بازیابی تغییر شکل علامت تجاری در مدل دو بعدی شبه مخفی مارکوف

A new deformed trademark retrieval method based on two-dimensional pseudo-hidden Markov model (2D PHMM) is proposed in this paper. Most trademark retrieval systems focus on color features, shape silhouettes, or the combination of color and shape. However, these approaches adopted individual silhouettes as shape features, leading to the following two crucial problems. First, most trademarks have various numbers of decomposed components, while the silhouette-based approaches cannot handle the variety correctly. Second, the infringement cases in which trademarks are changed by non-rigid deformation, in particular nonlinear deformation, may escape detection. Thus, our method focuses on the overall appearance of trademarks and incorporates color and shape features into 2D PHMM to tackle the above two problems. The reason to involve 2D PHMM is that it has high tolerance to noise and distortion, moreover, contextual information can be incorporated into it in a natural and elegant way. However, 2D PHMM is computation intensive and sensitive to rotation, scale and translation variations. Thus, it is the main originality of this paper to include the advantages of 2D PHMM but to exclude its disadvantages. As a result, similar trademarks can be retrieved effectively, even those with different numbers of components or non-rigid deformation. Various experiments have been conducted on a trademark database to prove the effectiveness and practicability of the proposed method.

Trademark recognition is an important research issue since the increasing number of registered trademarks puts a heavy burden on manual examiners. Hence, it is imperative to develop similar trademark retrieval for automatic trademark recognition, which in turn speeds up manual examination process. The developed trademark recognition methods in the literature include those using color features [1], shape features [2], [3], [4] and [5], or both of them [6], [7], [8] and [9]. However, most shape features used in these approaches are restricted to silhouettes, thus resulting in two crucial problems related to composition and deformation resemblances. The composition resemblance means that two images may look alike although the numbers of components included in the images may be different. Two examples are shown between Figs. 1(a) and (b). The deformation resemblance can be defined in the similar way except that the difference between two images is caused by deformation. Six examples are shown between Figs. 1(a) and (c), (d) and (f). Past approaches might derive low similarity values between the images having either the composition or deformation resemblances due to the weaknesses listed below. First, although some approaches concerned more than one silhouettes, the techniques used to handle differences in the numbers of components such as hierarchical representation [2], combination summation [3], [4], [6], [7] and [8], histogram intersection method [9] or maximum and average terms of similarities [5] are too rough to tackle the composition resemblance problem correctly. Second, most approaches took into account mild non-rigid transformation rather than the general non-rigid and nonlinear deformation.

A new deformed trademark retrieval method based on 2D PHMM is proposed in this paper. By our color quantization method, the number of colors are reduced from 2563 true colors to 36 colors, which in turn abates the requirements of storage and computing time. After that, the log-polar mapping takes into account the translation, rotation and scale variations. Thus, the proposed method can handle the invariant requirement. Moreover, the spatial resolution can be reduced 18–300 times. Obviously, the computation complexity of 2D PHMM can be alleviated. Finally, the flexibility for pattern matching can be increased since the 2D PHMM is high tolerance to noise as well as distortion and contextual information can be incorporated into the 2D PHMM in a natural and elegant way. However, 2D PHMM is computation intensive and sensitive to rotation, scale and translation variations. Thus, it is the main originality of this paper to include the advantages of 2D PHMM but to exclude its disadvantages. As a result, the composition and deformation resemblances can be coped with in the proposed method. Experimental results prove the effectiveness and practicability of our method. Further research may be directed to the following topics. First, parameter-learning strategy can be incorporated into the 2D PHMM to improve the retrieval performance. Second, the color quantization method can be generalized to be more adaptive. Third, the proposed method can be extended to natural images.