Multidirectional water meter reading area detection algorithm employing full convolution neural network

Abstract

The invention discloses a multidirectional water meter reading area detection algorithm employing a full convolution neural network, and the algorithm comprises the following steps: S1, obtaining training data which comprises a water meter image and reading region mark information; S2, training the full convolution neural network through the mark information for the extraction of multilayer cascading features, and obtaining a multichannel characteristic image; S3, carrying out the sliding window scanning of the characteristic image, taking a full connection neural network as a classifier and a regression device, and screening out a rectangular candidate window of a water meter reading region preliminarily; S4, extracting the features of a corresponding region in the characteristic image according to the region position information of the candidate window, taking a second full connection neural network as the classifier and the regression device, and obtaining the center, length, width and angle information of the water meter reading region; S5, finally obtaining a detection result of the multidirectional water meter reading area in a manner of a rotating rectangular frame. The algorithm is accurate, robust and practical.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a multi-directional water meter reading area detection algorithm of a fully convolutional neural network. Background technique [0002] In recent years, with the development of the mobile Internet and the popularization of digital products, the image data from different devices (smart phones, digital cameras, and even self-driving street view cars, drones and other cameras) has continued to grow explosively. Among these massive images, a considerable part of image data carries text information, and text information usually contains very beneficial semantic information. For example, these text information may be descriptions of buildings, shops, traffic signs, street signs, product names, etc. Therefore, these high-level semantic information can be widely used in machine reading, automatic translation, image retrieval, video retrieval, language translation, automatic driving, robot...

AI Technical Summary

Problems solved by technology

However, this method has poor adaptability to conditions such as illumination, deformation, and occlusion in various complex scenes, is easily disturbed, and has poor robustness.

Images