A Novel Framework for Logo Detection and Recognition from Document Images

Abstract

Logo detection and recognition module is a vital requirement in official automation systems for document image archiving and retrieval applications. In this paper, we present a novel framework for logo detection and recognition based on sequential segmentation and classification strategy of document image. In this framework, using a two-stage segmentation algorithm (consisting of wavelet-based and threshold-based segmentation algorithms) and hierarchical classification by two multilayer Perceptron (MLP) classifiers and a k-nearest neighbor (KNN) classifier, a document image divides to text, pure picture and logo candidate regions. Ultimsately, in final decision, class of logo candidate region is determined based on pre-defined classes. In the hierarchical classification and logo recognition stages, the best feature space is selected by forward selection algorithm from a perfect set of texture and shape features. The proposed structure is evaluated on a variety and vast database consisting of the document and non-document images with Persian and international logos. The obtained results show efficiency of the proposed framework in the real and operational conditions.

Keywords

• Logo detection and recognition
• document image
• two-stage segmentation
• hierarchical classification