Skip to main content

Validation of Computer Vision Models Applied to Harvests

This use case provides a validation service for fruit detection algorithms using agricultural images. It uses datasets with real annotations to compare the predictions generated by the models with ground truth. The objective is to offer companies in the sector a reliable tool to evaluate the accuracy of their algorithms without conflicts of interest.

Fig. 1. Commercial logo of the use case. (source: AgrospAI)

Introduction​

Objectives​

  • Provide a validation service that allows companies to evaluate the accuracy and reliability of their fruit detection algorithms using agricultural images.
  • Ensure neutral validation without conflicts of interest, being driven by the University of Lleida (UdL), a public entity acting as a trusted third party.
  • Contribute to the improvement of the quality of predictive models used in the agri-food sector, promoting the responsible and transparent use of artificial intelligence in agricultural environments.
  • Guarantee data sovereignty, ensuring that producers maintain full ownership and control over the information generated on their farms.

Problem Description​

Currently, many companies in the agri-food sector face the difficulty of objectively and reliably validating the detection and prediction algorithms they use for agricultural image analysis. The absence of standardized and accessible methods to check the accuracy of these tools generates uncertainty about the quality of the predictions made.

This lack hinders trust in the adoption of artificial intelligence and computer vision technologies, limiting the potential for innovation and improvement in production processes. Furthermore, the lack of independent validation services leads to a potential conflict of interest when evaluations are carried out by the developing companies themselves.

🔎 Therefore, it is necessary to have a neutral and rigorous system that allows for reliable evaluation of algorithm effectiveness, offering companies transparent and objective validation that promotes the trustworthy use of these technologies in the agricultural sector.

Proposed Solution​

Fig. 2. Visual scheme of the proposed solution in this use case. (source: AgrospAI)

The scheme above visually illustrates the functioning of the proposed system for validating fruit detection models using agricultural images.

In this system, different participants provide their artificial intelligence models, which are executed on a real dataset containing agricultural images annotated with ground truth.

These annotations serve as a reliable reference for evaluating model performance. The models generate automatic fruit predictions or detections that are compared with the actual annotations through an evaluation service. This service automatically activates a performance estimation module that calculates objective metrics.

With the obtained results, a complete evaluation report is generated and delivered to the consumer interested in validating their model. The entire process takes place within an infrastructure managed by a neutral access and computing provider, ensuring an independent, transparent evaluation without conflicts of interest, and also ensuring that the data used remains under the control of its original owners.

Harvest Validation Algorithm​

What the algorithm does?​

The validation algorithm runs a process that compares the predictions made by a computer vision model with the ground truth contained in a set of annotated agricultural images. To do this, it generates a confusion matrix from the detected hits, false positives, and false negatives, and calculates standard evaluation metrics.

Result and Benefits​

The final validation result is a comprehensive, downloadable report implemented in HTML, JavaScript, and Python. This report is designed to provide a clear and structured view of the evaluated model's performance. It includes an executive summary with the main results, a detailed description of the applied methodology, a visual and quantitative analysis of the confusion matrix, a section dedicated to average metrics, and a performance comparison between different models.

Fig. 3. Result obtained from the application of the validation algorithm. (fuente: AgrospAI)

Thanks to this report, companies can objectively identify the strengths and limitations of their algorithms, justify their technological decisions with quantitative evidence, and move toward more responsible and efficient adoption of AI-based tools in agricultural settings.