Retail terminal goods shelf image intelligent analyzing system based on cloud processing method

Abstract

The invention relates to a retail terminal goods shelf image intelligent analyzing system which comprises a sample collecting unit, a retail terminal target image collecting system, and a cloud intelligent image analyzing unit, wherein the sample collecting unit is used for collecting sample image information, the retail terminal target image collecting system is used for collecting image information of goods shelves at a retail terminal, and the cloud intelligent image analyzing unit comprises a feature extraction part, an image segmentation part, a pattern recognition part, and a data analyzing unit. The feature extraction part analyzes target images, obtains color feature data of sample images, and establishes a sample database by the utilization of the data. The feature extraction part further analyzes images collected through a target image collecting system and extracts color feature data of the target images at the retail terminal. The image segmentation part segments the target images to further recognize an outer frame of single goods. The pattern recognizing part recognizes goods of the target images. The data analyzing unit collects and/or analyzes information obtained through other parts in a cloud intelligent image analyzing system. Through the system, the retail terminal goods shelf image intelligent analyzing system based on the cloud processing method is capable of providing display and arrangement information of products quickly, reliably and in a low-cost mode.

Description

technical field [0001] The invention belongs to the field of image pattern recognition, performs pattern recognition and analysis on collected images through cloud processing, and is applied to the management of retail terminals. Background technique [0002] Today, with the increasing competition in retail terminals, consumer goods manufacturers are paying more and more attention to the sales of products at various retail terminals. It is well known that the display of products on retail terminal shelves directly affects consumers' attention to products and brands. Affecting product sales is a crucial factor affecting sales. However, the collection of existing retail terminal shelf display information is usually done manually through a large amount of manpower at the retail terminal, which results in poor accuracy and timeliness of information, especially with the rise of labor costs and the increasing competition. Intense, management requires more precise, more evidence-b...

AI Technical Summary

Problems solved by technology

[0004] However, this method has great limitations: firstly, it must use specially processed shelves with scales, which are not universal, and cannot be used in practical applications, and the practical applicability is not optimistic; secondly, the algorithm is layered according to the scales. Monomer segmentation and direct identification of monomers, and no auxiliary means are mentioned. In practical applications, there are various complex situations in the placement of goods on shelves, including out-of-stock, overlapping, covering, etc. If direct identification is not performed, it is likely to cause Unpredictable results such as Siamese (missing segmentation), half-body (over-segmentation), and inability to recognize, resulting in a very low recognition rate

[0006] However, this solution is only used to detect the free space of the shelf, and cannot identify other product display information on the shelf, and only identifying the free space is only conducive to improving the utilization rate of the shelf, but does not help much to increase sales; secondly, the system’s Commodity information is read from the database according to the location, so there is no sample library for pattern recognition. In practice, the product information is constantly changing. When the sample library does not store the corresponding information, this solution is difficult to implement, and it is impossible to use this solution. Identify the location of the product; third, the deployment space of the system is limited, and it is usually deployed in the store, which cannot cover a large area

Images