Model decoding method and device, text recognition method and device, medium and equipment
A text recognition and model technology, applied in the field of image processing, can solve the problems of insufficient image clarity, attention drift, missed recognition, etc., to avoid attention drift, avoid repeated positioning, and improve the user experience.
Pending Publication Date: 2022-07-01
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In related technologies, a corresponding text recognition model can be obtained by training based on a neural network, but attention drift may occur during the decoding process based on the text recognition model due to insufficient clarity of the image or repeated characters in the text in the image. As a result, it is impossible to accurately locate the position of the current character, resulting in deviation of positioning, and the problem of repeated or missed recognition of characters.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0033] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for the purpose of A more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not intended to limit the protection scope of the present disclosure.
[0034] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit performing the illustrated steps. The scope of the present discl...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a model decoding method and device, a text recognition method and device, a medium and equipment. The method comprises the steps of obtaining a coding vector corresponding to a to-be-recognized text image; a mask vector corresponding to decoding of an attention layer in a decoder at the current moment is determined, the mask vector is used for representing position information positioned by the attention layer, the text recognition model comprises an encoder and the decoder, the encoder is used for encoding a received to-be-recognized text image, and the decoder is used for decoding the to-be-recognized text image. Obtaining the coding vector; updating the attention distribution information of the attention layer at the current moment according to the mask vector to obtain a target attention weight corresponding to the current moment; and decoding according to the target attention weight and the coding vector to obtain an identification result of the text identification model. Therefore, attention drifting can be avoided to a certain extent, and missing recognition of characters of the text image and repeated positioning of the same position are avoided.
Description
technical field [0001] The present disclosure relates to the field of image processing, and in particular, to a model decoding method, text recognition method, apparatus, medium and device. Background technique [0002] Optical Character Recognition (OCR) refers to the process of analyzing and recognizing image files to obtain text information in the image files. OCR is usually divided into two processes: text detection and text recognition. In the text recognition process, it is necessary to identify the text area sub-images segmented by the text detection module to obtain text information. [0003] In the related art, a corresponding text recognition model can be obtained by training based on a neural network. However, due to insufficient clarity of the image or repeated characters in the text in the image, attention drift may occur during the decoding process based on the text recognition model. As a result, the position of the current character cannot be accurately loca...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T9/00G06V30/40G06N3/04
CPCG06T9/001G06T9/002G06T2207/20084G06N3/047G06N3/044
Inventor 蔡悦黄灿
Owner BEIJING BYTEDANCE NETWORK TECH CO LTD