recognition of objects
Recently Published Documents


TOTAL DOCUMENTS

231
(FIVE YEARS 71)

H-INDEX

18
(FIVE YEARS 3)

Electronics ◽  
2022 ◽  
Vol 11 (2) ◽  
pp. 278
Author(s):  
Cătălina Lucia Cocianu ◽  
Cristian Răzvan Uscatu

Many technological applications of our time rely on images captured by multiple cameras. Such applications include the detection and recognition of objects in captured images, the tracking of objects and analysis of their motion, and the detection of changes in appearance. The alignment of images captured at different times and/or from different angles is a key processing step in these applications. One of the most challenging tasks is to develop fast algorithms to accurately align images perturbed by various types of transformations. The paper reports a new method used to register images in the case of geometric perturbations that include rotations, translations, and non-uniform scaling. The input images can be monochrome or colored, and they are preprocessed by a noise-insensitive edge detector to obtain binarized versions. Isotropic scaling transformations are used to compute multi-scale representations of the binarized inputs. The algorithm is of memetic type and exploits the fact that the computation carried out in reduced representations usually produces promising initial solutions very fast. The proposed method combines bio-inspired and evolutionary computation techniques with clustered search and implements a procedure specially tailored to address the premature convergence issue in various scaled representations. A long series of tests on perturbed images were performed, evidencing the efficiency of our memetic multi-scale approach. In addition, a comparative analysis has proved that the proposed algorithm outperforms some well-known registration procedures both in terms of accuracy and runtime.


2022 ◽  
Vol 12 (1) ◽  
pp. 97
Author(s):  
Elisa Visani ◽  
Davide Rossi Sebastiano ◽  
Dunja Duran ◽  
Gioacchino Garofalo ◽  
Fabio Magliocco ◽  
...  

Current literature supports the notion that the recognition of objects, when visually presented, is sub-served by neural structures different from those responsible for the semantic processing of their nouns. However, embodiment foresees that processing observed objects and their verbal labels should share similar neural mechanisms. In a combined behavioral and MEG study, we compared the modulation of motor responses and cortical rhythms during the processing of graspable natural objects and tools, either verbally or pictorially presented. Our findings demonstrate that conveying meaning to an observed object or processing its noun similarly modulates both motor responses and cortical rhythms; being natural graspable objects and tools differently represented in the brain, they affect in a different manner both behavioral and MEG findings, independent of presentation modality. These results provide experimental evidence that neural substrates responsible for conveying meaning to objects overlap with those where the object is represented, thus supporting an embodied view of semantic processing.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yoshiko Bamba ◽  
Shimpei Ogawa ◽  
Michio Itabashi ◽  
Shingo Kameoka ◽  
Takahiro Okamoto ◽  
...  

AbstractAnalysis of operative data with convolutional neural networks (CNNs) is expected to improve the knowledge and professional skills of surgeons. Identification of objects in videos recorded during surgery can be used for surgical skill assessment and surgical navigation. The objectives of this study were to recognize objects and types of forceps in surgical videos acquired during colorectal surgeries and evaluate detection accuracy. Images (n = 1818) were extracted from 11 surgical videos for model training, and another 500 images were extracted from 6 additional videos for validation. The following 5 types of forceps were selected for annotation: ultrasonic scalpel, grasping, clip, angled (Maryland and right-angled), and spatula. IBM Visual Insights software was used, which incorporates the most popular open-source deep-learning CNN frameworks. In total, 1039/1062 (97.8%) forceps were correctly identified among 500 test images. Calculated recall and precision values were as follows: grasping forceps, 98.1% and 98.0%; ultrasonic scalpel, 99.4% and 93.9%; clip forceps, 96.2% and 92.7%; angled forceps, 94.9% and 100%; and spatula forceps, 98.1% and 94.5%, respectively. Forceps recognition can be achieved with high accuracy using deep-learning models, providing the opportunity to evaluate how forceps are used in various operations.


2021 ◽  
pp. 52-63
Author(s):  
Елена Владимировна Демишкевич ◽  
Оксана Александровна Кузина ◽  
Татьяна Петровна Найденова

Статья посвящена вопросу изучения русского языка как иностранного. Помощь в изучении русского языка может оказать словарь, как богатый источник информации. Целью работы является показать, что предложенная работа со словарём является полезным видом деятельности. Словарь можно использовать как при чтении, так и при выполнении письменных работ. Данная работа играет важную роль в изучении русского языка как иностранного. Авторы обращают внимание, что герменевтическая и лингвистическая функции представляют собой систему профессионально  значимых операций, видов и форм учебной деятельности при овладении иностранным языком. К используемым методам относятся: метод пояснения, метод сопоставления, метод уточнения. Методологический основой послужили работы в области теоретической и практической  методики преподавания иностранных языков. Результатом является описание профессионально значимых операций, видов и форм учебной деятельности, которые можно использовать при работе со словарём. К герменевтической функции относятся: понимание, восприятие, осмысление, узнавание предметов и явлений, речевая деятельность, структурная схема речевой деятельности, речь, понятие смысловой структуры текста и тектообразующая функция терминов. К лингвистической функции относятся: оперирование лексическими и грамматическими нормами оформления терминов, моделирование групп терминов, владение орфографическими, орфоэпическими нормами оформления терминов, оформление результатов обмена информацией, формирование отдельных навыков словоупотребления и осмысление экстралингвистической информации. Приводятся примеры работы со словарной статьёй. Результаты могут быть применены при обучении иностранных обучающихся русскому языку как иностранному в военно-морских вузах. Авторы пришли к выводу, что обучение иностранных слушателей возможно проводить по специально разработанной программе, которую необходимо строить с учетом учебного материала и тех видов речевой деятельности, в которые включается обучающийся на занятиях по профилирующим предметам. The article is devoted to the issue of studying Russian as a foreign language. A dictionary can help you learn Russian as a rich source of information. The purpose of the work is to show that the proposed work with the dictionary is a useful activity. The dictionary can be used both when reading and when doing written work. This work plays an important role in the study of Russian as a foreign language. The authors draw attention to the fact that hermeneutical and linguistic functions represent a system of professionally significant operations, types and forms of educational activity in mastering a foreign language. The methods used include: the method of explanation, the method of comparison, the method of clarification. The methodological basis was the work in the field of theoretical and practical methods of teaching foreign languages. The result is a description of professionally significant operations, types and forms of educational activities that can be used when working with a dictionary. The hermeneutic function includes: understanding, perception, comprehension, recognition of objects and phenomena, speech activity, the structural scheme of speech activity, speech, the concept of the semantic structure of the text and the tectonic function of terms. The linguistic function includes: the operation of lexical and grammatical norms of the design of terms, the modeling of groups of terms, the possession of spelling, orthoepic norms of the design of terms, the design of the results of information exchange, the formation of individual skills of word usage and the comprehension of extralinguistic information. Examples of working with a dictionary entry are given. The results can be applied in teaching foreign students Russian as a foreign language in naval universities. The authors came to the conclusion that the training of foreign students can be carried out according to a specially developed program, which must be built taking into account the educational material and those types of speech activity in which the student is included in the classes on core subjects.


2021 ◽  
Vol 41 (40) ◽  
pp. 8375-8389
Author(s):  
Loris Naspi ◽  
Paul Hoffman ◽  
Barry Devereux ◽  
Alexa M. Morcom

Author(s):  
K.D. Muratov

The idea of adversariality in criminal proceedings, carried away by its simplicity and originality in the context of public legal relations, after a certain period of time had passed the Criminal Procedure Code of the Russian Federation, gradually began to be reasonably questioned. The study of procedural procedures, the recognition of objects and documents as material evidence, as well as the subjects of the collection and presentation of material evidence, allow a closer look at the legal relationship and powers of the parties in criminal proceedings in the field of their implementation both in pre-trial and in court proceedings. Investigative and judicial processes as historically established forms of criminal procedure should be adversarial. The author examines the importance of the adversarial nature of the parties in the formation of material evidence in criminal cases and their assessment by the parties when substantiating the conclusions in the case, shows their theoretical and legal significance, procedural and legal, preventive and prophylactic and informational and evidentiary value.


2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Muhammad Hafidh Firmansyah ◽  
Seok-Joo Koh ◽  
Wahyu Kurnia Dewanto ◽  
Trismayanti Dwi Puspitasari

The machine learning models based on Convolutional Neural Networks (CNNs) can be effectively used for detection and recognition of objects, such as Corona Virus Disease 19 (COVID-19). In particular, the MobileNet and Single Shot multi-box Detector (SSD) have recently been proposed as the machine learning model for object detection. However, there are still some challenges for deployment of such architectures on the embedded devices, due to the limited computational power. Another problem is that the accuracy of the associated machine learning model may be decreased, depending on the number of concerned parameters and layers. This paper proposes a light-weight MobileNet (LMN) architecture that can be used to improve the accuracy of the machine learning model, with a small number of layers and lower computation time, compared to the existing models. By experimentation, we show that the proposed LMN model can be effectively used for detection of COVID-19 virus. The proposed LMN can achieve the accuracy of 98% with the file size of 27.8 Mbits by replacing the standard CNN layers with separable convolutional layers.


Sign in / Sign up

Export Citation Format

Share Document