Trademark is a symbol that can be seen everywhere in life. In the case of effective use of trademark, people can quickly identify the organization, its image and reputation, so that the trademark owner can obtain resources for maintenance and development. However, there are unfair competitors in the market that would imitate similar trademarks to steal or damage the reputation and interests of the original trademark owners. Failure of preventing counterfeit trademarks from affecting the interests of others will make developers hard to develop novel technologies that contribute to the progress of the country and society due to insufficient or scarce resources. In the past research in this field,many studies have proposed protection methods for protecting trademark interests. These related studies have obtained excellent results in the search and analysis of trademarks. Nevertheless, some unfair competitors use the human cognition of visual psychology in the human vision system (HVS) to circumvent similar methods of trademark images to steal or damage the credit and interests of the original trademark owners. In order to deter unfair competitors or the abuse of such confusing trademarks, this article proposes a method for trademark background analysis. This article also proposes a method to generate a large amount of background trademark data. Then, we use that large amount of generated data for training neural networks that can analyze trademarks that are easily confused due to background. Eventually, we use the testing independent data for system verification. This experiment uses two common deep learning network architecture for testing. The experimental results show that the proposed system can achieve a true positive rate (TPR) over 98% in the face of this confusing trademark plagiarism method. And the comparison result is better than existing methods. This result confirms that the system proposed in this article can prevent infringement problems that used background.