TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask.
Yuchen SuZhiwen ShaoYong ZhouFanrong MengHancheng ZhuBing LiuRui YaoPublished in: IEEE Trans. Multim. (2023)
Keyphrases
- discrete cosine transform
- text detection
- arbitrary shaped
- image compression
- dct coefficients
- transform domain
- object recognition
- text information
- video analysis
- arbitrary shape
- urban scenes
- filter bank
- connected components
- packing problem
- image segmentation
- complex background
- wavelet transform
- feature selection
- bounding box
- spatial domain
- outdoor scenes
- data structure
- image sequences
- three dimensional