Non-segmented character positioning and identification method based on deep learning

Abstract

The invention discloses a non-segmented character positioning and identification method based on deep learning. The non-segmented character positioning and identification method comprises steps of constructing a deep convolution neural network, wherein the deep convolution neural network comprises a universal convolution network, a candidate positioning network and a classification identification network, constructing a target function in order to realize global end-to-end training of a whole network, adopting an artificially-calibrated training set and a progressive-combined training mode to perform training on the network, using a network obtained through training to extract possible areas of a plurality of characters in a test image and a classified identification result when applied to a test, and performing non-maximum suppression on a result obtained by the network and performing post-processing on score threshold determination to obtain a final detection result. The non-segmented character positioning and identification method is simple, does not need to perform character segmentation pre-processing, can be compatible with a plurality of character forms, has a strong capability of resisting background interference and can be used as a general character detection method.

Description

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

AI Technical Summary

Benefits of technology

This patented technology allows for efficient and flexible identification or recognition of images based on their content rather than requiring specific processing steps like pixel-by-pixel analysis. It also includes an algorithm called Deep Learning Network (DLN) that can accurately locate and recognize certain parts within each frame of video data quickly while reducing costs associated therewith. Overall, this new approach provides technical benefits over previous approaches such as separate model selection processes, neural networks, etc., resulting in improved efficiency and accuracy in identifying and understanding complex scenes.

Problems solved by technology

Technological Problem addressed in this patents relates to improving automatic identification systems for recognizing unique patterns found within various types of documents or media data. Current methods require manually selecting specific parts from these documents beforehand, but doing so may result in errors due to variations in light conditions during imagery collection process. There has been an effort towards developing techniques called Deep Belief Networks (DBN), where artificial neurons learn how well their trained models work over time without relying solely upon hand crafted featurities. These advancements aim at automating symbolic pattern recognition processes while also enabling them to recognize different forms of nonstandard symbols.

Images