“…Existing DIR techniques [3], [5], [6], [9], [10], [11], [12], [14], [15], [17], [18], [19], [20] can be roughly divided into two categories. Methods of the first category rely on matching local features.…”
Section: Introductionmentioning
confidence: 99%
“…For instance, Hull [10] imposed a grid to the CCITT G4 pass-code maps of document images and consequently composed feature vectors for recognition. Hu et al [9] proposed interval code to describe the spatial layout of document images; Peng et al [14], [15] used Component-Block-List (CBL) matching to recognize document images with general layout and contents. Compared to the first category, methods in the second category often produce relatively better recognition accuracy, although they are still subject to great improvement for real applications.…”
Document Image Recognition (DIR), a very useful technique in office automation and digital library applications, is to find the most similar template for any input document image in a prestored template document image data set. Existing methods use both local features and global layout information. In this paper, we propose a novel algorithm based on the global matching of Component Block Projections (CBP), which are the concatenated directional projection vectors of the component blocks of a document image. Compared to those existing methods, CBP-based template-matching methods possess two major advantages: 1) The spatial relationship among the component blocks of a document image is better represented, hence a very high matching accuracy can be obtained even for a large template set and seriously distorted input images; and 2) the effective matching distance of each template and the triangle inequality are proposed to significantly reduce the computational cost. Our experimental results confirm these advantages and show that the CBP-based template-matching methods are very suitable for DIR applications.
“…Existing DIR techniques [3], [5], [6], [9], [10], [11], [12], [14], [15], [17], [18], [19], [20] can be roughly divided into two categories. Methods of the first category rely on matching local features.…”
Section: Introductionmentioning
confidence: 99%
“…For instance, Hull [10] imposed a grid to the CCITT G4 pass-code maps of document images and consequently composed feature vectors for recognition. Hu et al [9] proposed interval code to describe the spatial layout of document images; Peng et al [14], [15] used Component-Block-List (CBL) matching to recognize document images with general layout and contents. Compared to the first category, methods in the second category often produce relatively better recognition accuracy, although they are still subject to great improvement for real applications.…”
Document Image Recognition (DIR), a very useful technique in office automation and digital library applications, is to find the most similar template for any input document image in a prestored template document image data set. Existing methods use both local features and global layout information. In this paper, we propose a novel algorithm based on the global matching of Component Block Projections (CBP), which are the concatenated directional projection vectors of the component blocks of a document image. Compared to those existing methods, CBP-based template-matching methods possess two major advantages: 1) The spatial relationship among the component blocks of a document image is better represented, hence a very high matching accuracy can be obtained even for a large template set and seriously distorted input images; and 2) the effective matching distance of each template and the triangle inequality are proposed to significantly reduce the computational cost. Our experimental results confirm these advantages and show that the CBP-based template-matching methods are very suitable for DIR applications.
“…Document image retrieval systems that rely on digital image processing extract features representing images. A number of features such as total number of black pixels in character bounding box areas [5], character shape coding techniques [6], word shape coding [7], vertical and horizontal projection techniques [8], lower and upper bound profiles [9], size and position of component block list in document images [10], document page layout features [11], etc. have been proposed to represent document images.…”
This paper presents a novel approach to Amharic document image retrieval by taking the morphology of the language into account. In addition to the general problems and issues concerning document image retrieval systems, Amharic poses further difficulties in modeling retrieval systems due to its complex morphology. We encode the morphological characteristics of the language to improve query formulation and image database indexing. In this work, morphological generator is used to automatically synthesize surface words from a lexicon containing Amharic root forms resulting in surface word image features coded with their respective root forms. Using this morphological coding, document word images and query terms are processed to be represented by their root forms. In the process of indexing and query formulation, cosine similarity is used for comparing word image features extracted from vertical projection, upper bound profile and lower bound profile. The proposed system is tested by using real-life Amharic documents collected from various sources and experimental results are reported.
“…C. L. Tan et al proposed a document image retrieval method based on horizontal traverse density and vertical traverse density of the character objects [5]. H. Peng et al proposed a document image matching method based on sizes and positions of component block list in document image [6]. C. Wang et al proposed a document image retrieval method based on the proportion of the black pixel area in character bounding box areas [7].…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.