Cloud Chaser: real time deep learning computer vision on low computing power devices

Luo, Zhengyi; Small, Austin; Dugan, Liam; Lane, Stephen H.

doi:10.1117/12.2523087

Cited by 10 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the introduction of a convolutional neural network (CNN) LeNet-5 and its results on the MNIST dataset [34], the OCR task is usually solved with various ANNs that demonstrate stateof-the-art results on public datasets for object classification [35]- [39]. However, to be usable, ANNs employed in ''on the device'' software should satisfy the tight constraints on computational power and memory size [40]. In particular, it is essential for multi-language applications that require several classifiers.…”

Section: Anns In ''On the Device'' Ocr Solutionsmentioning

confidence: 99%

Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images

Chernyshova¹,

Sheshkus²,

Arlazarov

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we introduce an ''on the device'' text line recognition framework that is designed for mobile or embedded systems. We consider per-character segmentation as a language-independent problem and individual character recognition as a language-dependent one. Thus, the proposed solution is based on two separate artificial neural networks (ANN) and dynamic programming instead of employing image processing methods for the segmentation step or end-to-end ANN. To satisfy the tight constraints on memory size imposed by embedded systems and to avoid overfitting, we employ ANNs with a small number of trainable parameters. The primary purpose of our framework is the recognition of low-quality images of identity documents with complex backgrounds and a variety of languages and fonts. We demonstrate that our solution shows high recognition accuracy on natural datasets even being trained on purely synthetic data. We use MIDV-500 and Census 1961 Project datasets for text line recognition. The proposed method considerably surpasses the algorithmic method implemented in Tesseract 3.05, the LSTM method (Tesseract 4.00), and unpublished method used in the ABBYY FineReader 15 system. Also, our framework is faster than other compared solutions. We show the language-independence of our segmenter with the experiment with Cyrillic, Armenian, and Chinese text lines.

show abstract

Section: Anns In ''On the Device'' Ocr Solutionsmentioning

confidence: 99%

Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images

Chernyshova¹,

Sheshkus²,

Arlazarov

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The advances in deep learning have to be realised by performing continuous training on the real time data. Cloud Chaser [60] is a technique in which the computational load is borne by the cloud and the power of deep learning can be harnessed on low computing capacity devices. Big Data Analytics can be effectively performed by employing a hybrid "Machine Learning + Cloud Computing" approach [57].…”

Section: Deep Learningmentioning

confidence: 99%

Transformative effects of IoT, Blockchain and Artificial Intelligence on cloud computing: Evolution, vision, trends and open challenges

et al. 2019

View full text Add to dashboard Cite

Cloud computing plays a critical role in modern society and enables a range of applications from infrastructure to social media. Such system must cope with varying load and evolving usage reflecting societies' interaction and dependency on automated computing systems whilst satisfying Quality of Service (QoS) guarantees. Enabling these systems are a cohort of conceptual technologies, synthesised to meet demand of evolving computing applications. In order to understand current and future challenges of such system, there is a need to identify key technologies enabling future applications. In this study, we aim to explore how three emerging paradigms (Blockchain, IoT and Artificial Intelligence) will influence future cloud computing systems. Further, we identify several technologies driving these paradigms and invite international experts to discuss the current status and future directions of cloud computing. Finally, we proposed a conceptual model for cloud futurology to explore the influence of emerging paradigms and technologies on evolution of cloud computing.

show abstract

“…However, this kind of cross domain learning and knowledge transfer is still an important aspect of current research in this field [38,39]. Using prior research on cross domain learning, this study incorporates the deep learning concept of combining cloud resources with high-performance computing and storage and edge devices with strong personalized adaptability and good time limit control [40]. In this paper, a real-time high-speed train fault diagnosis method based on edge and cloud collaboration is proposed, which aims to utilize the advantages of both cloud and edge computing, and conduct real-time fault diagnosis through the coordination of computing resources and real-time requirements.…”

Section: Related Workmentioning

confidence: 99%

A Fault Diagnosis and Visualization Method for High-Speed Train Based on Edge and Cloud Collaboration

et al. 2021

View full text Add to dashboard Cite

Safety is the most important aspect of railway transportation. To ensure the safety of high-speed trains, various train components are equipped with sensor devices for real-time monitoring. Sensor monitoring data can be used for fast intelligent diagnosis and accurate positioning of train faults. However, existing train fault diagnosis technology based on cloud computing has disadvantages of long processing times and high consumption of computing resources, which conflict with the real-time response requirements of fault diagnosis. Aiming at the problems of train fault diagnosis in the cloud environment, this paper proposes a train fault diagnosis model based on edge and cloud collaboration. The model first utilizes a SAES-DNN (stacked auto-encoders deep neural network) fault recognition method, which can integrate automatic feature extraction and type recognition and complete fault classification over deep hidden features in high-dimensional data, so as to quickly locate faults. Next, to adapt to the characteristics of edge computing, the model applies a SAES-DNN model trained in the cloud and deployed in the edge via the transfer learning strategy and carries out real-time fault diagnosis on the vehicle sensor monitoring data. Using a motor fault as an example, when compared with a similar intelligent learning model, the proposed intelligent fault diagnosis model can greatly improve diagnosis accuracy and significantly reduce training time. Through the transfer learning approach, adaptability of the fault diagnosis algorithm for personalized applications and real-time performance of the fault diagnosis is enhanced. This paper also proposes a visual analysis method of train fault data based on knowledge graphs, which can effectively analyze fault causes and fault correlation.

show abstract

Cloud Chaser: real time deep learning computer vision on low computing power devices

Cited by 10 publications

References 8 publications

Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images

Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images

Transformative effects of IoT, Blockchain and Artificial Intelligence on cloud computing: Evolution, vision, trends and open challenges

A Fault Diagnosis and Visualization Method for High-Speed Train Based on Edge and Cloud Collaboration

Contact Info

Product

Resources

About