Trademark Similarity Research Articles

Trademark Similarity Evaluation Using a Combination of ViT and Local Features

The origin of the trademark similarity analysis problem lies within the legal area, specifically the protection of intellectual property. One of the possible technical solutions for this issue is the trademark similarity evaluation pipeline based on the content-based image retrieval approach. CNN-based off-the-shelf features have shown themselves as a good baseline for trademark retrieval. However, in recent years, the computer vision area has been transitioning from CNNs to a new architecture, namely, Vision Transformer. In this paper, we investigate the performance of off-the-shelf features extracted with vision transformers and explore the effects of pre-, post-processing, and pre-training on big datasets. We propose the enhancement of the trademark similarity evaluation pipeline by joint usage of global and local features, which leverages the best aspects of both approaches. Experimental results on the METU Trademark Dataset show that off-the-shelf features extracted with ViT-based models outperform off-the-shelf features from CNN-based models. The proposed method achieves a mAP value of 31.23, surpassing previous state-of-the-art results. We assume that the usage of an enhanced trademark similarity evaluation pipeline allows for the improvement of the protection of intellectual property with the help of artificial intelligence methods. Moreover, this approach enables one to identify cases of unfair use of such data and form an evidence base for litigation.

The Procedure of Determining Degree of Similarity between Оbjects in Linguistic Examination

The article describes the research procedures for determining the degree of similarity between the objects of linguistic examination. The procedure is based on the combination of qualitative and quantitative methods and the use of computer tools. The main objective of this study is to describe ways of obtaining the most reliable results, which can be verified. For carrying out of research three sets are allocated: initial object, object compared with initial, and object-construct, which includes the characteristics common for the compared sets. The objects may be interrogation protocols, texts checked for plagiarism, trademark names, newspaper publications and other. Qualitative procedures imply singling out characteristics describing objects, while quantitative procedures allow normalization of parameters identified in the objects. The extraction of characteristics is carried out by expertise, relying on the classifications accepted in linguistics. The analysis of texts with identical content is carried out by selecting identical fragments and estimating their volumes. The analysis of the similarity of trademarks is carried out on the basis of phonetic, graphic, semantic and associative parameters. The analysis of texts for possible authorship is carried out with the help of lexical, morphological and syntactic data. On the basis of the obtained numerical indicators, similarity coefficients are calculated. Characteristics that involve a selection of a yes/no answer are marked with 1 for a positive answer and zero for a negative one. Characteristics that have a numerical expression are compared using correlation coefficients and are recognized as identical when the value is 0.7 or higher. Numeric analytical procedures are generally based on the use of computer services. The numeric data obtained are represented by the coefficients of Jaccard, Sørensen, Kulczynski and Ochiai.

TradeMarker: Artificial Intelligence Based Trademarks Similarity Search Engine

Abstract: A trademark is a mark used by a company or a private human for the purpose of marking products or services that they manufacture or trade in. A restriction on the use of the trademark is necessary to enable sellers and manufacturers to build a reputation for themselves, to differentiate themselves from their competitors and thereby promote their businesses. In addition, the restriction also serves consumers and prevents their misuse by a name similar to another product. This restriction is done through the formal examination and approval of the trademarks. This process entails trademark examination against other approved trademarks which is currently a long manual process performed by experienced examiners. Current state-of-the-art trademark similarity search systems attempt to provide a single metric to quantify trademark similarities to a given mark [6, 7, 8, 9, 10, 11]. In this work we introduce a new way to carry out this process, by simultaneously conducting several independent searches on different similarity aspects - Automated content similarity, Image/pixel similarity, Text similarity, and Manual content similarity. This separation enables us to benefit from the advantages of each aspect, as opposed to combining them into one similarity aspect and diminishing the significance of each one of them Keywords: CNN, OCR, Image processing, Numpy, Scipy, Spyder

Intelligent trademark recognition and similarity analysis using a two-stage transfer learning approach

The ubiquitous and fast-growing e-marketplaces are causing serious concerns of unauthorized trademark usages, especially their pictorial images. There is a significant need for e-commerce service intermediaries and trading sites to actively check whether product images posted online are not infringing upon others’ intellectual property rights (IPRs). To ensure registered trademark (TM) or copyrighted logo-image (logo) protection, this research develops an intelligent system that can detect, locate, and crop (cut) logos posted online and check whether they are substantially or deceptively similar to registered TM logos. This research integrates two deep learning models to achieve the research goal. The first is the logo detection and localization model for cropping trademark like images from complex online merchandise photos, which could have images of many product views and even worn and displayed on a human model. Only the cropped logo image is needed for comparison to a database of registered trademarks. The second model performs TM similarity analysis using the cropped logos compared to the published TM images. Yolo v4 is adopted as the general logo locator for intelligent logo image cropping. The triplet convolutional neural network model is used to fine-tuned for intelligent trademark similarity analysis. The models are trained with an image dataset, combining image samples from LogoDet-3k and images found through web search. The system performance is quantitatively tested using the FlickrLogos-32 dataset and consumer product images extracted from an e-commerce platform. The test results of the system achieve high precision (0.91) for trademark class matching.

Trademark Image Similarity Detection Using Convolutional Neural Network

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.

Факторы смешения товарных знаков: социологический анализ

The aim of the present study is to provide a detailed list of factors influencing the probability of confus-ing similarity of trademarks. The identification of a set of such factors is a practically significant task of applied sociology of management, as it allows to make a comprehensive assessment of the views of the parties in disputes about the similarity of means of individualization based on the data of sociologi-cal expertise. Apart from that, the development of understanding of the phenomenon of confusing similarity is a topical theoretical problem in consum-er behavior research. The author supports the fac-tors analysis with a hypothetical description of the mechanism by means of which each factor contrib-utes to the resulting probability of confusing simi-larity of trademarks in consumer’s mind. The system of factors proposed by the author is a useful tool for selecting a coordinate system where a sociologist can model consumer behavior.

Intelligent trademark similarity analysis of image, spelling, and phonetic features using machine learning methodologies

The rapid development of consumer products with short life spans, along with fast, global e-commerce and e-marketing distribution of products and services requires greater due diligence to protect intangible assets such as brands and corporate logos which can easily be copied or distributed through grey channels and internet sales sites. Trademarks (TMs) are government registered intellectual property rights (IPRs) used to legally protect a companies’ identities and brand equity. The rapid growth of global trademark (TM) registrations and the number of TM infringement cases pose a great challenge for TM owners to detect infringement and take action to protect TMs, consumer trust, and market share. This research develops advanced TM similarity assessment models using machine learning (ML) approaches. Litigation principles over similarity follow US TM laws which are consistent with global TM protection convention under the World Intellectual Property Organization (WIPO). This research covers the similarity analysis of TM spelling, pronunciation, and images, which are most likely to cause TM confusion among customers. The research focuses on deploying machine learning for natural language (spelling and phonetic features) and image similarity analyses. The vector space modeling algorithms are trained and verified for the similarity analysis of TM wordings in both spelling and pronunciation. The convolutional neural network and Siamese neural network models are trained and verified for TM image similarity comparison. The training and testing sets consist of 250,000 and 20,000 different image pairs respectively. This research provides a significant contribution toward implementing intelligent and automated IPR protection. The system solution supports users (companies, TM attorneys, or IP officers) to identify similar registered TMs before registering new TMs ensuring uniqueness to avoid infringement disputes. The solution also supports automatic screening of online content to detect potential infringement of TM images and wording for effective global IPR protection.

Deceptive Similarity of Trade Marks in India

Legal protections for trademarks are doctrinally justified by the need to prevent consumer confusion, which potentially disadvantages both individuals who are tricked by confusing or deceptive trademarks into purchasing goods and services other than those they intended to procure, and the providers of goods and services who lose sales when consumers are confused or deceived. Alternatively phrased, deceptive similarity of trademarks occurs when one party adopts a trademark that is the same as or is so similar to an existing mark that, when it is applied to the second user’s goods or services, the purchasing public is likely to be confused, mistaken, or deceived about the source of goods or services themselves, or about the relationship between the parties that make the goods or provide the services. Referentially compressed into the term “deceptive similarity,” this concept is the touchstone of trademark infringement and passing off actions.

A Comparative Study on the Concept of ‘Separate Observation Theory’ in the Determination of Trademark Similarity

A Comparative Study on the Concept of ‘Separate Observation Theory’ in the Determination of Trademark Similarity

Methodological Reflection in a Pith Helmet Commentary on the Article by R. E. Bumagin and D. M. Rogozin, “Criticism of the Interview Approach in Examining the Similarity of the Appearance of Products Belonging to the Same Product Category”

This paper is a polemical response to the article “Criticism of the Interview Approach in Examining the Similarity of the Appearance of Products Belonging to the Same Product Category”, which also appeared in the Journal of Economic Sociology [2018, vol. 19, no 2, pp. 86-117]. In this work, Roman Bumagin and Dmitry Rogozin claim that in trademark similarity research, it is necessary to take into consideration the overall similarity of designs in the same product category. They also criticize the current research practices’ focus on survey methods and call for a fundamental revision of the decision-making process on trademark similarity. While welcoming the attention given to some important subjects (e.g., the need for controls and the background level of similarity), we question the appropriateness of Bumagin and Rogozin’s research procedure and draw attention to the instances of incorrect citations and the distortion of facts in their text. Using specific examples, we show that the arguments proposed in support of the criticism, in fact, illustrate the advantages of current research practices. The procedure actively uses experimental plans and considers the background level of similarity. Our article also asserts, more generally, that to criticize current decision-making in trademarks’ similarity from the perspective of scientism, as Bumagin and Rogozin have done, fails to reflect the specific conditions of arbitration (in a broad sense) authorities. Their goal is not only to establish the truth but also to resolve economic conflicts, and this requires not only a strict but an understandable research procedure. We conclude that hypercriticism in trademark similarity research causes a “colonial” attitude, and it prevents real research practice improvement.

의약품 상표의 유사 판단에 관한 유럽연합의 판단기준 고찰

의약품 상표의 유사 판단에 관한 유럽연합의 판단기준 고찰

Trademark Infraction Prevention Policies and Challenges

The objective of this paper is identification and analysis of the prevention policies of trademark infraction and challenges to find similarity between trademarks. Additionally, this paper proposed an approach to enhance semantic retrieval system of conceptually similar trademarks using algorithms of machine learning like Naive Bayes (NB), Artificial Neural Network (ANN) and Support Vector Machine (SVM). Similarity of trademarks is calculated using Tversky index, Cosine similarity, Jaccard coefficient etc. The performance of classification algorithms are compared on the parameter like accuracy on a same set of trademarks representing real trademark infraction cases. The proposed approach is the first step to automate the process of finding conceptually similar trademarks.

Multi-faceted assessment of trademark similarity

Trademarks are intellectual property assets with potentially high reputational value. Their infringement may lead to lost revenue, lower profits and damages to brand reputation. A test normally conducted to check whether a trademark is highly likely to infringe other existing, already registered, trademarks is called a likelihood of confusion test. One of the most influential factors in this test is establishing similarity in appearance, meaning or sound. However, even though the trademark registration process suggests a multi-faceted similarity assessment, relevant research in expert systems mainly focuses on computing individual aspects of similarity between trademarks. Therefore, this paper contributes to the knowledge in this field by proposing a method, which, similar to the way people perceive trademarks, blends together the three fundamental aspects of trademark similarity and produces an aggregated score based on the individual visual, semantic and phonetic assessments. In particular, semantic similarity is a new aspect, which has not been considered by other researchers in approaches aimed at providing decision support in trademark similarity assessment. Another specific scientific contribution of this paper is the innovative integration, using a fuzzy engine, of three independent assessments, which collectively provide a more balanced and human-centered view on potential infringement problems. In addition, the paper introduces the concept of degree of similarity since the line between similar and dissimilar trademarks is not always easy to define especially when dealing with blending three very different assessments. The work described in the paper is evaluated using a database comprising 1400 trademarks compiled from a collection of real legal cases of trademark disputes. The evaluation involved two experiments. The first experiment employed information retrieval measures to test the classification accuracy of the proposed method while the second used human collective opinion to examine correlations between the trademark scoring/rating and the ranking of the proposed method, and human judgment. In the first experiment, the proposed method improved the F-score, precision and accuracy of classification by 12.5%, 35% and 8.3%, respectively, against the best score computed using individual similarity. In the second experiment, the proposed method produced a perfect positive Spearman rank correlation score of 1.00 in the ranking task and a pairwise Pearson correlation score of 0.92 in the rating task. The test of significance conducted on both scores rejected the null hypotheses of the experiment and showed that both scores correlated well with collective human judgment. The combined overall assessment could add value to existing support systems and be beneficial for both trademark examiners and trademark applicants. The method could be further used in addressing recent cyberspace phenomena related to trademark infringement such as customer hijacking and cybersquatting.

Trademark image retrieval using weighted combination of sift and HSV correlogram

This paper describes an effective tool to automate the process of trademark similarity checking at the time of registration. A combination of shape and colour feature has been illustrated here so that images taken from different vantage points or levels fall into the same group. This was particularly important for trademark images to curb attempts at trademark infringement through object transformations. SIFT has been used as a powerful technique that is unaffected by various transformations like rotation, scaling, translation, change in view etc. Correlogram on the other hand has been used to describe the colour content of the image which is then combined with SIFT to completely represent a trademark image.

Study of Semantic Retrieval by Data Similarity of Trademarks

Study of Semantic Retrieval by Data Similarity of Trademarks

The Strategy Tool: The Trademark Map of Best 100 Brands in the World

In this research, five steps are brought up to build up the trademark map, including (1) deciding sample range of trademarks, (2) analyzing the first-time information, (3) analyzing the second-time information, (4) building up the trademark map, and (5) analyzing the trademark map. This standard procedure can help enterprises create their trademark maps efficiently. A multi-dimensional scale is used for analyzing and building up the trademark map of the most famous one hundred brands, and 86 consumers are requested to proceed with the experiment of brand identification. The results are shown as follows. (1) To display the distribution of trademark samples clearly by building a visualized map, the level of trademark similarity between samples can be understood. (2) Enterprises can the apply trademark map for judging the identification and feasibility of their trademarks so that they are capable of avoiding tort and creating their own and only brand image.

Studying Factors Causing Wordmark Confusions to Improve Brand Identity

By establishing a trademark map, an enterprise could understand the similarities among trademarks for trademark orientation. This study aims to analyze four similar patterns of word marks, namely (1) Alphabet Similar, (2) Pronunciation Similar, (3) Font Similar, and (4) Color Similar. From 2012 brand value report of BrandZ, Google is selected as the word mark sample in this study, tending to understand the confusion of graphic designers and consumers in the four similar patterns. Aiming at 34 graphic designers with more than 2-year design experiences and 30 consumers, the similarity test of trademark samples is proceeded to construct the trademark map presented by the graphic designers and consumers for detailed analyses and cognitive differences. The experimental results show judging differences in trademark similarity between the two groups that Font Similar is the major factor in trademark confusion. However, graphic designers are not likely to confuse Pronunciation Similar, and consumers do not easily confuse Alphabet Similar. The results could guide enterprises to the concept of trademark map when designing trademarks so as to obtain the optimal brand orientation.

A Conceptual Model of Trademark Retrieval based on Conceptual Similarity

The rapid expansion of e-commerce at the beginning of 21st century has had a significant impact on intellectual property management. A particular area of concern is the misuse of trademarks and trademark protection. Trademarks are proprietary words and images with high reputational value; they are important assets, often used as a marketing tool, which require infringement protection. One of the issues considered during infringement litigation is the visual, conceptual and phonetic similarity of different trademarks. In particular, the conceptual similarity of trademarks is an area never previously studied in information retrieval. This paper focuses on this important aspect by proposing a conceptual model of the comparison process, aimed at retrieving conceptually similar trademarks. The proposed model employs natural language processing and semantic technology to compute the conceptual similarity between trademarks.

Trademark image retrieval using an integrated shape descriptor

Trademarks are distinctive visual symbols with high reputational value, due to the perception of quality and innovation associated with them. They are important reputational assets used as a marketing tool to convey a certain assurance of quality, innovation, and the standards, which the manufacturer seeks to maintain. This motivates the need for trademark protection by providing a solution to prevent infringement. This problem can be addressed by developing retrieval systems capable of comparing the visual similarity of trademarks. This paper contributes to the research in this field by proposing an innovative trademark retrieval technique with improved retrieval performance due to the integration of global and local descriptors. The global descriptor employed is the Zernike moment’s coefficients. The local descriptor is the edge-gradient co-occurrence matrix, derived from the contour information that is considered very important in human perception of visual similarity. The proposed retrieval technique is tested using the standard MPEG-7 shape database of 1400 images and the MPEG-7 trademark database of 3260 images. The results show 5% precision/recall improvement in the case of the MPEG-7 shape database, as well as 2.35% Bull’s eye score improvement and 19.8% NMRR score improvement for the 10 randomly selected trademarks from the MPEG-7 trademarks database.

The Extent to which Trade Marks are Protected against Dilution in Mexico and the United States

This is the text of a thesis submitted (and subsequently passed) for the degree of Master of Studies in Legal Research (MSt) at the University of Oxford, Faculty of Law, in October 2004. The primary purpose of the thesis is to analyse the longstanding treatment of trade mark dilution in the United States with a view to comparing it to equivalent dilution protection available in the Law of Industrial Property of Mexico. Despite a literal reading of the Mexican statute, it is argued that dilution protection is not read at face value and is simply treated as another form of confusion protection for well-known trade marks. Beginning with an understanding of the subject matter and its underlying principles, some arguments for its justification are examined. Relevant cases interpreting the federal anti-dilution statute in the US and the principles that have emerged from such interpretations are exposed. These valuable principles are used as a benchmark by which some parallels are drawn with the Trade Mark and Courts decisions interpreting the Mexican statute. Further, the analysis suggests that both the US and Mexico face difficulties in applying their respective statutes. However, the main focus remains in Mexico and its inconsistencies in determining relevant criteria related to trade mark dilution such renown, consumer recognition, similarity, and evidence to prove it. Finally, it is suggested that urgent legislative guidance is needed to address the failure to read the Mexican statute at face value.