Dense small commodity rapid detection recognition method based on target detection

Abstract

Provided is a dense small commodity rapid detection recognition method based on target detection. The method includes: processing an acquired commodity picture through a python or matlab programming language; establishing a convolutional neural network model including a convolution layer, a pooling layer and a total connection layer, wherein the model comprises convolution and RoIpooling; performing multi-task combined training on classification of the convolutional neural network model and a region proposal network model and bounding box regression through a training sample, performing learning update on a convolution kernel parameter in the convolutional neural network model through reverse propagation, and determining a hyper-parameter of the convolutional neural network model through averification set until a loss function reaches a target set value; and testing the recognition precision of the trained convolutional neural network model through the test set. According to the method, high-efficiency and accurate statistics of the number and the distribution of the commodities can be realized, the work efficiency of commodity suppliers and shopping mall management personnel canbe greatly improved, the manpower cost is reduced, and the commercial value is high.

Description

technical field [0001] The invention relates to a rapid detection and identification method for dense small commodities. In particular, it relates to a fast detection and recognition method for dense small commodities based on target detection. Background technique [0002] With the widespread application of computer vision principles, the research on target detection through computer image processing technology has attracted the attention of scholars at home and abroad. Target detection can be divided into two key sub-tasks: target classification and target localization, which can accurately determine the category of each target object in an image containing one or more target objects, and give the corresponding boundary frame. [0003] The traditional target detection algorithm has the following disadvantages: 1) Select candidate frames by sliding window method, the number is redundant, and the calculation is complicated; 2) The features of the region are extracted throu...

AI Technical Summary

Problems solved by technology

Therefore, the detection and recognition effect of densely distributed small commodities under different geometric deformations is poor. The geometric structure of the built convolutional network is also fixed, so it does not have the ability to model geometric deformation

Images