Multi-Scale Commodity Targets Detection Algorithm Based On Convolutional Neural Network

With the rapid development of E-Commerce,online shopping has become an indispensable part of people's daily life.However,with the increasing number of online merchandise types and the massive increase of merchandise images,the text-based product search system is difficult to satisfy the user's needs in terms of accuracy because of the limitation of text labeling.The retrieval method based on image feature uses the features of the image itself to express the image content,which makes up for the shortcomings of text retrieval and improves the accuracy of product classification and retrieval.However,in real life,the product image has many attributes and the background is complex.At the same time,it is easily affected by factors such as occlusion and illumination.Using traditional image feature extraction methods cannot eliminate the interference of these factors.Therefore,how to accurately describe the product and use it to increase product detection accuracy is a research hotspot in the field of product search.In recent years,the application and development of convolutional neural networks in the field of commodity retrieval has attracted the attention of many scholars,and has made great progress,but there are still some problems.Therefore,this paper proposes a multi-scale commodity image target detection algorithm based on convolutional neural network for these problems.The main research contents are as follows:1.Because the background of the product image is very complex,it will interfere with the detection and recognition of the product.Therefore,accurate extraction of the target area is an important prerequisite for product detection and recognition.Firstly,this paper uses the full convolutional network to extract the human body area,reducing the impact of complex background on clothing segmentation.Then the multi-target detection frame is used to extract the pattern area on the clothing area and clothing on the segmented human body area,which lays a good foundation for subsequent feature extraction and product classification and recognition.2.Based on the segmentation of product images,in order to improve the learning ability of multi-attribute features of products,the multi-task learning method is introduced into the network structure.In addition,because offline merchandise images are greatly affected by light and other factors,the triplet structure in metric learning is introduced.Through the online and offline clothing pair learning,the recognition accuracy of online clothing goods under the line is improved.3.To improve the accuracy of multi-scale product image detection and recognition,this article simultaneously detects and recognizes apparel product areas and clothing pattern areas,and uses the residual network to describe product features from multiple scales in order to be able to Accurately identify and classify the target products and effectively solve problems such as incomplete product areas due to size.In this paper,the existing problems in the detection of existing goods targets are improved from three aspects: image preprocessing,target area extraction and feature recognition.Finally,through experiments comparing with other algorithms from different angles,compared with mainstream algorithms can effectively improve the accuracy rate,verifying the superiority of the algorithm in commodity target detection.