Existing Recognition Systems Research Articles

Exploring User-Defined Gestures as Input for Hearables and Recognizing Ear-Level Gestures with IMUs

Hearables are highly functional earphone-type wearables; however, existing input methods using stand-alone hearables are limited in the number of commands, and there is a need to extend device operation through hand gestures. In previous research on hearables for hand input, user understanding and gesture recognition systems have been developed. However, in the realm of user understanding, investigation concerning hand input with hearables remains incomplete, and existing recognition systems have not demonstrated proficiency in discerning user-defined gestures. In this study, we conducted a gesture elicitation study (GES) assuming hand input using hearables under six conditions (three interaction areas x two device shapes). Then, we extracted ear-level gestures that the device's built-in IMU sensor could recognize from the user-defined gestures and investigated the recognition performance. The results of sitting experiments showed that the gesture recognition rate for in-ear devices was 91.0% and that for ear-hook devices was 74.7%.

An Improved YOLOv7-Based Model for Real-Time Meter Reading with PConv and Attention Mechanisms.

With the increasing complexity of the grid meter dial, precise feature extraction is becoming more and more difficult. Many automatic recognition solutions have been proposed for grid meter readings. However, traditional inspection methods cannot guarantee detection accuracy in complex environments. So, deep-learning methods are combined with grid meter recognition. Existing recognition systems that utilize segmentation models exhibit very high computation. It is challenging to ensure high real-time performance in edge computing devices. Therefore, an improved meter recognition model based on YOLOv7 is proposed in this paper. Partial convolution (PConv) is introduced into YOLOv7 to create a lighter network. Different PConv introduction locations on the base module have been used in order to find the optimal approach for reducing the parameters and floating point of operations (FLOPs). Meanwhile, the dynamic head (DyHead) module is utilized to enhance the attention mechanism for the YOLOv7 model. It can improve the detection accuracy of striped objects. As a result, this paper achieves mAP50val of 97.87% and mAP50:90val of 62.4% with only 5.37 M parameters. The improved model's inference speed can reach 108 frames per second (FPS). It enables detection accuracy that can reach ±0.1 degrees in the grid meter.

Generating bimodal privacy-preserving data for face recognition

The performance of state-of-the-art face recognition systems depends crucially on the availability of large-scale training datasets. However, increasing privacy concerns nowadays accompany the collection and distribution of biometric data, which has already resulted in the retraction of valuable face recognition datasets. The use of synthetic data represents a potential solution, however, the generation of privacy-preserving facial images useful for training recognition models is still an open problem. Generative methods also remain bound to the visible spectrum, despite the benefits that multispectral data can provide. To address these issues, we present a novel identity-conditioned generative framework capable of producing large-scale recognition datasets of visible and near-infrared privacy-preserving face images. The framework relies on a novel identity-conditioned dual-branch style-based generative adversarial network to enable the synthesis of aligned high-quality samples of identities determined by features of a pretrained recognition model. In addition, the framework incorporates a novel filter to prevent samples of privacy-breaching identities from reaching the generated datasets and improve both identity separability and intra-identity diversity. Extensive experiments on six publicly available datasets reveal that our framework achieves competitive synthesis capabilities while preserving the privacy of real-world subjects. The synthesized datasets also facilitate training more powerful recognition models than datasets generated by competing methods or even small-scale real-world datasets. Employing both visible and near-infrared data for training also results in higher recognition accuracy on real-world visible spectrum benchmarks. Therefore, training with multispectral data could potentially improve existing recognition systems that utilize only the visible spectrum, without the need for additional sensors.

A Handwriting Recognition System With WiFi

Handwriting recognition systems are a convenient and alternative way of writing in the air with fingers rather than typing on keyboards. However, existing recognition systems are limited by their low accuracy and the requirement to wear dedicated devices. To address these issues, we propose WiWrite, an accurate contactless handwriting recognition system that allows users to write in the air without wearing any wearable devices. Specifically, we employ a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CSI division scheme</i> to process the noisy raw WiFi channel state information (CSI), which stabilizes the CSI phase and reduces noise in CSI amplitude. To automatically retain low noise data for identification in the LOS scenario, we propose a self-paced dense convolutional network (SPDCN), which is a self-paced loss function based on a modified convolutional neural network coupled with a dense convolutional network. Furthermore, to achieve accurate handwriting recognition in the NLOS scenario, we combine ADOA and PCA algorithms to remove location-induced interference and extract action features. Comprehensive experiments show the merits of WiWrite, revealing that the recognition accuracy for the same-size input and different-size input are 93.6% and 89.0%, respectively. Moreover, WiWrite can achieve accurate recognition regardless of environment and target diversity in LOS and NLOS scenarios.

Strawberry Maturity Recognition Based on Improved YOLOv5

Strawberry maturity detection plays an essential role in modern strawberry yield estimation and robot-assisted picking and sorting. Due to the small size and complex growth environment of strawberries, there are still problems with existing recognition systems’ accuracy and maturity classifications. This article proposes a strawberry maturity recognition algorithm based on an improved YOLOv5s model named YOLOv5s-BiCE. This algorithm model is a replacement of the upsampling algorithm with a CARAFE module structure. It is an improvement on the previous model in terms of its content-aware processing; it also widens the field of vision and maintains a high level of efficiency, resulting in improved object detection capabilities. This article also introduces a double attention mechanism named Biformed for small-target detection, optimizing computing allocation, and enhancing content perception flexibility. Via multi-scale feature fusion, we utilized double attention mechanisms to reduce the number of redundant computations. Additionally, the Focal_EIOU optimization method was introduced to improve its accuracy and address issues related to uneven sample classification in the loss function. The YOLOv5s-BiCE algorithm was better at recognizing strawberry maturity compared to the original YOLOv5s model. It achieved a 2.8% increase in the mean average precision and a 7.4% increase in accuracy for the strawberry maturity dataset. The improved algorithm outperformed other networks, like YOLOv4-tiny, YOLOv4-lite-e, YOLOv4-lite-s, YOLOv7, and Fast RCNN, with recognition accuracy improvements of 3.3%, 4.7%, 4.2%, 1.5%, and 2.2%, respectively. In addition, we developed a corresponding detection app and combined the algorithm with DeepSort to apply it to patrol robots. It was found that the detection algorithm exhibits a fast real-time detection speed, can support intelligent estimations of strawberry yield, and can assist picking robots.

Recent advances of ML and DL approaches for Arabic handwriting recognition: A review

Handwritten text recognition remains a popular area of research. An analysis of these techniques is more necessary. This article is practically interested in a bibliographic study on existing recognition systems with the aim of motivating researchers to look into these techniques and try to develop more advanced ones. It presents a detailed comparative study carried out on some Arabic handwritten character recognition techniques using holistic, analytical and a segmentation-free approaches. In this study, first, we show the difference between different recognition approaches: deep learning vs machine learning. Secondly, a description of the Arabic handwriting recognition process regrouping pre-processing, feature extraction and segmentation was presented. Then, we illustrate the main techniques used in the field of handwriting recognition and we make a synthesis of these methods.

GCF2-Net: global-aware cross-modal feature fusion network for speech emotion recognition.

Emotion recognition plays an essential role in interpersonal communication. However, existing recognition systems use only features of a single modality for emotion recognition, ignoring the interaction of information from the different modalities. Therefore, in our study, we propose a global-aware Cross-modal feature Fusion Network (GCF2-Net) for recognizing emotion. We construct a residual cross-modal fusion attention module (ResCMFA) to fuse information from multiple modalities and design a global-aware module to capture global details. More specifically, we first use transfer learning to extract wav2vec 2.0 features and text features fused by the ResCMFA module. Then, cross-modal fusion features are fed into the global-aware module to capture the most essential emotional information globally. Finally, the experiment results have shown that our proposed method has significant advantages than state-of-the-art methods on the IEMOCAP and MELD datasets, respectively.

Exploiting Human Pose and Scene Information for Interaction Detection

Identifying human actions and interactions finds its use in many areas, such as security, surveillance, assisted living, patient monitoring, rehabilitation, sports, and e-learning. This wide range of applications has attracted many researchers to this field. Inspired by the existing recognition systems, this paper proposes a new and efficient human-object interaction recognition (HOIR) model which is based on modeling human pose and scene feature information. There are different aspects involved in an interaction, including the humans, the objects, the various body parts of the human, and the background scene. The main objectives of this research include critically examining the importance of all these elements in determining the interaction, estimating human pose through image foresting transform (IFT), and detecting the performed interactions based on an optimized multi-feature vector. The proposed methodology has six main phases. The first phase involves preprocessing the images. During preprocessing stages, the videos are converted into image frames. Then their contrast is adjusted, and noise is removed. In the second phase, the human-object pair is detected and extracted from each image frame. The third phase involves the identification of key body parts of the detected humans using IFT. The fourth phase relates to three different kinds of feature extraction techniques. Then these features are combined and optimized during the fifth phase. The optimized vector is used to classify the interactions in the last phase. The MSR Daily Activity 3D dataset has been used to test this model and to prove its efficiency. The proposed system obtains an average accuracy of 91.7% on this dataset.

Adaptive ship-radiated noise recognition with learnable fine-grained wavelet transform

Analyzing the ocean acoustic environment is a tricky task. Background noise and variable channel transmission environment make it complicated to implement accurate ship-radiated noise recognition. Existing recognition systems are weak in addressing the variable underwater environment, thus leading to disappointing performance in practical application. In order to keep the recognition system robust in various underwater environments, this work proposes an adaptive generalized recognition system — AGNet (Adaptive Generalized Network). By converting fixed wavelet parameters into fine-grained learnable parameters, AGNet learns the characteristics of underwater sound at different frequencies. Its flexible and fine-grained design is conducive to capturing more background acoustic information (e.g., background noise, underwater transmission channel). To utilize the implicit information in wavelet spectrograms, AGNet adopts the convolutional neural network with parallel convolution attention modules as the classifier. Experiments reveal that our AGNet outperforms all baseline methods on several underwater acoustic datasets, and AGNet could benefit more from transfer learning. Moreover, AGNet shows robust performance against various interference factors.

Developing a Speech Recognition System for Recognizing Tonal Speech Signals Using a Convolutional Neural Network

Deep learning-based machine learning models have shown significant results in speech recognition and numerous vision-related tasks. The performance of the present speech-to-text model relies upon the hyperparameters used in this research work. In this research work, it is shown that convolutional neural networks (CNNs) can model raw and tonal speech signals. Their performance is on par with existing recognition systems. This study extends the role of the CNN-based approach to robust and uncommon speech signals (tonal) using its own designed database for target research. The main objective of this research work was to develop a speech-to-text recognition system to recognize the tonal speech signals of Gurbani hymns using a CNN. Further, the CNN model, with six layers of 2DConv, 2DMax Pooling, and 256 dense layer units (Google’s TensorFlow service) was also used in this work, as well as Praat for speech segmentation. Feature extraction was enforced using the MFCC feature extraction technique, which extracts standard speech features and features of background music as well. Our study reveals that the CNN-based method for identifying tonal speech sentences and adding instrumental knowledge performs better than the existing and conventional approaches. The experimental results demonstrate the significant performance of the present CNN architecture by providing an 89.15% accuracy rate and a 10.56% WER for continuous and extensive vocabulary sentences of speech signals with different tones.

Convolutional neural networks framework for human hand gesture recognition

Recently, the recognition of human hand gestures is becoming a valuable technology for various applications like sign language recognition, virtual games and robotics control, video surveillance, and home automation. Owing to the recent development of deep learning and its excellent performance, deep learning-based hand gesture recognition systems can provide promising results. However, accurate recognition of hand gestures remains a substantial challenge that faces most of the recently existing recognition systems. In this paper, convolutional neural networks (CNN) framework with multiple layers for accurate, effective, and less complex human hand gesture recognition has been proposed. Since the images of the infrared hand gestures can provide accurate gesture information through the low illumination environment, the proposed system is tested and evaluated on a database of hand-based near-infrared which including ten gesture poses. Extensive experiments prove that the proposed system provides excellent results of accuracy, precision, sensitivity (recall), and F1-score. Furthermore, a comparison with recently existing systems is reported.

Post-comparison mitigation of demographic bias in face recognition using fair score normalization

Abstract Current face recognition systems achieve high progress on several benchmark tests. Despite this progress, recent works showed that these systems are strongly biased against demographic sub-groups. Consequently, an easily integrable solution is needed to reduce the discriminatory effect of these biased systems. Previous work mainly focused on learning less biased face representations, which comes at the cost of a strongly degraded overall recognition performance. In this work, we propose a novel unsupervised fair score normalization approach that is specifically designed to reduce the effect of bias in face recognition and subsequently lead to a significant overall performance boost. Our hypothesis is built on the notation of individual fairness by designing a normalization approach that leads to treating “similar” individuals “similarly”. Experiments were conducted on three publicly available datasets captured under controlled and in-the-wild circumstances. Results demonstrate that our solution reduces demographic biases, e.g. by up to 82.7% in the case when gender is considered. Moreover, it mitigates the bias more consistently than existing works. In contrast to previous works, our fair normalization approach enhances the overall performance by up to 53.2% at false match rate of 10 − 3 and up to 82.9% at a false match rate of 10 − 5 . Additionally, it is easily integrable into existing recognition systems and not limited to face biometrics.

A Text Classification Algorithm Based on Improved Multidimensional–Multiresolution Topological Pattern Recognition

Traditional pattern recognition is based on “optimal partition” and the goal is to find an optimal classification interface based on the distribution of each category in high-dimensional space, thus has its inherent shortcomings and deficiencies. While topology pattern recognition can effectively compensate for the shortcomings of traditional pattern recognition, topological pattern recognition is based on “cognition” and the goal is to find the appropriate cover according to the “complex set cover” in high-dimensional space to achieve cognitive effect. Topological pattern recognition can effectively consummate the characteristics of high error rate, low recognition rate and repetitive training in the existing recognition system with low training sample number. At present, topology pattern recognition has been applied in many areas of social life. However, one problem that can’t be ignored is that topological pattern recognition requires a long training time and low fault tolerance rate. Therefore, this paper proposes an improved multidimensional–multiresolution topological pattern recognition, and applies it to text classification and recognition. The results show that the improved multidimensional–multiresolution topological pattern recognition method can effectively reduce the training time of text classification and improve the classification efficiency.

Eyes Wide Open: an interactive learning method for the design of rule-based systems

We present in this paper a new general method, the Eyes Wide Open method (EWO) for the design of rule-based document recognition systems. Our contribution is to introduce a learning procedure, through machine learning techniques, in interaction with the user to design the recognition system. Therefore, and unlike many approaches that are manually designed, ours can easily adapt to a new type of documents while taking advantage of the expressiveness of rule-based systems and their ability to convey the hierarchical structure of a document. The EWO method is independent of any existing recognition system. An automatic analysis of an annotated corpus, guided by the user, is made to help the adaption of the recognition system to a new kind of document. The user will then bring sense to the automatically extracted information. In this paper, we validate EWO by producing two rule-based systems: one for the Maurdor international competition, on a heterogeneous corpus of documents, containing handwritten and printed documents, written in different languages and another one for the RIMES competition corpus, a homogeneous corpus of French handwritten business letters. On the RIMES corpus, our method allows an assisted design of a grammatical description that gives better results than all the previously proposed statistical systems.

Unconstrained handwritten digit recognition using perceptual shape primitives

In this paper, we propose a new handwritten digit recognition method which works in a very similar way as human perception. The digit image boundary is decomposed into four salient visual primitives, namely closure, smooth curve, protrusion and straight segment by defining a set of external symmetry axis. Unlike the conventional algorithms, our low complexity shape decomposition method neither searches for curvature minima nor finds optimal parsing by using shortcut and convexity rules. Based on the spatial configuration of extracted primitives, the recognizer classifies a test digit image using a set of classification rules. The performance of our proposed recognition system is evaluated on five digit datasets of four popular scripts, Odia, Bangla, Arabic and English. The recognition accuracies on the ISI Kolkata Odia and Bangla, IITBBS Odia, CMATERdb Arabic and MNIST English digit datasets are found to be 99.02, 99.25, 99.66, 97.96 and 99.11%, respectively. The proposed method outperforms the existing recognition systems on both the Odia digit datasets and achieves comparable performance in other cases.

СИСТЕМА РАСПОЗНАВАНИЯ ОБЪЕКТОВ НА ДОРОГЕ

This article outlines the existing safety problems on the road, describes the existing recognition systems of well-known automobile manufacturers, and considers advantages and disadvantages of existing solutions. The general scheme of solving the problem of objects detection and recognition was showed.

Supervised dictionary learning with multiple classifier integration

Supervised sparse coding has become a widely-used module in existing recognition systems, which unifies classifier training and dictionary learning to enforce discrimination in sparse codes. Many existing methods suffer from the insufficient discrimination when dealing with high-complexity data due to the use of simple supervised techniques. In this paper, we integrate multiple classifier training into dictionary learning to overcome such a weakness. A minimization model is developed, in which an ensemble of classifiers for prediction and a dictionary for representation are jointly learned. The ensemble of classifiers is constructed from a set of linear classifiers, each of which is associated with a group of atoms and applied to the corresponding sparse codes. Such a construction scheme allows the dictionary and all the classifiers to be simultaneously updated during training. In addition, we provide an interesting insight into label consistency from the view of multiple classifier learning by showing its relation with the proposed method. Compared with the existing supervised sparse coding approaches, our method is able to learn a compact dictionary with better discrimination and a set of classifiers with improved robustness. The experiments in several image recognition tasks show the improvement of the proposed method over several state-of-the-art approaches.

An Innovative and Effective Approach for Sclera Detection

Background/Objectives: Providing security to systems is one of the major challenges faced in day-to-day life. Biometrics plays a vital role in ensuring security. Out of the different existing recognition systems available - namely face, finger, gait, retina and so on, sclera recognition system gives out better performance. Sclera is the white part of the eye, which is unique and consistent in nature because of which it is chosen for recognition. In this paper, we analyzed the existing sclera recognition system with both human and animal eye images. Methods/Statistical Analysis: In this paper, we compared the performance of the algorithm with both human and animal eye images. The animals we considered for the algorithm analysis include deer, buffalo and lion. Human eyes are the most observable due to the presence of more sclera area. The blood vessel patterns present in the sclera region are stable over lifetime and unique person by person, thus making it appropriate for identification. The results show that the algorithm works better for human eye. Results/Findings: In this paper, we compared the extracted input vessel structure with that in the database and verify whether the input is authorized or not. It is observed that the system underperforms for animal eye images, whereas it shows an acceptable performance with human eye images. Conclusion/Application: The results prove that the algorithm works satisfactorily for identifying human. It can be incorporated with other recognition systems to build up a multimodal biometric system that can provide better security than the existing systems.

Interview

Dr Damien Vivet, of the University of Orléans, talks about the story behind their paper ‘Access control based on gait analysis and face recognition’ page 751. Dr Damien Vivet My field focuses on multi-modal perception and its interpretation for an efficient use of sensor measurements, whatever the modality (radar, vision, laser…). I worked on various applications such as localisation and mapping for robots, autonomous or assisted driving and even for traffic analysis. Even though robotics is a very interesting research field, I wanted to apply such perception technics in a different context with the objective to assist people and analyse their behaviours. Our Letter presents a human recognition application for access control, but it has also been applied in a medical context to distinguish patients in nursing homes. I think home care applications have a big future in the current context of an aging population. For example, in France, by 2035, it is estimated that 31% of people will be over 60 years old and 13.6% will be over 75. In this situation, applications to improve home care take a very important dimension. It seems natural that detection and localisation technics used to measure activities, will be essential to increase the autonomy of these populations. This research area is wide, but we try to make a contribution by proposing descriptors in order to detect and understand human behaviour. In this article, we deal with gait, but within our research team other works are in progress on human 3D pose detection, emotion analysis and even abnormal event detection. We have proposed a people identification technic based on gait analysis and face recognition, applied and evaluated in an access control context. Our system is based on a unique low-cost camera and can be easily positioned in a room to analyse the gait of the detected people. The system is able to detect people and their faces automatically and to process both static (for faces) and dynamic (for gait) descriptors. Based on previous learning about the characteristics, the system is able to identify detected people very accurately even if the face is hidden. Existing recognition systems are mainly based on face recognition. Their main problem is when the face is hidden, for example, when people are wearing a hat, or when the detected faces are of poor quality (small image size, noisy image), detection cannot be done. Our system overcomes these limitations as, in such conditions, it can identify people using only their gait, even from the back. Of course very different clothing can also cause problems for our gait descriptor. This is why we chose to use both. In my opinion, human analysis research has a bright future. The need for behaviour analysis is increasing, whether for security or access control, home care application or even for intelligent management of building energy use in response to occupant activities. Nevertheless, we should be aware of the ethical problems of such systems. For me, the main challenge to overcome is the public's acceptance of camera sensors in a housing environment or even on the streets. Respect for private life is becoming more and more important so such visual sensors could become unsuitable. Even if we certify that no image is transmitted outside the system, people are still reticent to have such technology at home. If we want this development to happen and to be integrated in future intelligent houses, new non-intrusive imaging sensors have to be developed. Part of our group is exploring scene analysis with the objective of detecting if something that happens is abnormal or not. For this purpose, we are developing new descriptors to characterise scenes. For example, in addition to face, emotion or gait descriptors, we are currently trying to extract the 3D human pose using only a single camera, in order to easily detect and recognise activities. Moreover, we don’t just consider people, but also deal with traffic monitoring to detect infractions or accidents using a camera network.

Biometrics-based consumer applications driven by reconfigurable hardware architectures

Nowadays the development of automatic biometrics-based personal recognition systems is a reality in the current technological age. Not only those applications demanding stringent security levels but also many daily use consumer applications request the existence of high performance computational platforms in charge of recognizing the identity of an individual based on the analysis of his/her physiological or behavioural characteristics. The state of the art points out two main open problems in the implementation of such automatic applications: on the one hand, the needed improvement of the reliability level of the existing recognition systems in terms of accuracy, security and real-time performances; on the other hand, the cost reduction of those physical platforms in charge of the processing. This work addresses those limitations of current systems and aims at finding the proper system architecture to develop this kind of high-performance applications at low cost. Because of that, those existing solutions based on expensive multiprocessor systems like HPC (High Performance Computer), GPU (Graphics Processing Unit), or PC (Personal Computer) platforms need to be discarded, and instead of them embedded system solutions based on programmable logic devices are suggested in this work. The programmability performances of FPGA (Field Programmable Gate Array) devices together with the inherent parallelism of hardware design provide the needed flexibility to develop made-to-measure coprocessors in charge of accelerating those time-critical computational tasks. To address the cost of the system, dynamically reconfigurable FPGAs are suggested in this work. The scheduling of the recognition application into a series of mutually exclusive tasks, and the reutilization of those functional resources available in the FPGA by multiplexing different coprocessors in the same area along the application execution time allows reducing the size of the device and therefore its cost at the expense of the reconfiguration overhead. The hardware–software co-design of an AFAS (automatic fingerprint-based authentication system) under two different run-time reconfigurable platforms is presented as the proof of concept of the suggested architecture. The outstanding results achieved in this work pave the way for the implementation of biometric applications by means of run-time reconfigurable FPGAs.