Logo Detection in Document Images Based on Boundary Extension of Feature Rectangles

Abstract

A new method of logo detection in document images is proposed in this paper. It is based on the boundary extension of feature rectangles of which the definition is also given in this paper. This novel method takes advantage of a layout assumption that logos have background (white spaces) surrounding it in a document. Compared with other logo detection methods, this new method has the advantage that it is independent on logo shapes and very fast. After the logo candidates are detected, a simple decision tree is used to reduce the false positive from the logo candidate pool. We have tested our method on a public image database involving logos. Experiments show that our method is more precise and robust than the previous methods and is well qualified as an effective assistance in document retrieval.

Logo Recognition, Detection and Logo Based Document Image Retrieval: A Review

“…In G.Zhu [10] it is said that the logo is detected only when the 75% pixels of the detected contains black pixels. For performance evaluation of logo based document retrieval following parameters are used:…”

“…The segmented region which is obtained by vertical analysis is analyzed horizontally for further segmentation in vertical direction. In second part logo is extracted by using boundary extension of feature rectangle [10]. In third part, for logo recognition the boundary of logo region is extracted, whose size and direction is then normalized, and after eliminating its skew angle, for feature extraction the bounding box of logo is then blocked.…”

“…In 2009 H.wang and Y.Chen [10], proposed a method for detecting logos based on boundary extension of feature rectangle. Compared with other method it has some advantages such as it is independent of logo shape and it is fast.…”

Scalable ranked retrieval using document images

“…In recent years, there have been a number of papers exploring retrieval in document images using graphical objects such as logos, which OCR cannot handle. Wang and Chen use a decision tree to grow rectangle boundaries around candidate logos in [19]. In [18], Zhu and Doermann detect logos on a page using connected component features and a Fisher classifier.…”

Identification of Institutional Logo based on Wavelet Features

“…Zhu et al [9] developed a detection system which is segmentation free, fast and layout independent based on generic features and shape descriptors of the connected components and line profiles. Hongye Wang [10] has identified the deficiency of the available method lacking in adoptability to variable real-worl documents. He observed this deficiency from different point of view and reveal its inherent causation, then re-organize the structure of the logo detection and recognition process and integrated into unified frame work.…”