This study aims to enhance the recognition performance of children’s furniture pattern recognition by improving a multiscale image enhancement algorithm using genetic algorithms, addressing the limitations of current recognition methods. The study integrates genetic algorithms with a multi-scale image enhancement approach to process edge details and restores pattern damage factors. The performance of the improved algorithm is evaluated using accuracy, recall, precision, and mean absolute error as key metrics, and compared with other algorithms. The improved algorithm achieved an average accuracy of 0.986, significantly outperforming other algorithms. Its mean absolute error was 2.635, lower than the comparison methods. The proposed algorithm also demonstrated superior recognition accuracy across different categories of children’s furniture patterns, confirming its effectiveness in pattern classification. This study introduces a novel combination of genetic algorithms and multi-scale image enhancement for children’s furniture pattern recognition, offering a substantial improvement in recognition accuracy. The algorithm’s high performance in handling diverse patterns provides a significant advancement in the field of image recognition.