Occluded text restoration and recognition

Chang, Lanlan; Sun, Jun; Suwa, Misako; Takebe, Hiroaki; He, Yuan; Naoi, Satoshi

doi:10.1145/1815330.1815350

Cited by 5 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar research has been done on occluded English characters ( Fukushima, 2001( Fukushima, , 2013Chang, Sun, Suwa, Takebe, He, & Naoi, 2010 ). Fukushima (2001 ) asserted that an occluded English character is easier to recognize if the occluding cover or object is visible.…”

mentioning

confidence: 69%

“…The goal of this study was to create a recognition scheme for partially occluded Chinese characters, based on 18 commonly used Chinese char-acters, to assist graphic designers to determine which occlusion position is associated with the shortest recognition time and the highest recognition accuracy for better design. Similar research has been done on occluded English characters ( Fukushima, 2001( Fukushima, , 2013Chang, Sun, Suwa, Takebe, He, & Naoi, 2010 ). Fukushima (2001 ) asserted that an occluded English character is easier to recognize if the occluding cover or object is visible.…”

mentioning

confidence: 69%

“…Fukushima (2001 ) asserted that an occluded English character is easier to recognize if the occluding cover or object is visible. Chang, et al . (2010 ) explored ways to recover occluded strokes when watermark text overlaps the main text on a page in Chinese or English.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Effect of Structural Composition and Position of Occlusion on the Legibility of Occluded Chinese Characters

Tsao

Liao

2015

Percept Mot Skills

View full text Add to dashboard Cite

The study examined the effect of structural composition, position of occlusion, and education background on response time and accuracy rate of adult participants in recognition of occluded Chinese characters used in graphic design. Based on 18 Chinese characters selected from the top 4,000 most commonly used characters, a recognition experiment was conducted. Results indicated that, for the characters with two different composition structures, the right position was the best position of occlusion because the recognition of the radical or feature of a character would be least affected, leading to a shorter response time and more accurate reading comprehension. Educational background did not have a significant influence on response time and recognition accuracy.

show abstract

mentioning

confidence: 69%

mentioning

confidence: 69%

See 1 more Smart Citation

Effect of Structural Composition and Position of Occlusion on the Legibility of Occluded Chinese Characters

Tsao

Liao

2015

Percept Mot Skills

View full text Add to dashboard Cite

show abstract

“…Bertozzi et al [6] suggest an in-painting method for text images that is based on a slightly modified Cahn-Hilliard equation, which models the phase separation in binary fluids. Chang et al [10] address the problem of visible watermark characters, occluded by foreground content. Their algorithm is based on an exemplarbased in-painting which reconstructs the missing areas by referring to similar patches from undamaged areas.…”

Section: Introductionmentioning

confidence: 99%

Occluded Character Restoration Using Active Contour with Shape Priors

Cohen

Kedem

Dinstein

et al. 2012

2012 International Conference on Frontiers in Handwriting Recognition

View full text Add to dashboard Cite

Broken or partially visible characters is common phenomenon in historical documents. It stems from various factors, such as overlaid text or degradation. Restoring such characters is necessary for document analysis applications. This paper presents a new approach for restoring underlaying Hebrew broken characters that were partially occluded by Arabic text in a palimpsest. We apply text recognition on the fragments of the Hebrew letters and select the k candidate letters that match best the fragments of the Hebrew letters. We then complete the broken Hebrew characters using active contour with the k candidates as shape priors. We use a modified geodesic active contour, which we tailored to occluded text restoration. It is initialized on the fragments of the Hebrew text, then it undergoes an expansion phase and a contraction phase via the occluding Arabic text to form the restored Hebrew character. We measure the distance between the completed character and its corresponding priors and choose the shape with the minimal distance as the reconstructed character. Experimental results are presented. On average 68% of the characters were correctly reconstructed.

show abstract

Automated hand-marked semantic text recognition from photographs

Suh,

Lee,

Gil

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Automated text recognition techniques have made significant advancements; however, certain tasks still present challenges. This study is motivated by the need to automatically recognize hand-marked text on construction defect tags among millions of photographs. To address this challenge, we investigated three methods for automating hand-marked semantic text recognition (HMSTR)—a modified scene text recognition-based (STR) approach, a two-step HMSTR approach, and a lumped approach. The STR approach involves locating marked text using an object detection model and recognizing it using a competition-winning STR model. Similarly, the two-step HMSTR approach first localizes the marked text and then recognizes the semantic text using an image classification model. By contrast, the lumped approach performs both localization and identification of marked semantic text in a single step using object detection. Among these approaches, the two-step HMSTR approach achieved the highest F1 score (0.92) for recognizing circled text, followed by the STR approach (0.87) and the lumped approach (0.78). To validate the generalizability of the two-step HMSTR approach, subsequent experiments were conducted using check-marked text, resulting in an F1 score of 0.88. Although the proposed methods have been tested specifically with tags, they can be extended to recognize marked text in reports or books.

show abstract

Occluded text restoration and recognition

Cited by 5 publications

References 10 publications

Effect of Structural Composition and Position of Occlusion on the Legibility of Occluded Chinese Characters

Effect of Structural Composition and Position of Occlusion on the Legibility of Occluded Chinese Characters

Occluded Character Restoration Using Active Contour with Shape Priors

Automated hand-marked semantic text recognition from photographs

Contact Info

Product

Resources

About