Comparison of deep CNN and ResNet for Handwritten Devanagari Character Recognition

Patnaik, Suprava; Kumari, Saloni; Mahapatra, Shreya Das

doi:10.1109/icce50343.2020.9290637

Cited by 7 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It sometimes applied in researches for comparisons. For instance, it was compared with the deep CNN method in Devenagari character recognition [3], and it was contrasted with GoogleNet in the field of malware detection [4].…”

Section: Related Workmentioning

confidence: 99%

Network architecture exploration for Chinese character recognition with densenet

Dai

2023

TNS

View full text Add to dashboard Cite

Chinese character recognition can be widely used in many fields. Though Resnet and Densenet are both used in this area already, using these two networks and making a comparison on training performances between them is a ground that has not been explored. In this paper, these two methods are built and compared. Firstly, a dataset of Chinese character including 5,772 images with 28*28 size will be introduced. Next, Resnet and Densenet model pre-trained on the dataset is selected. Then fine-tuning is done to improve the accuracy of networks. After 50 epochs of training, the final result shows that Densenet is more stable compared with Resnet but less efficient with more epoches to perform well.

show abstract

Section: Related Workmentioning

confidence: 99%

Network architecture exploration for Chinese character recognition with densenet

Dai

2023

TNS

View full text Add to dashboard Cite

show abstract

“…It uses web scraping techniques to gather data from Amazon's product pages, and includes features for tracking price changes over time and setting price alerts. Keepa also provides users with access to historical pricing data, which can be useful for understanding pricing trends over time [12] .…”

Section: B) Keepamentioning

confidence: 99%

Real-time object detection with image recognition and web scraping

Pratap

2019

Pharma Innovation

View full text Add to dashboard Cite

The problem of price discrepancies between physical stores and online retailers has been a growing concern for consumers and businesses alike. In this paper, we propose a real-time object detection system that utilizes image recognition and web scraping to identify and compare prices of physical items with prices of ecommerce sites. The motivation for this project is to provide consumers with a more efficient way to identify price discrepancies and take advantage of potential cost savings. In the literature review section, we examine existing research and methods for price comparison, including computer vision and machine learning techniques. We analyze the strengths and weaknesses of existing methods and highlight how the proposed approach differs. Our methodology section provides a detailed description of the tools and techniques used, including OpenCV, web scraping, and OCR. We also provide an overview of the steps involved in the process, including image processing, text recognition, and data analysis. The results section presents an analysis of the data collected, including a comparison of prices between physical stores and ecommerce sites. We discuss any patterns or trends that emerged from the data, including differences in pricing between different types of products or websites. Our system was able to successfully identify and compare prices in real-time, providing users with accurate and up-to-date information about price discrepancies. Overall, our proposed real-time object detection system shows promise in addressing the problem of price discrepancies between physical stores and online retailers. By utilizing image recognition and web scraping, we were able to provide consumers with a more efficient way to identify potential cost savings. Future research can focus on improving the accuracy of the system and expanding its scope to include additional features such as user reviews and product availability.

show abstract