# A convenient method for the accurate identification of Citri Reticulatae Pericarpium using image and multi-stream

## TL;DR

This paper introduces a convenient and accurate method for identifying the origin and aging of Citri Reticulatae Pericarpium using images and multi-stream processing.

## Contribution

The novel approach combines multi-stream feature extraction and meta-learning for improved accuracy and adaptability across different imaging devices.

## Key findings

- The method achieves 95.5% accuracy on iPhone-captured images.
- It shows a 34% relative accuracy improvement over direct transfer methods for images from different devices.
- The meta-learning module enhances adaptability to varying imaging conditions.

## Abstract

Citri Reticulatae Pericarpium (CRP), the dried peel of citrus fruits, holds notable dietary and medicinal value. Its quality and price largely depend on origin and aging. Lower-grade CRP is often adulterated to imitate premium products, making accurate authentication of region and vintage essential for quality assurance and fair market valuation. Existing methods for vintage classification are limited due to complex equipment and high operational costs, restricting their scalability in practical applications. To address these issues, a convenient method for the accurate identification of Citri Reticulatae Pericarpium using image and multi-stream is proposed. The method comprises three main stages. Firstly, an object detection network with bounding box refinement localizes exocarp and albedo regions from whole CRP images. Secondly, a three-stream feature extractor processes the whole images along with exocarp and albedo patches to capture complementary visual details. A channel-level feature interaction module further enhances robustness through cross-region feature integration. Thirdly, a meta-learning module enables rapid adaptation to images captured under varying conditions by different consumer-grade devices. Experimental results demonstrate that the proposed method achieves an accuracy of 95.5% on iPhone-captured images. In addition, for images captured by different devices, the proposed method achieves a relative accuracy improvement of more than 34% over the direct transfer method, mainly owing to the meta-learning adaptation to different devices.