|Table of Contents|

Research on Layout Inspection Technology of ModernTibetan Prints Based on Deep Learning(PDF)

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2021年01期
Page:
44-48
Research Field:
计算机科学与技术
Publishing date:

Info

Title:
Research on Layout Inspection Technology of ModernTibetan Prints Based on Deep Learning
Author(s):
Wu Yanru1; 2; Zhu Jie1; 2; Guan Meijing1; 2
(1.School of Information Science and Technology,Tibet University,Lhasa 850000,China)(2.National and Local Joint Center for Tibetan Information Technology,Lhasa 850000,China)
Keywords:
deep learning; modern Tibetan prints; Faster R-CNN; layout detection
PACS:
TP391
DOI:
10.3969/j.issn.1672-1292.2021.01.007
Abstract:
Aimed at the uneven distribution of text lines in the layout of modern Tibetan books and the large differences in modern Tibetan fonts,a layout text line detection algorithm based on Faster R-CNN is proposed. By training on collated and labeled data set,we use the ResNet-50 network to extract the feature information of the Tibetan modern book layout. In order to effectively improve the generalization ability of the model,transfer learning is performed in the network model under the COCO dataset. The experimental results show that this method can realize text line positioning on the layout of modern Tibetan printed materials,with a detection accuracy rate of 83% and the recall rate of 95%,which significantly improves the accuracy of layout detection.

References:

[1] 索南草. 浅谈藏文典籍文化的传承与保护[J]. 时代教育,2014(13):116-117.
[2]张西群. 面向藏文历史文献的版面分割方法研究[D]. 北京:北京工业大学,2018.
[3]EPSHTEIN B,OFEK E,WEXLER Y. Detecting text in natural scenes with stroke width transform[C]//IEEE Conference on Computer Vision and Pattern Recognition. San Francisco,USA:IEEE,2010.
[4]PAN Y F,HOU X W,LIU C L. A hybrid approach to detect and localize texts in natural scene images[J]. IEEE Trans Image Process,2011,20(3):800-813.
[5]ZHU J,CHEN X J,YUILLE A L,et al. DeePM:a deep part-based model for object detection and semantic part localization[C]//ICLR 2016. San Juan,Puerto Rico,2016.
[6]张学鹏. 基于深度学习的图像语义分割方法研究与实现[D]. 成都:电子科技大学,2018.
[7]CHEN C Y,LIU M Y,ONCEL T,et al. R-CNN for small object detection[C]//ACCV2016. Taipei,China,2016.
[8]赵丹凤. 基于通用对象估计的目标检测与模糊车牌识别算法研究[D]. 南京:南京邮电大学,2016.
[9]GIRSHICK R,LANDOLA F,DARRELL T,et al. Deformable part models are convolutional neural networks[C]//IEEE Conference on Computer Vision and Pattern Recognition. Boston,USA:IEEE Computer Society,2015.
[10]GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision(ICCV). Santiago,Chile:IEEE,2015.
[11]张勋,陈亮,朱雪婷,等. 基于区域卷积神经网络Faster R-CNN的手势识别方法[J]. 东华大学学报(自然科学版),2019,45(4):559-563.
[12]李响,苏娟,杨龙. 基于改进YOLOv3的合成孔径雷达图像中建筑物检测算法[J]. 兵工学报,2020,41(7):1347-1359.
[13]蒋强卫. 基于卷积神经网络的双目视觉物体识别与定位研究[D]. 哈尔滨:哈尔滨工程大学,2018.
[14]曾健. 基于深度学习的汽车门板焊点识别算法研究及应用[D]. 广州:华南理工大学,2019.
[15]张新,郭福亮,梁英杰,等. 基于R-CNN算法的海上船只的检测与识别[J]. 计算机应用研究,2020,37(增刊1):314-315,319.
[16]孙朝云,裴莉莉,李伟,等. 基于改进Faster R-CNN的路面灌装封裂缝检测方法[J]. 华南理工大学学报(自然科学版),2020,48(2):84-93.
[17]贺颖. 变换逼近理论指导下的卷积神经网络及其应用[D]. 唐山:华北理工大学,2019.
[18]SHI J H,CHANG Y J,XU C H,et al. Real-time leak detection using an infrared camera and Faster R-CNN technique[J]. Computer & Chemical Engineering,2020,135:106780.
[19]孙海铭,时兆峰,李晗,等. 基于Faster R-CNN的精密零部件的识别方法[J]. 飞控与探测,2020,3(2):26-36.
[20]王莹,丁鹏. 基于深度学习的交通信号灯检测及分类方法[J]. 汽车实用技术,2018(17):89-91.
[21]周华平,殷凯,桂海霞,等. 基于改进的Faster R-CNN目标人物检测[J]. 无线电通信技术,2020,46(6):712-716.
[22]朱旭,马淏,姬江涛,等. 基于Faster R-CNN的蓝莓冠层果实检测识别分析[J]. 南方农业学报,2020,51(6):1493-1501.

Memo

Memo:
-
Last Update: 2021-03-15