Character recognition method and system based on attention mechanism
A text recognition, attention technology, applied in character recognition, character and pattern recognition, computer parts and other directions, can solve the problem of forming noise area, limited attention area, attention drift and so on
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0069] Example 1
[0070] like figure 1 As shown, a text recognition method based on attention mechanism includes the following steps:
[0071] S1: Build a text recognition model for recognizing text in an image; the text recognition model consists of the following modules:
[0072] Convolutional neural network for extracting feature maps of input images;
[0073] An attention mechanism module, including a sequence encoder, a forward sequence decoder and a reverse sequence decoder, for encoding and decoding the feature map, and outputting the feature vector of the predicted character;
[0074] a character decoding layer, for compiling the feature vector of the predicted character into a text recognition result, and compiling the feature map into a feature map character probability vector;
[0075] S2: construct a training sample set, the training sample set includes a training image and an image annotation corresponding to the training image, wherein the image annotation is...
Example Embodiment
[0083] Embodiment 2
[0084] like figure 1 As shown, a text recognition method based on attention mechanism includes the following steps:
[0085] S1: Build a text recognition model for recognizing text in an image; the text recognition model is composed of a convolutional neural network, an attention mechanism module, and a character decoding layer, wherein the attention mechanism module includes a sequence encoder, a positive Forward Sequence Decoder and Reverse Sequence Decoder.
[0086] In the step S1, the convolutional neural network includes a multi-layer convolution filter bank and a pooling sub-module, the convolution filter bank adopts a residual structure, and the character decoding layer is fully connected by a multi-layer neural network. The multi-layer convolution filter bank extracts image features, the pooling sub-module changes the feature map resolution, and the output of the convolutional neural network is a feature map with a certain number of channels.
...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap