相关实验视频
Updated: Jul 26, 2026

13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.1K
深度转移学习骨干架构技术的比较,用于从非结构化文档中检测不同字体风格的印刷文本
Supriya Mahadevkar1, Shruti Patil2, Ketan Kotecha2
1Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, India.
PeerJ. Computer science
|April 30, 2024
概括
这项研究比较了用于打印文本识别的深度学习骨干架构. 在光学字符识别任务中,Xception模型获得了最高的准确性 (98.90%),优于其他模型.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 深度学习对象检测在银行和医疗保健等行业中至关重要.
- 从非结构化文档中检测和识别文本是关键的研究领域.
- 在文献中,用于打印文本识别的转移学习骨干架构的代表性不足.
研究的目的:
- 评估和比较各种基于转移学习的骨干架构,用于打印文本识别.
- 为光学字符识别 (OCR) 任务确定最有效的骨干架构.
- 分析预处理技术对文本识别精度的影响.
主要方法:
- 进行ResNet50,ResNet50V2,ResNet152V2,Inception,Xception和VGG19的骨干架构的比较.
- 应用的预处理技术:数据大小调整,规范化和消除噪音.
- 使用标准的OCR Kaggle数据集,将其分为80%的培训和20%的测试集.
- 在高性能架构上执行过度参数调整.
主要成果:
- Xception获得了最高的准确性 (98.90%) 和最低的损失 (0.19),超过了ResNet,Inception,VGG19和MobileNet.
- ResNet50V2 (96.92%准确度) 的性能高于ResNet152V2 (96.34%) 的性能.
- 该研究确定了Xception作为这个特定的OCR数据集和任务的优越架构.
结论:
- 使用骨干架构的转移学习显著提高了印刷文本的识别.
- 与其他评估模型相比,Xception架构在OCR任务中表现出卓越的性能.
- 对转移学习架构的进一步研究可以改善非结构化文档处理.
相关概念视频
Classification of Bones
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Differential Staining Technique
Differential staining is an essential microbiological technique that exploits variations in cell wall structures to classify and identify microorganisms. It facilitates the distinction of bacteria, aiding in diagnostic and research applications. Two of the most widely used differential staining methods are Gram staining and acid-fast staining, both of which rely on the chemical and structural differences in bacterial cell walls.Gram Staining TechniqueGram staining differentiates bacteria by...

