Siamese Neural Networks with Chi-square Distance for Trademark Image Similarity Detection

Abstract

Purpose: The objective of this study is to address the limitations of existing trademark image similarity analysis methods by integrating a Chi-square distance metric within a Siamese neural network framework. Traditional approaches using Euclidean distance often fail to accurately capture the complex visual features of trademarks, leading to suboptimal performance in distinguishing similar trademarks. This research aims to improve the precision and robustness of trademark comparison by leveraging the Chi-square distance, which is more sensitive to image variations.

Methods: The approach involves modifying a Siamese neural network traditionally employing Euclidean distance with the use the Chi-square distance metric instead. This alteration allows the network to better capture and analyze critical visual features such as color and texture. The modified network is trained and tested on a comprehensive dataset of trademark images, enabling the network to learn and distinguish between similar and dissimilar trademarks based on subtle visual cues.

Result: The findings from this study show a significant increase in accuracy, with the modified network achieving an accuracy rate of 98%. This marks a notable improvement over baseline models that utilize Euclidean distance, demonstrating the effectiveness of the Chi-square distance metric in enhancing the model's ability to discriminate between trademarks.

Novelty: The novelty of this research lies in its application of the Chi-square distance in a deep learning framework specifically for trademark image similarity detection, presenting a novel approach that yields higher precision in image-based comparisons.