Perfect Recognition Rate Research Articles

Design and Implementation of HD Mapping, Vehicle Control, and V2I Communication for Robo-Taxi Services

This paper presents our autonomous driving (AD) software stack, developed to complete the main mission of the contest we entered. The main mission can be simply described as a robo-taxi service on public roads, to transport passengers to their destination autonomously. Among the key competencies required for the main mission, this paper focused on high-definition mapping, vehicle control, and vehicle-to-infrastructure (V2I) communication. V2I communication refers to the task of wireless data exchange between a roadside unit and vehicles. With the data being captured and shared, rich, timely, and non-line-of-sight-aware traffic information can be utilized for a wide range of AD applications. In the contest, V2I communication was applied for a robo-taxi service, and also for traffic light recognition. A V2I communication-enabled traffic light recognizer was developed, to achieve a nearly perfect recognition rate, and a robo-taxi service handler was developed, to perform the main mission of the contest.

Assessing the Effect of Data Augmentation on Occluded Frontal Faces Using DWT-PCA/SVD Recognition Algorithm

The drift towards face-based recognition systems can be attributed to recent advances in supportive technology and emerging areas of application including voting systems, access control, human-computer interactions, entertainments, and crime control. Despite the obvious advantages of such systems being less intrusive and requiring minimal cooperation of subjects, the performances of their underlying recognition algorithms are challenged by the quality of face images, usually acquired from uncontrolled environments with poor illuminations, varying head poses, ageing, facial expressions, and occlusions. Although several researchers have leveraged on the property of bilateral symmetry to reconstruct half-occluded face images, their approach becomes deficient in the presence of random occlusions. In this paper, we harnessed the benefits of the multiple imputation by the chained equation technique and image denoising using Discrete Wavelet Transforms (DWTs) to reconstruct degraded face images with random missing pixels. Numerical evaluation of the study algorithm gave a perfect (100%) average recognition rate each for recognition of occluded and augmented face images. The study also revealed that the average recognition rate for the augmented face images (75.5811) was significantly lower than the average recognition rate (430.7153) of the occluded face images. MICE augmentation is recommended as a suitable data enhancement mechanism for imputing missing data/pixel of occluded face images.

<i>Die Grenzboten</i> on its Way to Virtual Research Environments and Infrastructures

The State and University Library Bremen (SuUB) is dedicated to the digitization of its historical collections. Digitization is an important instrument for improving the accessibility of valuable information contained in fragile historical documents. It facilitates academic research and teaching and is indispensable to the digital humanities. Especially the research of digital serial publications benefits from ‘recent systematic digitization efforts, often initiated by libraries […]. More and more historical periodicals and other serial publications are now digitally available in full, i.e., all of their issues’ [Piotrowski, this volume]. The historical journal presented in this article is one of these and the final section will discuss why it can be considered a complete corpus. Usually, digitization projects produce digital images, metadata for cataloguing and web-navigation purposes and OCR full text for searching. This information is made available through the library's web portal for digital collections. However, digital humanists need high-quality full texts enriched with metadata in the appropriate format to analyse them with powerful software tools. The historical journal Die Grenzboten serves as an exemplary model to bridge the gap between digitization projects in libraries and research infrastructures. Die Grenzboten is a long running serial publication (1841 – 1922). It can be classified as a literary journal that also covered politics and arts. We demonstrate that OCR post correction and a page-wise structuring are prerequisites for the creation of a high-quality TEI version of a full text. The TEI version was created in cooperation with the Deutsches Textarchiv (DTA) at the Berlin-Brandenburg Academy of Sciences and Humanities (BBAW). A fully automated OCR post correction developed at the SuUB Bremen is freely available on GitHub. To enable scientists to work with powerful software tools the transfer of high-quality full texts to research infrastructures is a necessary step. We describe transfers of full text and the experience we have made, but still some general questions persist: What has to be done to prepare raw OCR output for this purpose in a reasonable and cost-effective manner? What quality is needed or expected? Which metadata and file formats are needed? Should there not be a closer cooperation between research infrastructures and libraries handling the digitization? OCR full texts, even post corrected, are not perfect but character recognition rates around 99% certainly provide more options than just being used as a search index. There is a vast amount of textual resources available ready to be made fully accessible for scientific research! Finally, some suggestions for scholars and the researchers working on digital serial publications are given.

RF Fingerprint Feature Extraction and Recognition Algorithm Based on Double-Maximal

The proposed double-maximal radio frequency (RF) fingerprint feature extraction algorithm in this paper is aimed at the imperfect signal with noisy signal. It can achieve perfect recognition rate when the feature dimension is greatly reduced, and the classification performance is improved. The advantage of low computational complexity and high authentication accuracy is suitable for access authentication in scenarios such as power terminals, and is well compatible with the diversified and heterogeneous characteristics of power terminals under the power edge computing.

Spatial image polynomial decomposition with application to video classification

This paper addresses the use of orthogonal polynomial basis transform in video classification due to its multiple advantages, especially for multiscale and multiresolution analysis similar to the wavelet transform. In our approach, we benefit from these advantages to reduce the resolution of the video by using a multiscale/multiresolution decomposition to define a new algorithm that decomposes a color image into geometry and texture component by projecting the image on a bivariate polynomial basis and considering the geometry component as the partial reconstruction and the texture component as the remaining part, and finally to model the features (like motion and texture) extracted from reduced image sequences by projecting them into a bivariate polynomial basis in order to construct a hybrid polynomial motion texture video descriptor. To evaluate our approach, we consider two visual recognition tasks, namely the classification of dynamic textures and recognition of human actions. The experimental section shows that the proposed approach achieves a perfect recognition rate in the Weizmann database and highest accuracy in the Dyntex++ database compared to existing methods.

Noise Robust Automatic Speech Recognition Scheme with Histogram of Oriented Gradient Features

In this paper, we propose a novel technique for noise robust automatic speech recognition (ASR). The development of ASR techniques has made it possible to recognize isolated words with a near perfect word recognition rate. However, in a highly noisy environment, a distinct mismatch between the trained speech and the test data results in a significantly degraded word recognition rate (WRA). Unlike conventional ASR systems employing Mel-frequency cepstral coefficients (MFCCs) and a hidden Markov model (HMM), this study employ histogram of oriented gradient (HOG) features and a Support Vector Machine (SVM) to ASR tasks to overcome this problem. Our proposed ASR system is less vulnerable to external interference noise, and achieves a higher WRA compared to a conventional ASR system equipped with MFCCs and an HMM. The performance of our proposed ASR system was evaluated using a phonetically balanced word (PBW) set mixed with artificially added noise.

Iris Localization using Daugman's Intero-Differential Operator

recognition is regarded as the most reliable and accurate biometric identification system. Most commercial iris recognition systems use patented algorithms developed by Daugman and these algorithms are able to produce perfect recognition rates. These algorithms are based on linear search methods which make the identification process extremely slow and also raise the false acceptance rate beyond the acceptable range. The proposed iris recognition approach consists of an automatic segmentation system that is based on the various algorithms and is able to localise the circular iris and pupil region, occluding eyelids and eyelashes and reflections. Our proposed method has shown out performing results than existing Houghman algorithms.

Identification of Behaviour in Freely Moving Dogs (Canis familiaris) Using Inertial Sensors

Monitoring and describing the physical movements and body postures of animals is one of the most fundamental tasks of ethology. The more precise the observations are the more sophisticated the interpretations can be about the biology of a certain individual or species. Animal-borne data loggers have recently contributed much to the collection of motion-data from individuals, however, the problem of translating these measurements to distinct behavioural categories to create an ethogram is not overcome yet. The objective of the present study was to develop a “behaviour tracker”: a system composed of a multiple sensor data-logger device (with a tri-axial accelerometer and a tri-axial gyroscope) and a supervised learning algorithm as means of automated identification of the behaviour of freely moving dogs. We collected parallel sensor measurements and video recordings of each of our subjects (Belgian Malinois, N=12; Labrador Retrievers, N=12) that were guided through a predetermined series of standard activities. Seven behavioural categories (lay, sit, stand, walk, trot, gallop, canter) were pre-defined and each video recording was tagged accordingly. Evaluation of the measurements was performed by support vector machine (SVM) classification. During the analysis we used different combinations of independent measurements for training and validation (belonging to the same or different individuals or using different training data size) to determine the robustness of the application. We reached an overall accuracy of above 90% perfect identification of all the defined seven categories of behaviour when both training and validation data belonged to the same individual, and over 80% perfect recognition rate using a generalized training data set of multiple subjects. Our results indicate that the present method provides a good model for an easily applicable, fast, automatic behaviour classification system that can be trained with arbitrary motion patterns and potentially be applied to a wide range of species and situations.

Recognition of Color Objects Using Hybrids Descriptors

In this paper, the authors came up with a different approach based on the combination of the different descriptors. For object recognition, regardless of orientation, size and position, feature vectors are computed with the help of Zernike moments and Centrist descriptors. For a large data base the fact of using the classic descriptors has never been a satisfying method for perfect recognition rates. The authors deduced that the combination of descriptors can have good recognition rates, accordingthe result of a comparative study of the different descriptors and the different combinations (Zernike + Centrist, Zernike + ACP, Centrist + ACP). The Zernike moment with Centrist descriptors ended up being the best hybrid description. For the recognition process, the authors opted for support vector machine (SVM) and Neural Networks (NN). The authors illustrate the proposed method on 3D objects using representations of two-dimensional images that are taken from different angles of view are the main features leading the authors to their objective.

Brain-Like Emergent Temporal Processing: Emergent Open States

Informed by brain anatomical studies, we present the developmental network (DN) theory on brain-like temporal information processing. The states of the brain are at its effector end, emergent and open. A finite automaton (FA) is considered an external symbolic model of brain's temporal behaviors, but the FA uses handcrafted states and is without “internal” representations. The term “internal” means inside the network “skull.” Using action-based state equivalence and the emergent state representations, the time driven processing of DN performs state-based abstraction and state-based skill transfer. Each state of DN, as a set of actions, is openly observable by the external environment (including teachers). Thus, the external environment can teach the state at every frame time. Through incremental learning and autonomous practice, the DN lumps (abstracts) infinitely many temporal context sequences into a single equivalent state. Using this state equivalence, a skill learned under one sequence is automatically transferred to other infinitely many state-equivalent sequences in the future without the need for explicit learning. Two experiments are shown as examples: The experiments for video processing showed almost perfect recognition rates in disjoint tests. The experiment for text language, using corpora from the Wall Street Journal, treated semantics and syntax in a unified interactive way.

Rapid recognition of Chinese herbal pieces of Areca catechu by different concocted processes using Fourier transform mid-infrared and near-infrared spectroscopy combined with partial least-squares discriminant analysis

Abstract Rapid and sensitive recognition of herbal pieces according to different concocted processing is crucial to quality control and pharmaceutical effect. Near-infrared (NIR) and mid-infrared (MIR) technology combined with supervised pattern recognition based on partial least-squares discriminant analysis (PLSDA) was attempted to classify and recognize six different concocted processing pieces of 600 Areca catechu L. samples and the influence of fingerprint information preprocessing methods on recognition performance was also investigated in this work. Recognition rates of 99.24%, 100% and 99.49% for original fingerprint, multiple scatter correct (MSC) fingerprint and second derivative (2nd derivative) fingerprint of NIR spectra were achieved by PLSDA models, respectively. Meanwhile, a perfect recognition rate of 100% was obtained for the above three fingerprint models of MIR spectra. In conclusion, PLSDA can rapidly and effectively extract otherness of fingerprint information from NIR and MIR spectra to identify different concocted herbal pieces of A. catechu .

Achieving robust face recognition from video by combining a weak photometric model and a learnt generic face invariant

In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applications. The objective of this work is to recognize faces using video sequences both for training and recognition input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. The central contribution is an illumination invariant, which we show to be suitable for recognition from video of loosely constrained head motion. In particular there are three contributions: (i) we show how a photometric model of image formation can be combined with a statistical model of generic face appearance variation to exploit the proposed invariant and generalize in the presence of extreme illumination changes; (ii) we introduce a video sequence “re-illumination” algorithm to achieve fine alignment of two video sequences; and (iii) we use the smoothness of geodesically local appearance manifold structure and a robust same-identity likelihood to achieve robustness to unseen head poses. We describe a fully automatic recognition system based on the proposed method and an extensive evaluation on 323 individuals and 1474 video sequences with extreme illumination, pose and head motion variation. Our system consistently achieved a nearly perfect recognition rate (over 99.7% on all four databases).

Sensitive and fast recognition of explosives using fluorescent polymer sensors and pattern recognition analysis

An optical sensor array consisting four fluorescent polymer thin films was investigated to recognize nitro containing explosive, TNT (2,4,6-trinitro toluene) and its simulants. The fluorescence quenching behaviour in presence of these analyte vapors was measured at peak emission of fluorescent materials upon excitation at 440 nm under ambient conditions. The time-dependence of fluorescence intensity for each polymer was obtained in presence of the analyte vapors. Feature patterns, like fluorescence quenching percentage at a certain time, were extracted from the time-dependent fluorescence intensity curve and were used as the input for pattern recognition tools. Even though the explosives were not distinguishable by principle component analysis (PCA) in 2 s, support vector machine (SVM) neural network showed 90% recognition rate. However, the recognition rate of SVM neural network was improved to 100% in 5 s whereas the fuzzy ARTMAP network had a perfect recognition rate in 6 s. Furthermore, the developed recognition system showed robustness to additive noise and can detect and discriminate between simulants and the explosive TNT within 10 s at sub parts per billion (ppb) level.

Prodigious Utilization of Genetic Algorithm in Tuning Gabor filter parametersin the Application of Iris Recognition

Gabor filters find an important place in image processing field but the use is restricted because of its computational complexity. Many methods are used in practice for security systems. Most common being the face recognition, voice recognition and biometric methods. Biometric systems are finding a lot of acceptances in the market. Mostly the finger print recognition and the iris recognition. Accurate automatic personal identification is critical in a variety of applications in our electronically interconnected society. Biometrics, which refers to identification based on physical or behavioral characteristics, is being increasingly adopted to provide positive identification with a high degree of confidence. Among all the biometric techniques, IRIS based authentication systems have received the most attention because of the uniqueness of iris. Due to its reliability and nearly perfect recognition rates, iris recognition is used in high security areas In this paper, a systematic approach is introduced to design the parameters of the Gabor filter banks for iris recognition. In this paper we also introduce how the Genetic Algorithm (GA) can be used to tune the parameters of the Gabor filter banks. The paper also explains how Daugman’s method can be used from a different point of view. We have also tried to show how Gabor filters can be replaced by a different set of filters, i.e., the Derivative of Gaussian (DoG) and the Laplacian of Gaussian (LoG) without sacrificing the recognition rate.

Pattern discovery for semi-structured web pagesusing bar-tree representation

Many websites with an underlying database containing structured data provide the richest and most dense source of information relevant for topical data integration. The real data integration requires sustainable and reliable pattern discovery to enable accurate content retrieval and to recognize pattern changes from time to time; yet, extracting the structured data from web documents is still lacking from its accuracy. This paper proposes the bar-tree representation to describe the whole pattern of web pages in an efficient way based on the reverse algorithm. While previous algorithms always trace the pattern and extract the region of interest from \textit{top root}, the reverse algorithm recognizes the pattern from the region of interest to both top and bottom roots simultaneously. The attributes are then extracted and labeled reversely from the region of interest of targeted contents. Since using conventional representations for the algorithm should require more computational power, the bar-tree method is developed to represent the generated patterns using bar graphs characterized by the depths and widths from the document roots. We show that this representation is suitable for extracting the data from the semi-structured web sources, and for detecting the template changes of targeted pages. The experimental results show perfect recognition rate for template changes in several web targets.

Neural Network Based Accurate Biometric Recognition and Identification of Human Iris Patterns

Problem statement: A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual. Iris recognition is regarded as the most reliable and accurate biometric identification system available. Approach: Most commercial iris recognition systems use patented algorithms developed by Daugman and these algorithms are able to produce perfect recognition rates. However, published results have usually been produced under favorable conditions and there have been no independent trials of the technology. Results: In this study after providing brief picture on development of various techniques for iris recognition, hamming distance coupled with neural network based iris recognition techniques were discussed. Perfect recognition on a set of 150 eye images has been achieved through this approach. Further, Tests on another set of 801 images resulted in false accept and false reject rates of 0.0005 and 0.187% respectively, providing the reliability and accuracy of the biometric technology. Conclusion/Recommendations: This study provided results of iris recognition performed applying Hamming distance, Feed forward back propagation, Cascade forward back propagation, Elman forward back propagation and perceptron. It has been established that the method suggested applying perceptron provides the best accuracy in respect of iris recognition with no major additional computational complexity.

Spoken emotion recognition through optimum-path forest classification using glottal features

A new method for the recognition of spoken emotions is presented based on features of the glottal airflow signal. Its effectiveness is tested on the new optimum path classifier (OPF) as well as on six other previously established classification methods that included the Gaussian mixture model (GMM), support vector machine (SVM), artificial neural networks – multi layer perceptron (ANN-MLP), k-nearest neighbor rule (k-NN), Bayesian classifier (BC) and the C4.5 decision tree. The speech database used in this work was collected in an anechoic environment with ten speakers (5 M and 5 F) each speaking ten sentences in four different emotions: Happy, Angry, Sad, and Neutral. The glottal waveform was extracted from fluent speech via inverse filtering. The investigated features included the glottal symmetry and MFCC vectors of various lengths both for the glottal and the corresponding speech signal. Experimental results indicate that best performance is obtained for the glottal-only features with SVM and OPF generally providing the highest recognition rates, while for GMM or the combination of glottal and speech features performance was relatively inferior. For this text dependent, multi speaker task the top performing classifiers achieved perfect recognition rates for the case of 6th order glottal MFCCs.