Script Identification from Camera-Captured Multi-script Scene Text Components

Author(s):  
Madhuram Jajoo ◽  
Neelotpal Chakraborty ◽  
Ayatullah Faruk Mollah ◽  
Subhadip Basu ◽  
Ram Sarkar
Author(s):  
Changxu Cheng ◽  
Qiuhui Huang ◽  
Xiang Bai ◽  
Bin Feng ◽  
Wenyu Liu

2021 ◽  
Vol 421 ◽  
pp. 222-233
Author(s):  
Mengkai Ma ◽  
Qiu-Feng Wang ◽  
Shan Huang ◽  
Shen Huang ◽  
Yannis Goulermas ◽  
...  

2017 ◽  
Vol 67 ◽  
pp. 85-96 ◽  
Author(s):  
Lluis Gomez ◽  
Anguelos Nicolaou ◽  
Dimosthenis Karatzas

Panggung ◽  
2012 ◽  
Vol 22 (4) ◽  
Author(s):  
Tedi Permadi

ABSTRACTThis paper presents the results of the identification of rolled manuscripts made of daluang using diplomatic method. This method aims at getting the authenticity of the script based on the information that accompanies the text with the internal evidence contained in the manuscript. In terms of script identification techniques, diplomatic method utilizes direct observation techniques, assisted by other descriptions of contemporary manuscript as an evidence and support of the relevant literature. The use of diplomatic method in identifying rolled manuscripts produces the characteristics of the material, the literacy/language used in the text, and the editorial lapses contained in the text, but the identity of the author or the copyist and the time of the writing or copying manuscripts could not be found.Keywords: Manuscript identification, daluang, diplomatic method ABSTRAKTulisan ini menyajikan hasil identifikasi naskah gulungan berbahan daluang dengan menggunakan metode diplomatik. Metode diplomatik bertujuan untuk mendapatkan keaslian naskah berdasarkan informasi yang ada di dalam teks dengan bukti internal yang terkandung dalam naskah tersebut. Dalam hal teknik identifikasi naskah, metode diplomatik memanfaatkan teknik observasi langsung, dibantu dengan deskripsi dari naskah kontemporer lain sebagai bukti dan pendukung literatur yang relevan. Penggunaan metode diplomatik dalam mengidentifikasi naskah gulungan menghasilkan karakteristik material, huruf/bahasa yang digunakan dalam teks, dan penyimpangan editorial yang terkandung dalam teks, tetapi tidak bisa menemukan identitas penulis atau penyalin dan waktu penulisan atau penyalinan naskah.Kata kunci: Identifikasi naskah, daluang, metode diplomatik


2020 ◽  
Vol 167 ◽  
pp. 496-505
Author(s):  
Mridul Ghosh ◽  
Himadri Mukherjee ◽  
Sk. Md. Obaidullah ◽  
K.C. Santosh ◽  
Nibaran Das ◽  
...  

2021 ◽  
Vol 40 (1) ◽  
pp. 551-563
Author(s):  
Liqiong Lu ◽  
Dong Wu ◽  
Ziwei Tang ◽  
Yaohua Yi ◽  
Faliang Huang

This paper focuses on script identification in natural scene images. Traditional CNNs (Convolution Neural Networks) cannot solve this problem perfectly for two reasons: one is the arbitrary aspect ratios of scene images which bring much difficulty to traditional CNNs with a fixed size image as the input. And the other is that some scripts with minor differences are easily confused because they share a subset of characters with the same shapes. We propose a novel approach combing Score CNN, Attention CNN and patches. Attention CNN is utilized to determine whether a patch is a discriminative patch and calculate the contribution weight of the discriminative patch to script identification of the whole image. Score CNN uses a discriminative patch as input and predict the score of each script type. Firstly patches with the same size are extracted from the scene images. Secondly these patches are used as inputs to Score CNN and Attention CNN to train two patch-level classifiers. Finally, the results of multiple discriminative patches extracted from the same image via the above two classifiers are fused to obtain the script type of this image. Using patches with the same size as inputs to CNN can avoid the problems caused by arbitrary aspect ratios of scene images. The trained classifiers can mine discriminative patches to accurately identify some confusing scripts. The experimental results show the good performance of our approach on four public datasets.


Sign in / Sign up

Export Citation Format

Share Document