TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask

نویسندگان

چکیده

Arbitrary-shaped scene text detection is a challenging task due to the variety of changes in font, size, color, and orientation. Most existing regression based methods resort regress masks or contour points regions model instances. However, regressing complete requires high training complexity, are not sufficient capture details highly curved texts. To tackle above limitations, we propose novel light-weight anchor-free framework called TextDCT, which adopts discrete cosine transform (DCT) encode as compact vectors. Further, considering imbalanced number samples among pyramid layers, only employ single-level head for top-down prediction. multi-scale texts head, introduce positive sampling strategy by treating shrunk region samples, design feature awareness module (FAM) spatial-awareness scale-awareness fusing rich contextual information focusing on more significant features. Moreover, segmented non-maximum suppression (S-NMS) method that can filter low-quality mask regressions. Extensive experiments conducted four datasets, demonstrate our TextDCT obtains competitive performance both accuracy efficiency. Specifically, achieves F-measure 85.1 at 17.2 frames per second (FPS) 84.9 15.1 FPS CTW1500 Total-Text respectively.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

JPEG Encoder using Discrete Cosine Transform & Inverse Discrete Cosine Transform

In the past decade, the advancement in data communications was significant during explosive growth of the Internet, which led to the demand for using multimedia in portable devices. Video and Audio data streams require a huge amount of bandwidth to be transferred in an uncompressed form. The objective of this paper is to minimize the number of bits required to represent an image and also the ac...

متن کامل

Computation of Hilbert Transform via Discrete Cosine Transform

Hilbert transform (HT) is an important tool in constructing analytic signals for various purposes, such as envelope and instantaneous frequency analysis, amplitude modulation, shift invariant wavelet analysis and Hilbert-Huang decomposition. In this work we introduce a method for computation of HT based on the discrete cosine transform (DCT). We show that the Hilbert transformed signal can be o...

متن کامل

On discrete cosine transform

The discrete cosine transform (DCT), introduced by Ahmed, Natarajan and Rao, has been used in many applications of digital signal processing, data compression and information hiding. There are four types of the discrete cosine transform. In simulating the discrete cosine transform, we propose a generalized discrete cosine transform with three parameters, and prove its orthogonality for some new...

متن کامل

Discrete cosine transform

The discrete cosine transform (DCT) is a Fourier-related transform similar to the discrete Fourier transform (DFT), but using only real numbers. It is equivalent to a DFT of roughly twice the length, operating on real data with even symmetry (since the Fourier transform of a real and even function is real and even), where in some variants the input and/or output data are shifted by half a sampl...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Transactions on Multimedia

سال: 2022

ISSN: ['1520-9210', '1941-0077']

DOI: https://doi.org/10.1109/tmm.2022.3186431