A product detection method, device, equipment and storage medium

By combining coarse-grained and fine-grained detection using an image classification model, the high annotation cost problem in existing technologies is solved, and fine-grained detection is achieved by effectively reducing annotation costs and meeting product testing requirements.

CN116958113BActive Publication Date: 2026-06-12上海明胜品智人工智能科技有限公司
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
上海明胜品智人工智能科技有限公司
Filing Date
2023-07-31
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

Existing product testing methods require extensive image annotation when performing fine-grained testing, resulting in excessively high annotation costs and failing to meet actual needs.

Method used

Coarse-grained classification prediction is performed using an image classification model to obtain intermediate feature maps. Fine-grained classification prediction results are then calculated using the standard images corresponding to each detection result category. The final detection result is determined by combining the coarse-grained and fine-grained results, thus avoiding the introduction of an additional image segmentation model.

Benefits of technology

It effectively reduced the cost of image annotation, enabled fine-grained detection, and met the actual needs of product testing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116958113B_ABST
    Figure CN116958113B_ABST
Patent Text Reader

Abstract

The application provides a product detection method, device and equipment and a storage medium. The product detection method comprises: inputting a product image of a target product into a pre-trained image classification model, performing classification prediction on a detection result category to which the product image belongs by the image classification model, and outputting a coarse-grained classification prediction result for the target product; obtaining an intermediate feature map generated by the image classification model in an intermediate stage of classifying and predicting the product image; calculating a fine-grained classification prediction result of the target product based on the intermediate feature map and a standard image corresponding to each detection result category; and jointly determining a final product detection result of the target product based on the coarse-grained classification prediction result and the fine-grained classification prediction result. In this way, the application can realize fine-grained detection of the target product without introducing an image segmentation model, thereby effectively reducing the labeling cost of image labeling in the early model training stage.
Need to check novelty before this filing date? Find Prior Art