A Deep Learning Approach for Robust, Multi-oriented, and Curved Text Detection

Ranjbarzadeh, Ramin; Ghoushchi, Saeid Jafarzadeh; Anari, Shokofeh; Safavi, Sadaf; Sarshar, Nima; Tirkolaee, Erfan Babaee; Bendechache, Malika

doi:10.1007/s12559-022-10072-w

Cited by 26 publications

(18 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the jump to three rooms worth of data results in a significant jump in accuracy, getting much closer to the acceptable levels. The main steps of this work have been revised due to these references (Ranjbarzadeh et al, 2021;Anari et al, 2022;Ranjbarzadeh et al, 2022;Saadi et al, 2022;Ranjbarzadeh et al, 2023a;Ranjbarzadeh et al, 2023b).…”

Section: Resultsmentioning

confidence: 99%

Deep learning health management diagnostics applied to the NIST smoke experiments

2023

View full text Add to dashboard Cite

Fire is one of the most important hazards that must be considered in advanced nuclear power plant safety assessments. The Nuclear Regulatory Commission (NRC) has developed a large collection of experimental data and associated analyses related to the study of fire safety. In fact, computational fire models are based on quantitative comparisons to those experimental data. During the modeling process, it is important to develop diagnostic health management systems to check the equipment status in fire processes. For example, a fire sensor does not directly provide accurate and complex information that nuclear power plants (NPPs) require. With the assistance of the machine learning method, NPP operators can directly get information on local, ignition, fire material of an NPP fire, instead of temperature, smoke obscuration, gas concentration, and alarm signals. In order to improve the predictive capabilities, this work demonstrates how the deep learning classification method can be used as a diagnostic tool in a specific set of fire experiments. Through a single input from a sensor, the deep learning tool can predict the location and type of fire. This tool also has the capability to provide automatic signals to potential passive fire safety systems. In this work, test data are taken from a specific set of the National Institute of Standards and Technology (NIST) fire experiments in a residential home and analyzed by using the machine learning classification models. The networks chosen for comparison and evaluation are the dense neural networks, convolutional neural networks, long short-term memory networks, and decision trees. The dense neural network and long short-term memory network produce similar levels of accuracy, but the convolutional neural network produces the highest accuracy.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep learning health management diagnostics applied to the NIST smoke experiments

2023

View full text Add to dashboard Cite

show abstract

“…However, DL pipelines became very prevalent due to numerous practical developments, including cloud computing, high-performance graphic cards, and well-organized data processing strategies (e.g., pooling methods, non-linear activation functions, or data augmentation). These developments allow a model to efficiently calculate numerous non-linear transformations of the respective input samples (the ability of end-to-end learning) [ 23 , 26 , 55 , 56 ].…”

Section: Methodsmentioning

confidence: 99%

Point-of-Interest Preference Model Using an Attention Mechanism in a Convolutional Neural Network

et al. 2023

View full text Add to dashboard Cite

In recent years, there has been a growing interest in developing next point-of-interest (POI) recommendation systems in both industry and academia. However, current POI recommendation strategies suffer from the lack of sufficient mixing of details of the features related to individual users and their corresponding contexts. To overcome this issue, we propose a deep learning model based on an attention mechanism in this study. The suggested technique employs an attention mechanism that focuses on the pattern’s friendship, which is responsible for concentrating on the relevant features related to individual users. To compute context-aware similarities among diverse users, our model employs six features of each user as inputs, including user ID, hour, month, day, minute, and second of visiting time, which explore the influences of both spatial and temporal features for the users. In addition, we incorporate geographical information into our attention mechanism by creating an eccentricity score. Specifically, we map the trajectory of each user to a shape, such as a circle, triangle, or rectangle, each of which has a different eccentricity value. This attention-based mechanism is evaluated on two widely used datasets, and experimental outcomes prove a noteworthy improvement of our model over the state-of-the-art strategies for POI recommendation.

show abstract

“…These models are designed to mimic the structure and function of the human brain, utilizing multiple layers of interconnected artificial neurons to process and extract meaningful representations from raw data. By automatically learning hierarchical features, deep learning models have achieved remarkable success in various domains, including computer vision, natural language processing, and speech recognition (Kasgari et al, 2023;Ranjbarzadeh, Bagherian Kasgari, et al, 2021;Ranjbarzadeh, Jafarzadeh Ghoushchi, et al, 2022;Ranjbarzadeh, Sadeghi, et al, 2023;Saadi et al, 2022;Tataei Sarshar et al, 2021).…”

Section: Suggested Attention-based Deep Learning Modelmentioning

confidence: 99%

“…With the exponential growth of data in today's digital world, traditional machine learning models often struggle to capture intricate patterns and dependencies. Deep learning models, on the other hand, excel at handling complex data and discovering hidden patterns, leading to more accurate predictions and decision-making Ranjbarzadeh, Tataei Sarshar, et al, 2022;Saadi et al, 2021;Safavi & Jalali, 2021).…”

Section: Suggested Attention-based Deep Learning Modelmentioning

confidence: 99%

“…Max pooling selects the maximum value within a predefined region, effectively reducing the spatial dimensions of the features while retaining the most important information. This pooling operation helps to capture the most salient features and discard irrelevant or redundant information (Ranjbarzadeh, Dorosti, et al, 2022;Ranjbarzadeh, Tataei Sarshar, et al, 2022).…”

Section: Suggested Attention-based Deep Learning Modelmentioning

confidence: 99%

See 1 more Smart Citation

Attention-based deep learning model to improving multi-criteria decision-making for customer loyalty

Bayat,

Honari

2023

Am J Soc Sci Hum

View full text Add to dashboard Cite

Understanding the factors that influence product loyalty is crucial for businesses to effectively attract and retain customers. This study suggests a novel approach to assess the importance and weight of criteria that lead to product loyalty by considering the Halo effect in customer decision-making. The suggested method utilizes an attention-based deep learning model to analyze customer feedback collected through the Net Promoter Score (NPS) scale, incorporating the insights of a large number of customers. The proposed method overcomes the limitations of traditional methods that rely on expert judgments or data mining, providing a more comprehensive and customer-centric perspective. By considering the Halo effect, which can lead to biased perceptions of product features, the method offers a more accurate assessment of criteria weights and their impact on product loyalty. A case study focusing on mobile phone selection and loyalty is conducted to explain the applicability and efficiency of the suggested method. The outcomes are compared with the NPS index and several common multi-criteria decision-making (MCDM) techniques. The findings highlight the superiority of the suggested method in capturing the complex relationships between criteria and product loyalty, surpassing the limitations of expert-based approaches and outperforming traditional MCDM methods. The suggested technique provides valuable insights for companies seeking to enhance customer loyalty and optimize product development strategies. However, it is important to acknowledge limitations related to the reliance on customer feedback and the contextual specificity of the results.

show abstract

A Deep Learning Approach for Robust, Multi-oriented, and Curved Text Detection

Cited by 26 publications

References 78 publications

Deep learning health management diagnostics applied to the NIST smoke experiments

Deep learning health management diagnostics applied to the NIST smoke experiments

Point-of-Interest Preference Model Using an Attention Mechanism in a Convolutional Neural Network

Attention-based deep learning model to improving multi-criteria decision-making for customer loyalty

Contact Info

Product

Resources

About