Content based Trademark Retrieval by Integrating Shape with Colour and Texture Information

Abstract

Trademark is one of the most disputed items in Intellectual Property Rights. To grant a trademark, litigation is carried out to investigate if the new trademark applied for matches substantially with an already issued trademark. Considering the fact that the trademark database is very huge and keeps on increasing constantly, the manual search is definitely not a correct solution and an Information and Communication Technology (ICT) based system is required to automate this process.In a content based retrieval system, shape is easily the most important feature for the trademark image. Using shape feature various systems have been developed in the past. Here, a new approach is proposed that integrates shape with color and texture information that improves the results significantly in terms of Precision and Recall. A flexible combination of features is used for improving performance and clustering is applied to the database to enhance retrieval efficiency. General TermsTrademark, Content Based Image Retrieval.

Fuzzy Clustering of Image Trademark Database and Preprocessing Using Adaptive Filter and Karhunen–loève Transform

“…The color feature has been extracted using color histogram for dominant red, green and blue color channels (RGB). 13,15 The database images are partitioned using fuzzy c means clustering into three clusters. The initial testing is done using 500 database images.…”

Detección de texto en imágenes digitales como estrategia para mejorar la recuperación de imágenes por contenido

“…Básicamente emplean el algoritmo antes presentado en [13] y cuyos resultados tienen los mismos valores de las métricas de presicion y recall que los obtenidos usando SWT; ellos extraen el centro de la caja que confina a la o las letras detectadas, obteniendo además la escala y la orientación, para crear así un vector de características para que el sistema CBIR funcione mejor. En [14] otro sistema CBIR se propone y se usa la idea de identificar mediante la segmentación y búsqueda del componente (es decir, el caracter ó letra en cuestión), aplicando propiedades geométricas de los componentes detectados para crear así vectores de características.…”

Content based image retrieval system based on watershed transform for trademark images

“…Besides improving world economy, these practices are also prone to infringement [1,2,3] due to the fact that trademark is a form of intellectual property rights [4]. Thus it is necessary to provide system to facilitate trademark protection as an assurance to the safety of organization business activities.…”

“…In this field, many different techniques have been proposed and implemented such as knowledge-based system [5], geometry representation and spatial similarity [6], contour skeleton segmentation [7], morphological pattern [8], size feature [9], relevance feedback [10], 3D projection [11] and the utilization of shape, color and texture [3,12,13]. Commonly the main problem suffered by the most existing CBIR system above is in the image analysis part which deals with the function to define the content of the image.…”