Text detection, recognition, and script identification in natural scene images: a Review

Naosekpam, Veronica; Sahu, Nilkanta

doi:10.1007/s13735-022-00243-8

Cited by 24 publications

(13 citation statements)

References 158 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the learning process, there will be a lot of uncertain information. These uncertainties may cause the machine to fail to accurately identify the target object [13][14]. Therefore, how to effectively, quickly and reliably use the signal characteristics obtained by various sensors to describe and track is one of the prerequisites for robot recognition.…”

Section: Intelligent Machine Learningmentioning

confidence: 99%

Automatic Text Recognition Based on Intelligent Machine Learning Technology

2022

View full text Add to dashboard Cite

With the development of computer technology, digital image processing, pattern recognition and machine vision have become an important research field. Text classification is a process of extracting text based on content analysis. In this paper, RGB is used as the feature vector for character segmentation, and the string is converted into simple Chinese characters (i.e. binary). SVM is used to establish the vector relationship matrix between characters to obtain the corresponding pixel value of each word, and then combined with the threshold comparison function to generate a single word set, so as to realize the recognition of attribute parameters such as the Chinese and English abstract representing human information and background in the image, so as to meet the requirements of semantic connection between different classified texts. The test results show that the recognition accuracy of the intelligent machine learning automatic character recognition system based on text classification technology is more than 90%, and it can accurately recognize characters.

show abstract

Section: Intelligent Machine Learningmentioning

confidence: 99%

Automatic Text Recognition Based on Intelligent Machine Learning Technology

2022

View full text Add to dashboard Cite

show abstract

“…With the development of deep learning, object detection, and semantic segmentation techniques, text detection algorithms are constantly updated. Existing text detection algorithms can be generally classified into two main categories [1]: regressionbased methods and segmentation-based methods. Regression-based text detection algorithms are generally improved over object detection algorithms to make them suitable for text detection tasks.…”

Section: Introductionmentioning

confidence: 99%

Calligraphy font text detection based on attention mechanism feature fusion and enhancement

Zeng,

Zhang

2024

Second International Conference on Informatics, Networking, and Computing (ICINC 2023)

View full text Add to dashboard Cite

A text detection algorithm based on attention-mechanism based feature fusion and enhancement for calligraphy fonts is proposed for the problem of diverse fonts, styles, forms, and complex structures in calligraphy works, and the network performance is improved by building an attention-mechanism based feature fusion module (AFFM) and an attentionmechanism based feature enhancement module (AFEM). First, according to the characteristics of calligraphic text, the AFFM module adds a feature pyramid FPN to combine global information with remote contextual information and improve the connection between each feature channel to improve the accuracy of text detection; second, the AFEM module improves the prediction accuracy of the model in predicting text pixels by enhancing the characterization ability of feature information after fusion of feature maps at different scales. The experimental results on the self-built text detection dataset of calligraphy works show that the precision, recall, and overall evaluation metrics F1 reach 94.29%, 94.07%, and 94.18%, respectively, proving the effectiveness of the method on the text detection task of calligraphy fonts. Meanwhile, on the public dataset ICDAR2015, its precision, recall, and overall evaluation metrics F1 reached 89.09%, 76.76%, and 82.47%, respectively, proving that the model has good generalization properties.

show abstract

“…Videos primarily feature two text types: scene text 2–6 and captions 7 . Billboards, trucks, t‐shirts, streets, and buildings commonly display scene text, whereas captions, comprising subtitles and overlay text, undergo manual video edits.…”

Section: Introductionmentioning

confidence: 99%

Video text rediscovery: Predicting and tracking text across complex scenes

Naosekpam,

Sahu

2024

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Dynamic texts in scene videos provide valuable insights and semantic cues crucial for video applications. However, the movement of this text presents unique challenges, such as blur, shifts, and blockages. While efficient in tracking text, state‐of‐the‐art systems often need help when text becomes obscured or complicated scenes. This study introduces a novel method for detecting and tracking video text, specifically designed to predict the location of obscured or occluded text in subsequent frames using a tracking‐by‐detection paradigm. Our approach begins with a primary detector to identify text within individual frames, thus enhancing tracking accuracy. Using the Kalman filter, Munkres algorithm, and deep visual features, we establish connections between text instances across frames. Our technique works on the concept that when text goes missing in a frame due to obstructions, we use its previous speed and location to predict its next position. Experiments conducted on the ICDAR2013 Video and ICDAR2015 Video datasets confirm our method's efficacy, matching or surpassing established methods in performance.

show abstract

Text detection, recognition, and script identification in natural scene images: a Review

Cited by 24 publications

References 158 publications

Automatic Text Recognition Based on Intelligent Machine Learning Technology

Automatic Text Recognition Based on Intelligent Machine Learning Technology

Calligraphy font text detection based on attention mechanism feature fusion and enhancement

Video text rediscovery: Predicting and tracking text across complex scenes

Contact Info

Product

Resources

About