Trademark Image Similarity Detection Using Convolutional Neural Network

Abstract

A trademark is any recognizable sign that identifies products/services and distinguishes them from others. Many regional and international intellectual property offices are dedicated to dealing with trademark registration processes. The registration process involves examining the trademark to ensure there is no confusion or interference similarity to any other prior registered trademark. Due to the increasing number of registered trademarks annually, the current manual examining approach is becoming insufficient and more susceptible to human error. As such, there is potential for machine learning applications and deep learning, in particular, to enhance the examination process by providing an automated image detection system to be used by the examiners to facilitate and improve the accuracy of the examination process. Therefore, this paper proposed a trademark similarity detection system using deep-learning techniques to extract image features automatically in order to retrieve a trademark based on shape similarity. Two pretrained convolutional neural networks (VGGNet and ResNet) were individually used to extract image features. Then, their performance was compared. Subsequently, the extracted features were used to calculate the similarity between a new trademark and each of those registered using the Euclidean distance. Thereafter, the system retrieved the most similar trademark to the query according to the smallest distances. As a result, the system achieved an average rank of 67,067.788, a normalized average rank of 0.0725, and a mean average precision of 0.774 on the Middle East Technical University dataset, which displays a promising application in detecting trademark similarity.

Conflicting Marks Archive Dataset: A Dataset of Conflicting Marks from the Brazilian Intellectual Property Office

“…Such solutions will be able to avoid cases of litigation, which is a formal process of resolving legal disputes through the judicial system [10]. Automating the process of identifying conflicting marks through computer-based tools presents a promising solution [11]. Such tools can make the work of intellectual property officers more efficient [12], while simultaneously reducing costs in the trademark examination process.…”

“…In the literature, there are different datasets originally developed for the logo detection and image retrieval tasks, in which some studies have adapted them to be applied to the trademark similarity task [1,11,17]. Next, we describe the datasets created for the tasks.…”

Scale-Adaptive Deep Matching Network for Constrained Image Splicing Detection and Localization

“…In recent years, deep learning algorithms [14][15][16] represented by convolutional neural networks [17][18][19], recurrent neural networks [20] and generative adversarial networks have been widely used in many fields such as image classification [21,22], object detection [23], semantic segmentation [24,25], image retrieval [26], scene understanding [27], etc. and have made a leap forward compared with traditional methods.…”

“…Before the ASPP block, the correlation computation module produces a feature tensor of size W/8 × H/8 × 96. ASPP is the first part of the mask generator with three parallel layers of atrous convolution to capture multiscale features, setting atrous rates with [6,12,18]. Then the feature maps are concatened into a 1 × 1 convolution to reduce channels.…”

Hybrid-Margin Softmax for the Detection of Trademark Image Similarity

“…VGG16 is used to build an SNN. Alshowaish used pre-trained CNNs to build an SNN including VGG16 and ResNet50 [22]. Most of these works focused on data-driven metric learning methods.…”