Addressing the defect characteristics of multicolor interference and the high complexity of spray-printed variable color 2D codes, along with the challenges of insufficient accuracy and low efficiency in current detection methods used by printing enterprises, this paper proposes a defect classification model by integrating ResNet34 and Transformer structure (ResNet34-TE). Initially, a color 2D code defect dataset is constructed, followed by the introduction of a contour shape detection method to identify the target region and mitigate background interference. ResNet34 serves as the backbone network for feature extraction. In a significant modification, the average pooling layer is omitted, and a Transformer encoder layer is employed to capture the global information of the extracted features, emphasizing the region of interest. Experimental results demonstrate that the accuracy of ResNet34-TE reaches 96.80%, with the average detection time for a single sheet reduced to 15.59 ms. This represents a 5.3 percentage points improvement in accuracy and a 5.8% enhancement in detection speed compared to the baseline model, outperforming classical models. Additionally, on the public defect detection dataset NEU-DET, the proposed model achieves an accuracy of 98.86%, surpassing mainstream defect classification algorithms. Consequently, the proposed model exhibits superior classification effectiveness in defect recognition.