terms of high recognition accuracies, even after using a single cue for hand segmentation and extraction of features in the complex background which results in non-dependency on too many cues and much hardware.

A Study on the Meaning Recognition and Qualitative Research Methodology Class Experience of Graduate Students in Education

A Study on the Meaning Recognition and Qualitative Research Methodology Class Experience of Graduate Students in Education

A Pattern Recognition Model of Python Programming using Artificial Neural Network via NeMo

Background/Objectives: In the field of software development, the diversity of programming languages increases dramatically with the increase in their complexity. This leads both programmers and researchers to develop and investigate automated tools to distinguish these programming languages. Different efforts were conducted to achieve this task using keywords of source codes of these programming languages. Therefore, instead of using keywords classification for recognition, this work is conducted to investigate the ability to detect the pattern of a programming language characteristic by using NeMo(High-performance spiking neural network simulator) of neural network and testing the ability of this toolkit to provide detailed analyzable results. Methods/Statistical analysis: the method of achieving these objectives is by using a back propagation neural network via NeMo based on pattern recognition methodology. Findings: The results show that the NeMo neural network of pattern recognition can identify and recognize the pattern of python programming language with high accuracy. It also shows the ability of the NeMo toolkit to represent the analyzable results through a percentage of certainty. Improvements/Applications: it can be noticed from the results the ability of NeMo simulator to provide beneficial platform for studying and analyzing the complexity of the backpropagation neural network model.

Real-time detection of the interaction between an upper-limb power-assist robot user and another person for perception-assist

Assisting aged population or a population with disabilities is a critical problem in today’s world. To compensate for their declined motor function, power-assist wearable robots have been proposed. In some cases, however, the cognitive function of these populations may have declined as well, and it may be insufficient to compensate only for their motor function deficiency. Perception-assist wearable robots, which can perceive environmental information using visual sensors attached to them, have been proposed to address this problem. This study addresses the problem of identifying motion intentions of the user of an upper-limb power-assist wearable robot, while the user engages in desired interactions with others. It is important to consider both the interacting parties in order to accurately predict proper interaction. Therefore, this paper presents an interaction recognition methodology by combining both the user’s motion intention and the other party’s motion intention with environmental information. A fuzzy reasoning model is proposed to semantically combine the motion intentions of both parties and environmental information. In this method, the motion intentions of both the user and the other party are simultaneously estimated using kinematic information and visual information, respectively, and they are employed for predicting the interactions between both parties. The effectiveness of the proposed approach is experimentally evaluated.

Information Theory Based Probabilistic Approach to Blade Damage Detection of Turbomachine Using Sensor Data

An unplanned breakdown in power generation or chemical plant due to the component failure of turbomachines often results in a huge loss of property and productivity as well as a significant increase in maintenance costs. It has become of paramount importance to predict component damage in a turbomachine using instrumented data. Most existing models, however, are obtained from multiple assumptions, resulting in a high false detection ratio due to various data uncertainties. In this article, we present a novel model-free probabilistic methodology for damage detection to resolve the drawbacks of the classical methods. The proposed method adeptly integrates Bayesian inference, wavelets signal processing, probabilistic principal components analysis, and entropy information theory. Bayesian inference is developed for denoising raw data by integrating with multiscale discrete wavelet packets transform and reducing multivariate dimension by combining with principal components analysis. The entropy information theory has been proposed to extract the feature from principal components as a precursor of the event. A multimetric hierarchical alerting strategy is proposed to predict component damage to enhance the accuracy. The feasibility of the presented novel pattern recognition methodology is demonstrated with the detection of blade damage events in a real-world steam turbine using sensor data.

Using Wearable Sensors for Human Activity Recognition in Logistics: A Comparison of Different Feature Sets and Machine Learning Algorithms

The topic of human activity recognition has gained a lot of attention due to its usage for exercise monitoring, smart health and assisted living. Even though the aforementioned domains have received significant interest by researchers, activity recognition for industrial settings has received little attention in comparison. Industry 4.0 involves the assimilation of industrial workers with robots and other equipment used in the industry and necessitates the development of recognition methodologies for activities being performed in industries. In this regard, this paper presents a comparison in performance of various time/frequency domain features and popular machine learning algorithms for use in activity recognition in a logistics scenario. Experiments were conducted on inertial measurement sensor data from the recently released LARa dataset which involved three feature sets being used with four machine learning algorithms; Support Vector Machines, Decision Trees, Random Forests and Extreme Gradient Boost (XGBoost). The best result achieved in the experiments was an average accuracy of 78.61% using the XGBoost classifier while using both time and frequency domain features. This work serves as a baseline for activity recognition in logistics using IMU sensors and enables the development of solutions to support fulfillment of Industry 4.0 goals.

Alzheimer's Disease: The Role of Mutations in Protein Folding.

Misfolded proteins result when a protein follows the wrong folding pathway. Accumulation of misfolded proteins can cause disorders, known as amyloid diseases. Unfortunately, some of them are very common. The most prevalent one is Alzheimer's disease. Alzheimer's disease is a neurodegenerative disorder and the commonest form of dementia. The current study aims to assess the impact of somatic mutations in PSEN1 gene. The said mutations are the most common cause of familial Alzheimer's disease. As protein functionality can be affected by mutations, the study of possible alterations in the tertiary structure of proteins may reveal new insights related to the relationship between mutations and protein functions. To examine the effect of mutations, the primary structures and their related mutations were retrieved from public databases. Each structure (mutated and unmutated) was predicted based on effective structure prediction methodologies. A benchmarking of the structural predictive tools was accomplished. Comparative analyses of mutated and unmutated proteins were performed based on classic bioinformatics methods (TM-Score, RMSD, etc.) as well as on established shape-based descriptors retrieved from object recognition methodologies. Unsupervised methodologies were applied to the structures, in order to identify groups of mutation with similar mutational impact. Our results provide an essential knowledge toward protein's functionality in structure-based drug design.

Towards Complete and Accurate Iris Segmentation Using Deep Multi-Task Attention Network for Non-Cooperative Iris Recognition

Iris images captured in non-cooperative environments often suffer from adverse noise, which challenges many existing iris segmentation methods. To address this problem, this paper proposes a high-efficiency deep learning based iris segmentation approach, named IrisParseNet . Different from many previous CNN-based iris segmentation methods, which only focus on predicting accurate iris masks by following popular semantic segmentation frameworks, the proposed approach is a complete iris segmentation solution, i.e., iris mask and parameterized inner and outer iris boundaries are jointly achieved by actively modeling them into a unified multi-task network. Moreover, an elaborately designed attention module is incorporated into it to improve the segmentation performance. To train and evaluate the proposed approach, we manually label three representative and challenging iris databases, i.e., CASIA.v4-distance, UBIRIS.v2, and MICHE-I, which involve multiple illumination (NIR, VIS) and imaging sensors (long-range and mobile iris cameras), along with various types of noises. Additionally, several unified evaluation protocols are built for fair comparisons. Extensive experiments are conducted on these newly annotated databases, and results show that the proposed approach achieves state-of-the-art performance on various benchmarks. Further, as a general drop-in replacement, the proposed iris segmentation method can be used for any iris recognition methodology, and would significantly improve the performance of non-cooperative iris recognition.

Crop Detection and Classification using Remote Sensing Images

crop type identification timely and accurately is one of the applications of remote sensing (RS). It assists the people to regulate the variations in the costs of the food grains. RS images are utmost beneficial for agricultural productions. Recent research methodologies focuses mainly on the crops classification using satellite RS image. This paper proffers the survey on crop detection and classification utilizing RS images. This paper also highlights the latest studies regarding the implementation of crop detection and classification techniques like, review on disparate methodologies for crop recognition and classification (different classifiers are used to detect the crop), review on crop conditions monitoring system, and review on identification of yield estimation , crop region, and also crop growth. At last, the performances of the state-of-art methods are contrasted centered on the Kappa coefficient metrics and overall accuracy. Here, accuracy is the notable metric in the crop identification system.

Post-mortem iris recognition with deep-learning-based image segmentation

This paper proposes the first known to us iris recognition methodology designed specifically for post-mortem samples. We propose to use deep learning-based iris segmentation models to extract highly irregular iris texture areas in post-mortem iris images. We show how to use segmentation masks predicted by neural networks in conventional, Gabor-based iris recognition method, which employs circular approximations of the pupillary and limbic iris boundaries. As a whole, this method allows for a significant improvement in post-mortem iris recognition accuracy over the methods designed only for ante-mortem irises, including the academic OSIRIS and commercial IriCore implementations. The proposed method reaches the EER less than 1% for samples collected up to 10 hours after death, when compared to 16.89% and 5.37% of EER observed for OSIRIS and IriCore, respectively. For samples collected up to 369 h post-mortem, the proposed method achieves the EER 21.45%, while 33.59% and 25.38% are observed for OSIRIS and IriCore, respectively. Additionally, the method is tested on a database of iris images collected from ophthalmology clinic patients, for which it also offers an advantage over the two other algorithms. This work is the first step towards post-mortem-specific iris recognition, which increases the chances of identification of deceased subjects in forensic investigations. The new database of post-mortem iris images acquired from 42 subjects, as well as the deep learning-based segmentation models are made available along with the paper, to ensure all the results presented in this manuscript are reproducible.

ARTEMIdE—An Automated Underwater Material Recognition Method for Fluorescence LIDAR Invariant to Environmental Conditions

This article presents an automated underwater material recognition methodology for fluorescence light detection and ranging (LIDAR) invariant to environmental conditions (ARTEMIdE). Contrary to other state-of-the-art methods for submerged object recognition, ARTEMIdE can be applied when no a priori knowledge about environmental conditions is available and without resorting to any additional data besides the received signal and the fluorescence spectral signatures of the materials of interest. Experimental results over synthetic and real data show that ARTEMIdE is effective at automatically recognizing various object materials submerged at different depths within the water column. The presented approach reveals to provide great potential for many marine and submarine applications.