Text Extraction for Historical Tibetan Document Images Based on Connected Component Analysis and Corner Point Detection

Zhang, Xiqun; Duan, Lijuan; Ma, Li; Wu, Jian

doi:10.1007/978-981-10-7302-1_45

Cited by 9 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For touching character segmentation, we present a new touching Tibetan character string database from historical Tibetan document images [8]. This paper is the extension of our previous works [6]- [8]. We propose a unified segmentation and recognition framework integrating layout segmentation, text-line segmentation, touching character string segmentation and recognition.…”

Section: Introductionmentioning

confidence: 95%

“…Text-line segmentation methods based on baseline detection [4] and contour curve tracking [5] are used to segment the text regions into text-lines. In previous works, we propose the rule-based layout segmentation method [6] and text-line segmentation method based on baseline estimation [7]. For touching character segmentation, we present a new touching Tibetan character string database from historical Tibetan document images [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation and Recognition for Historical Tibetan Document Images

Long

Duan

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

As a shining pearl in traditional Tibetan culture, historical Tibetan documents have received extensive attention from historians, linguists and Buddhist scholars. These documents are converted into digital form using Tibetan document segmentation and recognition methods. The document digitization is of great significance for the research, protection and inheritance of Tibetan history. This paper proposes an overall segmentation and recognition framework for historical Tibetan document images. Firstly, the historical Tibetan document image is preprocessed to correct imbalanced illumination, tilt and noises, and is further transformed into the binarized image. Secondly, we propose a layout segmentation method based on block projection to segment Tibetan document images into texts, lines and frames. Thirdly, in order to solve the problems of touching strokes between text-lines and curvilinear text-lines, we present a text-line segmentation method based on graph model for historical Tibetan text-line segmentation. Lastly, we present a touching segmentation method to segment touching Tibetan character string, and then recognize Tibetan characters. Experimental results show our proposed methods on layout segmentation, text-line segmentation and touching character string segmentation, achieve the satisfactory performance. The proposed methods can also be applied to other fonts in Tibetan font family.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 99%

Segmentation and Recognition for Historical Tibetan Document Images

Long

Duan

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Beragam teknik pengolahan citra bisa digunakan, salah satunya adalah connected component analysis (CCA) untuk ekstraksi jumlah piksel dari objek citra dan density-based spatial clustering of applications with noise (DBSCAN) untuk klasterisasi ukuran objek dari hasil ekstraksi jumlah piksel. Metode CCA telah diterapkan untuk mengekstraks teks dari sebuah citra dokumen [9], klasterisasi citra laju alarm palsu konstan dari radar Doppler [10], klasifikasi telur ayam dan telur burung puyuh [11], dan aplikasi sistem tertanam [12], [13]. Metode DBSCAN telah diterapkan untuk segmentasi citra [14], ekstraksi objek citra radar FM-CW [15], klasterisasi radiasi matahari [16], pengelompokkan rumah kos mahasiswa [17], klasterisasi resiko tsunami [18], dan klasterisasi negara-negara dunia [19].…”

Section: Pendahuluanunclassified

“…Sebagai contoh, posisi badan udang yang membungkuk serta posisi kaki yang menjulur keluar menyebabkan luas objek udang menjadi bertambah sehingga ukuran udang yang terdeteksi oleh sistem juga menjadi lebih besar. Namun, rata-rata hasil akurasi sistem, yaitu 76,4 %, telah menunjukkan bahwa metode CCA dan DBSCAN dapat memberikan hasil yang baik dalam melakukan klasterisasi udang berdasarkan ukuran menggunakan teknik pengolahan citra digital seperti halnya [9]- [19].…”

Section: Hasil Dan Pembahasanunclassified

Shrimps clusterization by size using digital image processing with CCA and DBSCAN

Priadana

Murdiyanto

2020

Jurnal Teknologi dan Sistem Komputer

View full text Add to dashboard Cite

The quality of farmed shrimps has several criteria, one of which is shrimp size. The shrimp selection was carried out by the contractor at the harvest time by grouping the shrimp based on their size. This study aims to apply digital image processing for shrimp clustering based on size using the connected component analysis (CCA) and density-based spatial clustering of applications with noise (DBSCAN) methods. Shrimp group images were taken with a digital camera at a light intensity of 1200-3200 lux. The clustering results were compared with clustering from direct observation by two experts, each of which obtained an accuracy of 79.81 % and 72.99 % so that the average accuracy of the method was 76.4 %.

show abstract

“…Accuracy level achieved in ancient script is lower by 5% than modern script, as it contains noise and is not available in digitized and tagged format. Therefore, an extensive study has to be performed on ancient script [43]. .…”

Section: Quantative Researchmentioning

confidence: 99%

An Insight of Script Text Extraction Performance using Machine Learning Techniques

Chadha*,

Mittal,

Singhal

2019

IJITEE

View full text Add to dashboard Cite

With the evolution of huge amount of ancient and modern text available in digital format, it is ascertain to mine for researchers, government, tourist and travelers visiting all over the world. However, it is very challenging and costly. Further, it takes a lot of effort and time for script text mining. Therefore, the study investigates various techniques for script text mining viz supervised and unsupervised techniques. Firstly, the study presents a survey for various kinds of techniques adopted by the users for extraction of text from image. It also delivers information about gaps involved in the various approaches. Furthermore, it incorporate the quantitative comparisons based among the study of various approaches and techniques for text extraction as well as script level comparison. The result inferred on the basis of the script comparison indicates that, the accuracy level of ancient script was found to be 5% lesser than modern script. Again, furthermore comparison has been done on standalone and hybrid machine (Combination of CNN and KNN) / deep learning techniques. The accuracy has been found to be lower(4%) in case of standalone techniques.

show abstract

Text Extraction for Historical Tibetan Document Images Based on Connected Component Analysis and Corner Point Detection

Cited by 9 publications

References 11 publications

Segmentation and Recognition for Historical Tibetan Document Images

Segmentation and Recognition for Historical Tibetan Document Images

Shrimps clusterization by size using digital image processing with CCA and DBSCAN

An Insight of Script Text Extraction Performance using Machine Learning Techniques

Contact Info

Product

Resources

About