A Character Position-Aware Compression Framework for Screen Text Image

被引:0
|
作者
Zhu, Chen [1 ]
Lu, Guo [1 ]
Chen, Huanbang [2 ]
Feng, Donghui [1 ]
Wang, Shen [1 ]
Zhao, Yan [1 ]
Xie, Rong [1 ]
Song, Li [1 ,3 ]
机构
[1] Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai 200240, Peoples R China
[2] Huawei Technol Co Ltd, Shenzhen 518129, Peoples R China
[3] Shanghai Jiao Tong Univ, AI Inst, MoE Key Lab Artificial Intelligence, Shanghai 200240, Peoples R China
关键词
Screen content coding; text detection; motion vector prediction and coding; in-loop filter; SCENE TEXT; SEGMENTATION; PREDICTION;
D O I
10.1109/TCSVT.2024.3379675
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Text patterns typically exhibit distinct boundaries and sparse color histograms. However, in current hybrid codec frameworks, the positions of coding units are often misaligned with the text patterns, resulting in prediction and color mapping tools consuming a large number of bits to indicate these patterns. Nowadays, some text detection and recognition methods have been proposed to accurately locate and analyze the text regions in screen images. Combined with these techniques, we propose a character position-aware compression framework for screen text image. On the encoder side, a low-complexity detection method is adopted to locate the text characters. Then it copies the detected characters to the position aligned with the coding unit (CU) grid to form a text layer. This text-layer representation can further increase the efficiency of existing screen content coding tools such as Intra Block Copy (IBC). Moreover, we design several compression tools based on this representation. We extend the two Motion Vector (MV) prediction modes: Adaptive Motion Vector Prediction (AMVP) and Merge. We modify the MV encoding syntax according to the layout characteristics of the text layer. We present a Gradient-guided In-loop Filter (GIF) to sharpen the text lines using a convolutional network. Experiments conducted on VVC reference software VTM all_intra configuration show that the proposed framework can achieve an average bitrate savings of 4.6% and 3.6% under the w/GIF and w/o GIF versions, with a corresponding increase in CPU encoding complexity of 72% and 10%.
引用
收藏
页码:8821 / 8835
页数:15
相关论文
empty
未找到相关数据