Automatic Receipt Recognition System Based on Artificial Intelligence Technology

In this study, an automatic receipt recognition system (ARRS) is developed. First, a receipt is scanned for conversion into a high-resolution image. Receipt characters are automatically placed into two categories according to the receipt characteristics: printed and handwritten characters. Images of receipts with these characters are preprocessed separately. For handwritten characters, template matching and the fixed features of the receipts are used for text positioning, and projection is applied for character segmentation. Finally, a convolutional neural network is used for character recognition. For printed characters, a modified You Only Look Once (version 4) model (YOLOv4-s) executes precise text positioning and character recognition. The proposed YOLOv4-s model reduces downsampling, thereby enhancing small-object recognition. Finally, the system produces recognition results in a tax declaration format, which can upload to a tax declaration system. Experimental results revealed that the recognition accuracy of the proposed system was 80.93% for handwritten characters. Moreover, the YOLOv4-s model had a 99.39% accuracy rate for printed characters; only 33 characters were misjudged. The recognition accuracy of the YOLOv4-s model was higher than that of the traditional YOLOv4 model by 20.57%. Therefore, the proposed ARRS can considerably improve the efficiency of tax declaration, reduce labor costs, and simplify operating procedures.

Mechanical performance analysis and experimental study of soft-bodied bird-billed pneumatic gripper

Purpose Flexible mechanical gripper has better safety and adaptability than a rigid mechanical hand. At present, there are few soft grippers for small objects on a millimeter scale. Therefore, the purpose of this paper is to design a soft pneumatic gripper for grasping millimeter-scale small and fragile objects such as jewelry and electronic components. Design/methodology/approach By simulating the clamping action of the bird’s mouth and combining the high flexibility of the soft material, the bird’s beak soft pneumatic gripper is designed. First, the internal cavity of the gripping end of the gripper is determined by bending deformation calculation, and the brief manufacturing process of the gripper is outlined. Then, the single finger of the soft gripper is modeled mechanically, and the relationship between air pressure and bending deformation of the single finger is obtained. Finally, the experimental platform of the soft mechanical gripper is built, and the gripping performance of silicone rubber material is tested by comparison test, bending deformation test, stability test, adaptability test and gripping accuracy test. Findings The designed gripper has the advantages of simple structure, convenient operation, easy grasping of different small objects of millimeter-scale and good adaptability. It can grasp the precise dispensing needle with a minimum diameter of 0.19 mm, and its accuracy meets daily use. Originality/value A new type of soft pneumatic, the mechanical gripper is proposed and manufactured. According to the shape of the bird’s beak and the calculation of bending performance, a hollow finger gripper with better bending performance is designed. Various test results show that the gripper has a significant clamping effect on millimeter small objects, which supplements the research field of millimeter small object gripper.

Selecting Post-Processing Schemes for Accurate Detection of Small Objects in Low-Resolution Wide-Area Aerial Imagery

In low-resolution wide-area aerial imagery, object detection algorithms are categorized as feature extraction and machine learning approaches, where the former often requires a post-processing scheme to reduce false detections and the latter demands multi-stage learning followed by post-processing. In this paper, we present an approach on how to select post-processing schemes for aerial object detection. We evaluated combinations of each of ten vehicle detection algorithms with any of seven post-processing schemes, where the best three schemes for each algorithm were determined using average F-score metric. The performance improvement is quantified using basic information retrieval metrics as well as the classification of events, activities and relationships (CLEAR) metrics. We also implemented a two-stage learning algorithm using a hundred-layer densely connected convolutional neural network for small object detection and evaluated its degree of improvement when combined with the various post-processing schemes. The highest average F-scores after post-processing are 0.902, 0.704 and 0.891 for the Tucson, Phoenix and online VEDAI datasets, respectively. The combined results prove that our enhanced three-stage post-processing scheme achieves a mean average precision (mAP) of 63.9% for feature extraction methods and 82.8% for the machine learning approach.

TO THE PROBLEM OF APPLICABILITY OF THE TAMMAN TEMPERATURE CONCEPT TO NANOSIZED OBJECTS: TO THE 160TH ANNIVERSARY OF GUSTAV TAMMAN

Во введении представлен краткий критический обзор имеющихся интерпретаций температуры Таммана, обычно определяемой как T = 0,5T, и температуры Хюттига T = 0,3T, где T - макроскопическое значение температуры плавления материала. Для наночастиц предложено в указанных выше определяющих соотношениях заменить T на температуру плавления малого объекта T, т.е. определить T как 0,5T, а T как 0,3T. В молекулярно-динамических экспериментах на наночастицах Au, осуществленных с помощью LAMMPS, было установлено, что при температуре T=T как в центральной части ГЦК-наночастицы, так и в её поверхностном слое возникают локальные очаги квазикристаллической структуры, которые попеременно идентифицируются программой OVITO то как имеющие кристаллическую структуру, то как не имеющие кристаллической упорядоченности. Однако, вопреки мнению Э. Рукенштейна (1984), при T=T жидкий слой на поверхности кристаллической наночастицы еще не образуется. Вместе с тем в наших молекулярно-динамических экспериментах не обнаружено какое-либо проявление температуры Хюттига T в структуре кристаллических наночастиц Au. The introduction provides a brief critical review of the available definitions and interpretations of the Tamman temperature, usually defined as T = 0,5T, and of the Hüttig temperature T = 0,3T where T is the macroscopic value of the melting point of the material. For a nanoparticle we propose to replace in the above relations T by the melting temperature of the small object T , i.e. to define T as 0,5T and T as 0,3T . In our molecular dynamics experiments on Au nanoparticles, carried out using the LAMMPS program, we found that at the temperature T = T , in both the central part of the fcc nanoparticle (the core) and in its surface layer (the shell), some local species of a quasicrystalline structure appear which are alternately identified either as crystalline or as non-crystalline by the OVITO program. However, contrary to opinion of E. Rukenstein (1984), at T = T , a liquid layer on the surface of the crystalline nanoparticle is not formed yet. However, a liquid-like layer was gradually developed in the course of the further temperature elevation. At the same time, in our molecular dynamics experiments we did not reveal any manifestation of the Huttig temperature T in the structure of crystalline Au nanoparticles reproduced in our molecular dynamics experiments. It is also of interest that in our molecular dynamics experiments the nanoparticle sintering took place not only above the Tammann temperature but below it as well.

Microencapsulation Technology a Holistic Approach in the Field of Pharmaceutical Sciences a Review

Microencapsulation is a technique that uses a coating to encapsulate microscopic particles or droplets in order to generate miniature capsules with therapeutic properties. The substance contained within the microcapsule is referred to as the core, internal phase, or fill, whereas the wall is referred to as a shell, coating, or membrane. A microcapsule is a small object that contains essential items, internal components, or fillers and is encased by a shell, cover, or membrane. Microcapsules range in size from 1 to 1000 micrometres. This approach is frequently used for medication administration, molecular protection, and robustness. The microencapsulation programme has been established as a different delivery mechanism for multiple treatment regimens and offers potential benefits beyond those of normal medication delivery systems. Microencapsulation is a well-established review dedicated to the preparation, properties, and applications of individually encapsulated novel small particles, as well as significant improvements to tried-and-tested techniques relevant to micro and nano particles and their use in a wide range of industrial, engineering, pharmaceutical, biotechnology, and research applications. Its scope extends beyond conventional microcapsules to all other small particulate systems, such as self-assembling structures that involve preparative manipulation.

A Small Object Detection Research Based on Dynamic Convolution Neural Network

In view of the fact that the detection effect of EfficientNet-YOLOv3 object detection algorithm is not very good, this paper proposes a small object detection research based on dynamic convolution neural network. Firstly, the dynamic convolutional neural network is introduced to replace the traditional, which makes the algorithm model more robust; secondly, the optimization parameters are continuously adjusted in the training process to further strengthen the model structure; finally, the Learning Rate and Batch Size parameters are modified during the training process in order to prevent overfitting. In order to verify the effectiveness of the proposed algorithm, RSOD and TGRS-HRRSD remote sensing image data sets are used to test the effect. The results of the proposed algorithm on RSOD remote sensing image data sets show that compared with the original EfficientNet-YOLOv3 algorithm, the mean Average Precision (mAP) value is increased by 1.93% and the mean Log Average Miss Rate (mLAMR) value is reduced by 0.0500; The results of the proposed algorithm on TGRS-HRRSD remote sensing image data set show that compared with the original EfficientNet-YOLOv3 algorithm, the mAP value is increased by 0.07% and the mLAMR value is reduced by 0.0007.

Benchmarking Human Performance for Visual Search of Aerial Images

Aerial images are frequently used in geospatial analysis to inform responses to crises and disasters but can pose unique challenges for visual search when they contain low resolution, degraded information about color, and small object sizes. Aerial image analysis is often performed by humans, but machine learning approaches are being developed to complement manual analysis. To date, however, relatively little work has explored how humans perform visual search on these tasks, and understanding this could ultimately help enable human-machine teaming. We designed a set of studies to understand what features of an aerial image make visual search difficult for humans and what strategies humans use when performing these tasks. Across two experiments, we tested human performance on a counting task with a series of aerial images and examined the influence of features such as target size, location, color, clarity, and number of targets on accuracy and search strategies. Both experiments presented trials consisting of an aerial satellite image; participants were asked to find all instances of a search template in the image. Target size was consistently a significant predictor of performance, influencing not only accuracy of selections but the order in which participants selected target instances in the trial. Experiment 2 demonstrated that the clarity of the target instance and the match between the color of the search template and the color of the target instance also predicted accuracy. Furthermore, color also predicted the order of selecting instances in the trial. These experiments establish not only a benchmark of typical human performance on visual search of aerial images but also identify several features that can influence the task difficulty level for humans. These results have implications for understanding human visual search on real-world tasks and when humans may benefit from automated approaches.

Identification of public submitted tick images: A neural network approach

Ticks and tick-borne diseases represent a growing public health threat in North America and Europe. The number of ticks, their geographical distribution, and the incidence of tick-borne diseases, like Lyme disease, are all on the rise. Accurate, real-time tick-image identification through a smartphone app or similar platform could help mitigate this threat by informing users of the risks associated with encountered ticks and by providing researchers and public health agencies with additional data on tick activity and geographic range. Here we outline the requirements for such a system, present a model that meets those requirements, and discuss remaining challenges and frontiers in automated tick identification. We compiled a user-generated dataset of more than 12,000 images of the three most common tick species found on humans in the U.S.: Amblyomma americanum, Dermacentor variabilis, and Ixodes scapularis. We used image augmentation to further increase the size of our dataset to more than 90,000 images. Here we report the development and validation of a convolutional neural network which we call “TickIDNet,” that scores an 87.8% identification accuracy across all three species, outperforming the accuracy of identifications done by a member of the general public or healthcare professionals. However, the model fails to match the performance of experts with formal entomological training. We find that image quality, particularly the size of the tick in the image (measured in pixels), plays a significant role in the network’s ability to correctly identify an image: images where the tick is small are less likely to be correctly identified because of the small object detection problem in deep learning. TickIDNet’s performance can be increased by using confidence thresholds to introduce an “unsure” class and building image submission pipelines that encourage better quality photos. Our findings suggest that deep learning represents a promising frontier for tick identification that should be further explored and deployed as part of the toolkit for addressing the public health consequences of tick-borne diseases.

A robust approach for industrial small-object detection using an improved faster regional convolutional neural network

With the increasing pace in the industrial sector, the need for a smart environment is also increasing and the production of industrial products in terms of quality always matters. There is a strong burden on the industrial environment to continue to reduce impulsive downtime, concert deprivation, and safety risks, which needs an efficient solution to detect and improve potential obligations as soon as possible. The systems working in industrial environments for generating industrial products are very fast and generate products rapidly, sometimes leading to faulty products. Therefore, this problem needs to be solved efficiently. Considering this problem in terms of faulty small-object detection, this study proposed an improved faster regional convolutional neural network-based model to detect the faults in the product images. We introduced a novel data-augmentation method along with a bi-cubic interpolation-based feature amplification method. A center loss is also introduced in the loss function to decrease the inter-class similarity issue. The experimental results show that the proposed improved model achieved better classification accuracy for detecting our small faulty objects. The proposed model performs better than the state-of-the-art methods.