VIETNAM NATIONAL UNIVERSITY - HO CHI MINH CITY UNIVERSITY OF INFORMATION TECHNOLOGY FACULTY OF COMPUTER SCIENCE BACHELOR THESIS A Study on Handling Out-of-Vocab Problem in Scene Text Recognition Bachelor of Computer Science (Honors degree) HỨA THANH TÂN- 19520257 Supervised by DR. THANH DUC NGO HO CHI MINH CITY, 2023 VIETNAM NATIONAL UNIVERSITY - HO CHI MINH CITY UNIVERSITY OF INFORMATION TECHNOLOGY FACULTY OF COMPUTER SCIENCE BACHELOR THESIS A Study on Handling Out-of-Vocab Problem in Scene Text Recognition Bachelor of Computer Science (Honors degree) HỨA THANH TÂN- 19520257 Supervised by DR. THANH DUC NGO HO CHI MINH CITY, 2023 COMMITTEE The Thesis Defense Committee has been carefully established in accordance with the Decision. by the President of the Univer- sity of Information Technology.
This committee is comprised of eminent individ- uals who possess a great deal of expertise and knowledge in the specific area of study that is relevant to the thesis defense. To ensure that all aspects of the the- sis defense are properly addressed, the following personnel have been carefully chosen to comprise the committee: ¢ Chairman: ® Secretary: ¢ Member: ¢ Member: ACKNOWLEDGEMENT Iam immensely grateful to the invaluable assistance of Dr. Ngo Duc Thanh, Duc Khanh, Minh Phuong, and An Tran in the successful completion of my thesis. Their dedication and commitment to my project provided me with the support and guidance I needed to ensure the accuracy and quality of my work was up to par.
Ngo Duc Thanh has been an invaluable mentor to me throughout the course of my research journey. His guidance, support, and expertise have been invalu- able in teaching me the importance of critical thinking and providing valuable advice when needed. He has been a constant source of inspiration, providing me with the confidence to question and challenge my current understanding and push myself to reach my highest potential. Duc Khanh and Minh Phuong were my peers in this research journey, and I am thankful for their insightful suggestions and feedback which greatly improved the cohesiveness of my work.
Their contribution to data collection and analysis was invaluable, and without their help I would have struggled to complete my thesis. Iam especially thankful to An Tran for her help in proofreading and refining my thesis. Her expertise and careful attention to detail helped ensure that my work was of the highest standard, and I could not have achieved my goal without her help. Without the dedicated effort of these individuals, I would never have been able to complete my thesis, and I am profoundly thankful for their invaluable contri- bution.
I am grateful for the time and energy they devoted to helping me reach my goal. Contents IAbstractl 1 Overview 1 Introduction] gy.2 Introduction to Scene Text ecogmition|.1 Scene Text Recognition|l.2 Sub-problem in Scene Text Recognition [25]}.1 Cropped Scene Text Recognition).2 End-to-end Scene Text Recognition] .- [[3_ Introduce to Out-of-vocabulary problem|.1 Out-outvocabulary problem|.2 Challenges of OOV problem|.Ặ TQ eee 15 16 2_ Related Wor! 17 2.13 _ Multi-oriented Datasetl.2 Scene Text Recognition Methodsl.2 _Segmentation-based method|.2 Language-based methodsl.3 Long-short Term Memory (LSTM) based method}. 30 E3 Out-oF-vocabulary Problem|.1 Ensemble learning baselines approach|.2 Reducing impact of linguistic information over the visual featureapproach|.3 Automatically making decision to hold visual and linguistic approach}. eee 37 Evaluation on V 39 ¬ ee 39 3411 Dataset).1 _OOV-ST Challenge Datasetl.
Q Q Q Q Q Sc 41 B2 Experiment and Evaluation|.21 OOV-ST Challenge Datasltl.23_ Eval ation Resul 45 4 Conclusion! 49 References 51 List of Figures T. End-to-end System for Scene Text Recognition [20] See 6 1.4 Autonomous vehicles recognize "STOP" term to decide next action DS.5 Variants in font[6]].6 Variants in color[10]Ï.7 Variants in illumination.8 Variants in orientation and distortion [4]}.13 Slang words - that mean throwing something|.14 Typo words - diferent|.1 Synthetic images dataset 5] Se ee 18 2.2 Curved images dataset [2]|.3 Street view text dataset [24]]. 20 E4 Normal images dataset[16]].5 OOV-ST Challenge dataset (19 ¬ 21 [2.6 Four stages of STR frameworks Jð]].8 The combination of transformer and CTC makes the model robust in the presence of low resolution images.9_ Some failure cases of I2C2W [26||.10 Architecture of TextScanner [23]|.11 Robust prediction on Chinese script [23] mom. sss sss ees 25 2.12 Simple and Strong baseline - SAR[13j|.13 SAR compare to other solutions [13]|.14 By using 2D Attention mechanism, this architecture localize char- [|___acters without character-level annotations [13]].17 ABINet evaluation high accuracy on low-quality images [7]].19 SCATTER with different number of selective block decoders [14Ï|.20 Some failures of SCATTER [14||.21 Ensemble models architecture [HẢ| Se ee 33 2.22 OpenCCD architecture in simple version ft Se eee 35 [2.23 OpenCCD architecture with full components|.24 Comparision OpenCCD with other methods|.25 OpenCCD robust result on non-latinh characters|.26 The core architecture of VLAMD [12]|.
37 41 42 -3 {is added into word "prepare"].4 Result on various aspect of OOV Datasetl.5 Result our OpenCCD outputs on Vietnamese character with spe- cific 3 types of errOr|.6 Result our OpenCCD outputs on Vietnamese character with spe- cific 3 types of error]. eee 47 List of Tables 3.1 Approximately average accurary of current methods on some type of OOV words].2 Ranking accuracy of some baselines that not handle OOV problem} 43 3. Ranking accuracy of current OOV-handle methods}. eee 45 ABBREVIATIONS OOV Oout Of Vocabulary FWCONDHI STR Scene Text Recognition IV In Vocabulary CNN Convolution Neural Network RNN Recurrent Neural Network BiLSTM Bidirectional Long Short Term Memory CTC Connectionist Temporal Classification SOTA State Of The Art ABSTRACTION This thesis introduces the field of scene text recognition, exploring the out-of- vocabulary problem and outlining some of the most recent methods used to ad- dress it.
Scene text recognition is a process of recognizing and extracting text from an image, transforming it into a machine-readable format for further pro- cessing. The out-of-vocabulary problem is a challenge for recognizing text that is not included in a predefined vocabulary list, leading to the need for modern methods to address this issue. In this thesis: ¢ We discuss various approaches and techniques that have been used to tackle the out-of-vocabulary problem. These include those based on the use of contextual information, those that use the prediction of characters not seen in the training set, and those that leverage deep learning techniques to learn representations of out-of-vocabulary words.
e We present an evaluation of existing approaches, their effectiveness in tack- ling the out-of-vocabulary problem, and a new dataset for assessing out-of- vocabulary words which have no common characteristics and unstructured Additionally, we compare and analyze various state-of-the-art techniques to iden- tify which works best for this purpose, discussing the results in the thesis and ar- riving at a better understanding of the current approaches to the out-of-vocabulary problem. In order to guide future research, this thesis further suggests potential directions and strategies to further improve existing methods and address the out-of-vocabulary problem. These include exploring different ways of incorpo- rating contextual information into deep learning models and leveraging transfer learning to pre-train models on related tasks. In addition, further research should be conducted on the development of robust and efficient approaches for recog- nizing out-of-vocabulary words.1 Introduction Scene text recognition is a rapidly growing and increasingly important field of re- search, due to its many potential applications in areas such as image recognition, computer vision, and natural language processing.
In recent years, the develop- ment of deep learning techniques has enabled researchers to create models that can accurately recognize text from natural images. This has opened up a world of possibilities, with researchers now able to extend the scope of text recognition to a range of areas, including but not limited to document analysis, autonomous navigation, and even medical image processing. With the rapid advances in deep learning, computer vision, and natural language processing, the possibilities for scene text recognition have grown exponentially, making it an ever-more vital research field. In this thesis, we focus on the so-called "Out of vocabulary prob- lem," another facet of scene text recognition.
Finally, we study and evaluate a few solutions to this issue.2 Introduction to Scene Text Recognition 1.1 Scene Text Recognition Scene Text Recognition (STR) is a form of computer vision technology that is used to recognize text in natural scenes. It is a challenging task due to the variations in font, color, illumination, occlusion, orientation, size, and language that can be present within an image. In addition, the context of the image as a whole must be taken into account by STR algorithms in order to achieve a high degree of ac- curacy in text recognition. This is because the context of the image may provide additional clues that can help to identify the text.
For example, if the image con- tains a signpost, the context of the image can help to identify the language of the text on the sign. Therefore, in order to accurately recognize text from natural scenes, STR algorithms must be designed to consider all of these factors.2 Sub-problem in Scene Text Recognition [25] 1.1 Cropped Scene Text Recognition Cropped Text Recognition is the process of recognizing text from images which have been cropped around the text itself. This process is especially challenging due to the fact that the background of the image is usually cluttered and can con- tain other objects that may interfere with the recognition process. To address this issue, multiple techniques have been proposed such as incorporating contextual information into the recognition process, employing region-based convolutional neural networks (R-CNNs), and using multi-scale feature extraction.
® Input: a single image ¢ Output:: a word containing inside the input image 1.2 End-to-end Scene Text Recognition End-to-End Text Recognition is a more recent approach in which a single deep learning model is used to directly recognize text from an image. This approach has the advantage of being able to recognize text from more complex images which contain multiple lines of text and even curved text. To achieve this, many end-to-end text recognition models employ a combination of convolutional lay- ers for feature extraction, recurrent layers for sequence modeling, and attention mechanisms for sequence decoding. Overview ¢ Input: a single image ¢ Output:: a list of words and polygon area indicated the position of the word inside the input image.
End-to-End Spotting CAVE SPRING Recognition HIGH SCHOOL FIGURE 1.3: End-to-end System for Scene Text Recognition 1.3 Applications of STR Scene Text Recognition (STR) has a variety of applications that are revolutionizing the way we use technology. These include: ¢ Autonomous vehicles: Scene Text Recognition technology is playing a major role in making these vehicles smarter, more efficient, and far safer than ever before. By recognizing street signs and other relevant information, Scene Text Recognition can help make navigation smoother, easier, and far more secure for self-driving cars. As this technology continues to evolve, the po- tential for self-driving vehicles is growing exponentially and is likely to rev- olutionize the way we get around.
¢ Mobile phone applications: Scene Text Recognition can be used to power applications such as scanning bar codes, allowing users to quickly and eas- ily access information in an instant. Overview STOP Image Text detection Text recognition FIGURE 1.4: Autonomous vehicles recognize "STOP" term to decide next action 1.4 Challenges of STR One of the main challenges of Scene Text Recognition is recognizing text in natu- ral scenes, which requires the algorithm to take into account a variety of factors, such as variations in font, color, illumination, occlusion, orientation, size, and language: e Variations in font can make text difficult to recognize, as different fonts can have unique shapes and features that make them hard to distinguish. This can be especially true for text written in a stylized font, which may contain unique characters that are not found in more traditional typefaces. The size and spacing of the font can also make it difficult to differentiate from other fonts.
Furthermore, the font style can also make a difference, as some fonts are designed to be more ornate or decorative, while others are designed to be more plain and simple.