Chinese Image Text Recognition on grayscale pixels

Bai, Jinfeng; Chen, Zhineng; Feng, Bailan; Xu, Bo

doi:10.1109/icassp.2014.6853823

Cited by 18 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…if j − i > methods where potential segmentation points must be determined precariously [26,27,29,48], our method obviates this step since the SCW is known, which is an inborn advantage of our system. Three sliding windows identical to those in the Section 3.4 are adopted again to slide from left to right across S at stride one, and each window region is fed into the CNN ensemble for recognition.…”

Section: Algorithm 2 Slrb Determinationmentioning

confidence: 99%

“…Table 7 End-to-end performance. Notice that three baselines take subtitle region detected by our system as input rather than raw video frames, as ABBYY [50] and Microsoft OCR [51] may generate many false detections on raw video frames and gCITR [27] can only perform text recognition.…”

Section: End-to-end Performancementioning

confidence: 99%

“…[51]. gCITR [27] is the previous state-of-the-art system for Simplified Chinese subtitle recognition, where 85.44% word accuracy is achieved on another dataset. Besides, the performance of a single CNN is also reported in order to manifest the efficacy of the CNN ensemble.…”

Section: Experiments On Slrb Detectionmentioning

confidence: 99%

“…Table 6 Word Accuracy of Traditional Chinese. * gCITR [27] is not designed for Traditional Chinese. Table 5 and Table 6 shows the performance of ABBYY [50] , gCITR [27], Microsoft OCR library [51], our single CNN and the CNN ensemble on the Simplified Chinese and Traditional Chinese text line recognition task.…”

Section: Experiments On Slrb Detectionmentioning

confidence: 99%

“…Similar to Section 2.1 where the importance of features is addressed, existing image text recognition methods are also classified into those based on hand-engineered features [14,18,[24][25][26][27] and those based on feature learning [3,4,6,13,17,[28][29][30][31][32][33][34] …”

Section: Image Text Recognitionmentioning

confidence: 99%

See 4 more Smart Citations

End-to-end subtitle detection and recognition for videos in East Asian languages via CNN ensemble

Shan

Qiu

et al. 2018

Signal Processing: Image Communication

View full text Add to dashboard Cite

In this paper, we propose an innovative end-to-end subtitle detection and recognition system for videos in East Asian languages. Our end-to-end system consists of multiple stages. Subtitles are firstly detected by a novel image operator based on the sequence information of consecutive video frames.Then, an ensemble of Convolutional Neural Networks (CNNs) trained on synthetic data is adopted for detecting and recognizing East Asian characters. Finally, a dynamic programming approach leveraging language models * Corresponding author tively, which is a significant outperformance of other existing methods. The near-perfect accuracy of our system dramatically narrows the gap between human cognitive ability and state-of-the-art algorithms used for such a task.

show abstract

Section: Algorithm 2 Slrb Determinationmentioning

confidence: 99%

Section: End-to-end Performancementioning

confidence: 99%

Section: Experiments On Slrb Detectionmentioning

confidence: 99%

Section: Experiments On Slrb Detectionmentioning

confidence: 99%

Section: Image Text Recognitionmentioning

confidence: 99%

See 3 more Smart Citations

End-to-end subtitle detection and recognition for videos in East Asian languages via CNN ensemble

Shan

Qiu

et al. 2018

Signal Processing: Image Communication

View full text Add to dashboard Cite

show abstract

Chinese Image Character Recognition Using DNN and Machine Simulated Training Samples

Bai

Chen

Feng

et al. 2014

Artificial Neural Networks and Machine Learning – ICANN 2014

Self Cite

View full text Add to dashboard Cite

Abstract. Inspired by the success of deep neural network (DNN) models in solving challenging visual problems, this paper studies the task of Chinese Image Character Recognition (ChnICR) by leveraging DNN model and huge machine simulated training samples. To generate the samples, clean machine born Chinese characters are extracted and are plus with common variations of image characters such as changes in size, font, boldness, shift and complex backgrounds, which in total produces over 28 million character images, covering the vast majority of occurrences of Chinese character in real life images. Based on these samples, a DNN training procedure is employed to learn the appropriate Chinese character recognizer, where the width and depth of DNN, and the volume of samples are empirically discussed. Parallel to this, a holistic Chinese image text recognition system is developed. Encouraging experimental results on text from 13 TV channels demonstrate the effectiveness of the learned recognizer, from which significant performance gains are observed compared to the baseline system.

show abstract