Automatic identification algorithm index test method, storage medium and electronic terminal

Abstract

The invention provides an automatic identification algorithm index test method, a storage medium and an electronic terminal. The method comprises the steps of collecting a test sequence set of algorithm indexes; marking the test sequence set, establishing a table structure according to the marked test sequence set, obtaining index test parameters required for executing a test by a measured algorithm, inputting the test sequence set into the measured algorithm, executing the test and obtaining an algorithm result; comparing the algorithm result with a table structure to obtain an algorithm index test result; according to the invention, the algorithm can be tested; an index comparison result is rapidly and accurately output; test period can be shortened, the method is advantaged in that requirements of rapid algorithm optimization and algorithm index improvement are satisfied, situations of limited algorithm application scenes and the like caused by insufficient consideration of influence factors during acquisition of the test case set are avoided, test efficiency is improved, and result errors caused by large data volume of the identified object and the identification attribute in the test set in the manual proofreading process are avoided.

Description

technical field [0001] The invention relates to the field of electronics, in particular to a method for automatic identification algorithm index testing, a storage medium and an electronic terminal. Background technique [0002] Computer algorithms are researched and applied in many fields. Among them, computer algorithm testing has also become a key link before the application of various computer algorithms. Algorithm testing in video algorithm processing, especially the testing methods for identifying attribute indicators, are generally used by testers. Input the test sequence set into the algorithm, and then manually proofread through the recognition results output by the algorithm and the corresponding snapshots. In the actual algorithm application, the test results will be affected by factors such as image quality, light, shooting angle of the recognized object, space and time complexity in the test sequence set. In this case, algorithm metrics testing may require mult...

AI Technical Summary

Problems solved by technology

It may be difficult for testers to quickly give correct and credible test results due to problems such as high space / time complexity and many attributes of the identified objects in the test case set

This situation cannot meet the needs of enterprises to quickly optimize algorithms and improve algorithm indicators

Images