Fast Recognition Research Articles

Sensorless LED display screen interaction and object recognition

AbstractTaking advantage of the photoelectric characteristics of LED other than the light‐emitting function, this paper proposes a light sensing detection method and system without adding additional sensors to the LED screen. A two‐pole detection structure with a function of detecting positive and negative voltage is introduced to the LED drive circuit, which ensures the high‐speed characteristics during detection. What's more, the LED is controlled to work in photoconductive mode to obtain high voltage sensitivity when the intensity of incident light changes. The proposed module can reach an optical signal response rate of 19.1 μs with a detection rate of 23.5 Hz without affecting the original display function. The optical signal detection can reach a voltage sensitivity of 3.02 mV per lx. To verify the photoelectric detection capability of the method presented in this paper, a brand‐new screen object recognition system is built and tested. An 8 × 8 LED display module is used in experiment, and the scale of LED screen can be expanded easily and flexibly. In an ideal environment, a recognition accuracy of 99.25% can be achieved, while the recognition accuracy can still reach over 96.5% in a complex light environment. Therefore, this work has further application possibilities for light interaction and fast object recognition in large screens.

Lunar Crater Identification in Digital Images

It is often necessary to identify a pattern of observed craters in a single image of the lunar surface and without any prior knowledge of the camera’s location. This so-called “lost-in-space” crater identification problem is common in both crater-based terrain relative navigation (TRN) and in automatic registration of scientific imagery. Past work on crater identification has largely been based on heuristic schemes, with poor performance outside of a narrowly defined operating regime (e.g., nadir pointing images, small search areas). This work provides the first mathematically rigorous treatment of the general crater identification problem. It is shown when it is (and when it is not) possible to recognize a pattern of elliptical crater rims in an image formed by perspective projection. For the cases when it is possible to recognize a pattern, descriptors are developed using invariant theory that provably capture all of the viewpoint invariant information. These descriptors may be pre-computed for known crater patterns and placed in a searchable index for fast recognition. New techniques are also developed for computing pose from crater rim observations and for evaluating crater rim correspondences. These techniques are demonstrated on both synthetic and real images.

3D Face Recognition Based on an Attention Mechanism and Sparse Loss Function

Face recognition is one of the essential applications in computer vision, while current face recognition technology is mainly based on 2D images without depth information, which are easily affected by illumination and facial expressions. This paper presents a fast face recognition algorithm combining 3D point cloud face data with deep learning, focusing on key part of face for recognition with an attention mechanism, and reducing the coding space by the sparse loss function. First, an attention mechanism-based convolutional neural network was constructed to extract facial features to avoid expressions and illumination interference. Second, a Siamese network was trained with a sparse loss function to minimize the face coding space and enhance the separability of the face features. With the FRGC face dataset, the experimental results show that the proposed method could achieve the recognition accuracy of 95.33%.

Fast and Accurate Recognition for Codes on Complex Backgrounds for Real-Life Industrial Applications

In the food and beverage industry, the existing recognition of code characters on the surface of complex packaging usually suffers from low accuracy and low speed. This work presents an efficient and accurate inkjet code recognition system based on the combination of the deep learning and traditional image processing methods. The proposed system mainly consists of three sequential modules, i.e., the characters region extraction by modified YOLOv3-tiny network, the character processing by the traditional image processing methods such as binarization and the modified character projection segmentation, and the character recognition by a Convolutional recurrent neural network (CRNN) model based on a modified version of MobileNetV3. In this system, only a small amount of tag data has been made and an effective character data generator is designed to randomly generate different experimental data for the CRNN model training. To the best of our knowledge, this report for the first time describes that deep learning has been applied to the recognition of codes on complex background for the real-life industrial application. Experimental results have been provided to verify the accuracy and effectiveness of the proposed model, demonstrating a recognition accuracy of 0.986 and a processing speed of 100 ms per bottle in the end-to-end character recognition system.

Fast Blind Recognition of BCH Code Based on Spectral Analysis and Probability Statistics

This letter presents a fast blind recognition method for Bose, Chaudhuri, and Hocquenghem (BCH) code from noisy intercepted bit-streams. This approach employs the fact that the t-error-correcting BCH code has 2t continuous roots, and the roots correspond with the zero spectral. Specifically, the Galois field Fourier transform is simplified (S-GFFT) by using the property of conjugate roots. Then, the distribution characteristics of continuous zero spectra are analyzed. If the continuous zero spectra satisfy the threshold condition which is derived by the probability of zero spectrum component, the corresponding estimated length is the code length, and the relevant positions correspond to the continuous roots of the generated polynomial. Finally, the generator polynomial can be reconstructed based on algebras theory. Compared to the existing solutions, the computational amount of S-GFFT at most accounts for 60% of GFFT, and the proposed scheme manages to recognize the code parameters without traversing the whole candidate datasets.

Automatic Recognition of Solar Active Regions Based on Real-time SDO/HMI Full-disk Magnetograms

Solar Active Regions (ARs) are the main source regions of solar activities. The morphology, structure, and characteristic of ARs are important factors in determining solar eruptions. Therefore, the recognition of ARs is the precondition to predict solar eruptions. SDO/HMI can continuously provide full-disk photospheric images with high temporal and spatial resolution. Referring to the method of Zhang et al.[1], we performed a study of fast automatic recognition of ARs from full-disk HMI magnetograms, which involves the intensity-based thresholding, mathematical morphological analysis and region growing. Through comparing the automatic recognition ARs with the ARs compiled by NOAA/SWPC from 2010 May to 2018 December, it is found that the number of ARs recognized automatically and the number of SWPC ARs are basically consistent in the trend of variation, and their correlation coefficient is 0.87. The total number of ARs automatically recognized is slightly less than the number of SWPC ARs. Most of the unidentified ARs are small areas, weak magnetic fields and simple magnetic structures, which are highly impossible to produce powerful eruptions to affect the space environment. This method of the automatic AR recognition from real-time HMI full-disk magnetograms can directly provide the real-time AR data for forecasting solar eruptions, and accelerate the operational application of solar eruption prediction models.

Occluded iris classification and segmentation using self-customized artificial intelligence models and iterative randomized Hough transform

A fast and accurate iris recognition system is presented for noisy iris images, mainly the noises due to eye occlusion and from specular reflection. The proposed recognition system will adopt a self-customized support vector machine (SVM) and convolution neural network (CNN) classification models, where the models are built according to the iris texture GLCM and automated deep features datasets that are extracted exclusively from each subject individually. The image processing techniques used were optimized, whether the processing of iris region segmentation using iterative randomized Hough transform (IRHT), or the processing of the classification, where few significant features are considered, based on singular value decomposition (SVD) analysis, for testing the moving window matrix class if it is iris or non-iris. The iris segments matching techniques are optimized by extracting, first, the largest parallel-axis rectangle inscribed in the classified occluded-iris binary image, where its corresponding iris region is crosscorrelated with the same subject’s iris reference image for obtaining the most correlated iris segments in the two eye images. Finally, calculating the iriscode Hamming distance of the two most correlated segments to identify the subject’s unique iris pattern with high accuracy, security, and reliability.

Upper-airway foreign bodies: is a clinical approach enough for proceeding with invasive management? Evidence from a case

Abstract Introduction: Upper-airway foreign bodies are a common condition in the emergency room, which can lead to death among different-aged populations, and a fast clinical recognition and management have led to improvement in the outcomes. Objective: To present a clinical case of a male patient with an upper-airway foreign body, which only required clinical evaluation before surgical management. Clinical case: We report the case of an 8-year-old Hispanic boy, who presented to the emergency room with upper respiratory symptoms, including dry cough, dysphagia, and chest discomfort; after clinical evaluation, a diagnosis of an upper-airway foreign body was made; the patient was taken to the operating room, and a tracheal foreign body was removed using rigid bronchoscopy. The post-operative course was uneventful, and the patient was discharged. Discussion: The physiopathology, diagnosis, and management based on the presented case are discussed. Conclusion: A good clinical history, along with a thorough physical examination and a high index of suspicion from the clinician, is enough for achieving a diagnosis, facilitating early management and reducing complications.

Intra-Pulse Modulation Recognition of Dual-Component Radar Signals Based on Deep Convolutional Neural Network

In an ever-increasingly complicated electromagnetic environment with explosive radar signals density, accurate and fast recognition of dual-component radar signals has become an urgent problem in the current radar reconnaissance system. This letter proposes a novel multi-class learning framework based on deep convolutional neural network (DCNN) for recognizing eight types of randomly overlapping dual-component radar signals. The framework mainly includes dual-component radar signals preprocessing, DCNN model that aimed to extract more effective dual-component radar signals features, and multi-class classification. The results shown that the average classification accuracy of dual-component radar signals can be up to 96.17% when the signal-to-noise ratio (SNR) is −8 dB, which demonstrates the superior performance over others. The proposed model possesses the larger improvement for 4FSK, BPSK, EQFM, and FRANK, especially at the lower SNR. This work provides a sound guidance for further improving multi-component radar signals recognition.

Fast Recognition using Bar-based Data Mapping for Gamelan Music Genre Classification

This research aims to develop a gamelan music genre classifier based on the musical mode system determined based on the dominant notes in a certain order. Only experts can discriminate the musical mode system of compositions. The Feed Forward Neural Networks method was used to classify gamelan compositions into three musical mode systems. The challenge is to recognize the musical mode system of compositions between the initial melody without having to analyze the entire melody using a small amount of data for the dataset. Instead of conducting a melodic extraction from audio signal data, the text-based skeletal melody data, which is a form of extracted melodic features, are used for the dataset. Unique corpuses are controlled based on the cardinality of the one-to-many relationship, and a data mapping technique based on the bars is used to increase the number of corpuses. The results show that the proposed method is suitable to solve the specified problems, where the accuracy in recognizing the class of unseen compositions between the initial melody achieves at 86.7%.

Fast recognition using convolutional neural network for the coal particle density range based on images captured under multiple light sources

A method based on multiple images captured under different light sources at different incident angles was developed to recognize the coal density range in this study. The innovation is that two new images were constructed based on images captured under four single light sources. Reconstruction image 1 was constructed by fusing greyscale versions of the original images into one image, and Reconstruction image 2 was constructed based on the differences between the images captured under the different light sources. Subsequently, the four original images and two reconstructed images were input into the convolutional neural network AlexNet to recognize the density range in three cases: −1.5 (clean coal) and + 1.5 g/cm3 (non-clean coal); −1.8 (non-gangue) and + 1.8 g/cm3 (gangue); −1.5 (clean coal), 1.5–1.8 (middlings), and + 1.8 g/cm3 (gangue). The results show the following: (1) The reconstructed images, especially Reconstruction image 2, can effectively improve the recognition accuracy for the coal density range compared with images captured under single light source. (2) The recognition accuracies for gangue and non-gangue, clean coal and non-clean coal, and clean coal, middlings, and gangue reached 88.44%, 86.72% and 77.08%, respectively. (3) The recognition accuracy increases as the density moves further away from the boundary density.

Intelligent fault diagnosis under small sample size conditions via Bidirectional InfoMax GAN with unsupervised representation learning

The abnormal detection of rotating machinery under small sample size conditions is of prime importance in the field of fault diagnosis. In this work, we proposed an unsupervised representation learning method called Bidirectional InfoMax GAN (BIMGAN), which can perform fast and effective feature extraction and fault recognition with few samples. First, we obtain the low-dimensional feature representation by a prior normalized encoder and reconstruction of the sample via the generator. Second, the mapping relationship between the sample and its corresponding feature representation is learned by maximizing mutual information estimation with the constraint of the feature matching (FM) strategy. Different from the general GANs, we are aiming at learning a good feature mapping of an encoder to capture the feature representation instead of reconstructing realistic samples. And then, a supervised pattern recognition task based on the feature representation is conducted for fault diagnosis. Finally, the inverse mapping learned by the encoder is visualized and the effectiveness is demonstrated. And the performance of the proposed method outperforms several advanced unsupervised methods on two case studies of rolling bearings fault recognition with some standard architectures, where the average accuracy can achieve 99.73% and 98.36% respectively.

Dynamic optimization of hessian determinant image pyramid for memory‐efficient and high performance keypoint detection in SURF

With increasing demand for scale-invariant and fast object recognition, speeded up robust features (SURF) have emerged and become a widely used feature extraction algorithm in computer vision. Nevertheless, SURF still requires high memory usage and heavy computations caused by the keypoint detection procedure that produces huge image pyramid composed of many hessian determinant (HD) data for supporting the scale-invariance. Therefore, in this paper, dynamic optimization schemes of the HD image pyramid are proposed for completely removing the redundancies of the keypoint detection with keeping the original functionality of SURF without any loss. The proposed approach has shown to reduce memory usage by 45–51%, the execution time by 37–50% and the power consumption by 18–42% when compared with the keypoint detection in the original SURF algorithm.

Distinction of chiral penicillamine using metal-ion coupled cyclodextrin complex as chiral selector by trapped ion mobility-mass spectrometry and a structure investigation of the complexes

Penicillamine (Pen) is a common chiral drug that is obtained from penicillin. Between the two enantiomers of Pen, only D-Pen can be used to treat cystinuria and rheumatoid arthritis while L-Pen is toxic. Therefore, it requires great efforts for the research of the rigorous analysis and distinction of the two enantiomers. The non-covalent combination of chiral molecules and chiral selectors (CSs) has been proved as a unique strategy for chiral distinction by ion mobility spectrometry in coupling with -mss spectrometry (IM-MS). Here, we developed a simple method to distinguish D, L-Pen by using special CSs for IM-MS separation. The CSs utilized here include cyclodextrins (CD) and linear chain oligosaccharides plus metal ions. We found that non-covalent complexes [Pen+β-CD + Li]+ could be easily formed by electrospray ionization of the mixture of the solution, and the chirality of Pen could be effectively recognized by measuring their mobilities due to the different collision cross collision sections of [D-Pen+β-CD + Li]+ and [L-Pen+β-CD + Li]+. A detailed analysis of [Pen+β-CD + Li]+ was then conducted by the optical rotation measurements and NMR experiments to reveal their structural differences. Furthermore, DFT calculation showed the differences of molecular conformation between the complexes. The results provide a new powerful method for fast analysis and recognition of chirality of Pen compounds by IM-MS.

Modulation Recognition of Composite Signal Based on ResNet and Frequency Domain Graph

Aiming at the problem of composite signal recognition in measurement and control system, a modulation recognition method of composite signal is proposed based on clipped internal modulation signal frequency image and residual network. Residual network has the advantages of fast convergence and high recognition accuracy, which is used to realize the recognition of different modulation modes and different bandwidth signals. The experimental results show that, compared with the traditional decision tree algorithm and the constellation based CNN recognition algorithm, the recognition performance of the proposed method is improved by more than 3dB for the variable bandwidth composite modulation signal set (BPSK-FM and QPSK-FM with internal modulation bandwidth of 128kHz, BPSK-FM and QPSK-FM with internal modulation bandwidth of 2kHz and 2FSK-FM with internal modulation bandwidth of 32kHz and 2kHz).

Design and Implementation of Artificial Intelligence Image Detection System Based on Noise Monitoring

Image quality detection technology can replace manual inspections to automatically detect video quality, accurately analyze, judge and alarm abnormalities in video images in the surveillance system to ensure the normal operation of the expanding network video surveillance system. The thesis designs an intelligent traffic image sensor system to realize fast motion detection and object recognition of the surveillance scene. This system introduces a background model based on region segmentation and a feature-based object recognition algorithm. Experimental results show that the system can perform automatic movement detection and object classification and recognition efficiently in real time.

Non-invasive isthmus identification of complex arrhythmias in congenital heart disease.

Sustained re-entrant tachyarrhythmias treatment has become pivotal in the grown-up congenital heart patients clinical management. Cardiac LGE-MRI tissue characterization integrated with high definition electroanatomic map could allow fast recognition and effective treatment of substrate of tachyarrhythmias. Cardiac LGE-MRI areas were suggestive of post-surgical changes both in atrium and ventricle. High-density electro-anatomical map localized areas of slow conduction identifying conducting isthmuses of re-entrant arrhythmias.

Anesthesia Management of Venous Gas Embolism with Hepatectomy

Abstract Background: This is a case review of the intraoperative management of a 46 year old male patient with a history of stage IV sigmoid colon adenocarcinoma with metastasis to the liver that presented for a robotic assisted sigmoidectomy and partial hepatectomy and had an intraoperative venous gas embolism that resulted in acute hemodynamic instability. Description of the case: A robotic assisted sigmoidectomy and partial hepatectomy was performed on a 46 year old male patient with a history of stage IV sigmoid colon adenocarcinoma with metastasis to the liver. The patient was otherwise healthy with no other significant medical history, and the perioperative lab results were within normal ranges with the exception of elevated liver function test results. The patient received preoperative medications for multimodal pain management as part of the enhanced recovery after surgery (ERAS) protocol and had an uneventful induction with intravenous anesthetic induction and endotracheal intubation. During the intraoperative course, the patient exhibited an acute hypotensive episode followed by acute desaturation. A venous gas embolism was suspected, and immediate interventions were implemented which helped the patient stabilize. The patient remained hemodynamically stable throughout the remainder of the case. After surgery, the patient was admitted to the intensive care unit for postoperative monitoring for any neurological or cardiovascular effects related to the intraoperative venous gas embolism. The postoperative period was uneventful, and the patient was successfully discharged home several days later without any adverse sequelae. Discussion and conclusions: Venous gas embolism can be a life-threatening intraoperative event that requires fast recognition of the symptoms and appropriate interventions in response to the patient changes. Evidence suggests that venous gas embolisms are very common with certain procedures but often subclinical. Preventative measures, early recognition, and prompt treatment of venous gas embolisms are important interventions to minimize the risk for any significant hemodynamic instability and any resulting neurological or cardiovascular sequelae.

A handheld testing device for the fast and ultrasensitive recognition of cardiac troponin I via an ion-sensitive field-effect transistor

Cardiac troponin I (cTnI) is an efficient and specific biomarker for the accurate diagnosis of acute myocardial infarction (AMI), one of the diseases with the highest mortality worldwide. Due to the short course and high fatality of this disease, a rapid, accurate and portable device for quantitative detection is urgently needed for early diagnosis and treatment. In this work, we designed a handheld device based on a dual-gate ion-sensitive field-effect transistor (ISFET) for early and accurate warning of AMI through cTnI detection. A one-step enzyme-linked immunosorbent assay strategy was proposed for use in this device to recognize trace cTnI in serum, converting the cTnI concentration to a drain-source current generated by an ultrasensitive ISFET. This portable device exhibited an ultrahigh sensitivity of 132 pA pg−1·mL−1, a wide linear range from 1 to 1000 pg/mL that enabled coverage far exceeding the threshold level (280 pg/mL), and a low detection limit of 0.3 pg/mL for the cTnI assay, which was much lower than the current diagnostic cut-off for a healthy control level for AMI (40 pg/mL). In addition, this handheld device showed satisfactory selectivity and reliable results in the analysis of real serum within 20 min, indicating its potential applications in early screening and diagnosis for the clinical evaluation of AMI.

Solving the SSVEP Paradigm Using the Nonlinear Canonical Correlation Analysis Approach.

This paper presents the implementation of nonlinear canonical correlation analysis (NLCCA) approach to detect steady-state visual evoked potentials (SSVEP) quickly. The need for the fast recognition of proper stimulus to help end an SSVEP task in a BCI system is justified due to the flickering external stimulus exposure that causes users to start to feel fatigued. Measuring the accuracy and exposure time can be carried out through the information transfer rate—ITR, which is defined as a relationship between the precision, the number of stimuli, and the required time to obtain a result. NLCCA performance was evaluated by comparing it with two other approaches—the well-known canonical correlation analysis (CCA) and the least absolute reduction and selection operator (LASSO), both commonly used to solve the SSVEP paradigm. First, the best average ITR value was found from a dataset comprising ten healthy users with an average age of 28, where an exposure time of one second was obtained. In addition, the time sliding window responses were observed immediately after and around 200 ms after the flickering exposure to obtain the phase effects through the coefficient of variation (CV), where NLCCA obtained the lowest value. Finally, in order to obtain statistical significance to demonstrate that all approaches differ, the accuracy and ITR from the time sliding window responses was compared using a statistical analysis of variance per approach to identify differences between them using Tukey’s test.