Writer Identification: The Effect of Image Resizing on CNN Performance

Semma, Abdelillah; Lazrak, Said; Hannad, Yaâcoub; Boukhani, M.; Kettani, Youssfi El

doi:10.5194/isprs-archives-xlvi-4-w5-2021-501-2021

Cited by 5 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Selecting an appropriate image size for specific application scenarios and resource limitations and adjusting the data preprocessing workflow and model structure accordingly can more effectively balance size and performance [50,51]. The majority of deep convolutional neural networks, particularly those based on the ResNet model, are generally designed to handle deep learning tasks involving images with widths and heights ranging from tens to hundreds of pixels [52].…”

Section: Discussionmentioning

confidence: 99%

Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks

Zhang,

Yin,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

This study aims to establish a deep learning-based classification framework to efficiently and rapidly distinguish between coniferous and broadleaf forests across the Loess Plateau. By integrating the deep residual neural network (ResNet) architecture with transfer learning techniques and multispectral data from unmanned aerial vehicles (UAVs) and Landsat remote sensing data, the effectiveness of the framework was validated through well-designed experiments. The study began by selecting optimal spectral band combinations, using the random forest algorithm. Pre-trained models were then constructed, and model performance was optimized with different training strategies, considering factors such as image size, sample quantity, and model depth. The results indicated substantial improvements in the model’s classification accuracy and efficiency for reasonable image dimensions and sample sizes, especially for an image size of 3 × 3 pixels and 2000 samples. In addition, the application of transfer learning and model fine-tuning strategies greatly enhanced the adaptability and universality of the model in different classification scenarios. The fine-tuned model achieved remarkable performance improvements in forest-type classification tasks, increasing classification accuracy from 85% to 93% in Zhengning, from 89% to 96% in Yongshou, and from 86% to 94% in Baishui, as well as exceeding 90% in all counties. These results not only confirm the effectiveness of the proposed framework, but also emphasize the roles of image size, sample quantity, and model depth in improving the generalization ability and classification accuracy of the model. In conclusion, this research has developed a technological framework for effective forest landscape recognition, using a combination of multispectral data from UAVs and Landsat satellites. This combination proved to be more effective in identifying forest types than was using Landsat data alone, demonstrating the enhanced capability and accuracy gained by integrating UAV technology. This research provides valuable scientific guidance and tools for policymakers and practitioners in forest management and sustainable development.

show abstract

Section: Discussionmentioning

confidence: 99%

Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks

Zhang,

Yin,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Most previous journals claimed that resizing could affect the performance of the CNN model [38,39]. It was also explained that the most effective resizing is a size close to the original image size [38]. So, there is no correlation.…”

Section: ( ( ) )mentioning

confidence: 99%

Improving Waste Classification Using Convolutional Neural Networks: An Application of Machine Learning for Effective Environmental Management

Sunardi,

Yudhana,

Fahmi

2023

RIA

View full text Add to dashboard Cite

Waste management, particularly waste sorting, constitutes a critical global challenge. The integration of advanced technology, specifically machine learning, offers potential solutions to this pressing issue. In this study, a convolutional neural network (CNN) model was employed to devise an efficient waste classification system. The model achieved notable results, attaining an accuracy rate of 98.92% and a loss percentage of only 4.03% in overall performance on the test set, utilizing the Kaggle dataset. To further improve the CNN model's performance, advanced preprocessing techniques were implemented alongside a stream lined CNN model, yielding substantial effectiveness. This investigation demonstrates that the application of machine learning techniques can result in highly accurate and efficient waste classification, presenting promising solutions for waste management challenges. By accurately identifying and sorting waste materials, this technology has the potential to significantly reduce the volume of waste directed to landfills, safeguard the environment, and conserve valuable resources.

show abstract

Offline Writer Identification Based on Diagonal Gradient Angle of Small Fragments

Semma,

Lazrak,

Boukhani

et al. 2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Writer Identification: The Effect of Image Resizing on CNN Performance

Cited by 5 publications

References 0 publications

Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks

Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks

Improving Waste Classification Using Convolutional Neural Networks: An Application of Machine Learning for Effective Environmental Management

Offline Writer Identification Based on Diagonal Gradient Angle of Small Fragments

Contact Info

Product

Resources

About