Computer Vision Intelligence Test Modeling and Generation: A Case Study on Smart OCR

TL;DR

This paper introduces a comprehensive testing framework for AI-based image text extraction systems, specifically OCR, including a 3D classification model, coverage criteria, and evaluation metrics, validated through a mobile OCR case study.

Contribution

It presents a novel AI software testing model with a 3D classification approach and evaluation metrics, applied to OCR to improve quality assessment methods.

Findings

The framework effectively evaluates AI OCR quality.

The 3D classification model aids systematic testing.

Evaluation metrics provide comprehensive quality insights.

Abstract

AI-based systems possess distinctive characteristics and introduce challenges in quality evaluation at the same time. Consequently, ensuring and validating AI software quality is of critical importance. In this paper, we present an effective AI software functional testing model to address this challenge. Specifically, we first present a comprehensive literature review of previous work, covering key facets of AI software testing processes. We then introduce a 3D classification model to systematically evaluate the image-based text extraction AI function, as well as test coverage criteria and complexity. To evaluate the performance of our proposed AI software quality test, we propose four evaluation metrics to cover different aspects. Finally, based on the proposed framework and defined metrics, a mobile Optical Character Recognition (OCR) case study is presented to demonstrate the framework's effectiveness and capability in assessing AI function quality.