Essam A. El-Kwae

Content-based retrieval in picture archiving and communication systems

A Content-Based Retrieval Architecture (COBRA) for picture archiving and communication systems (PACS) is introduced. COBRA improves the diagnosis, research, and training capabilities of PACS systems by adding retrieval by content features to those systems. COBRA is an open architecture based on widely used health care and technology standards. In addition to regular PACS components, COBRA includes additional components to handle representation, storage, and content-based similarity retrieval. Within COBRA, an anatomy classification algorithm is introduced to automatically classify PACS studies based on their anatomy. Such a classification allows the use of different segmentation and image-processing algorithms for different anatomies. COBRA uses primitive retrieval criteria such as color, texture, shape, and more complex criteria including object-based spatial relations and regions of interest. A prototype content-based retrieval system for MR brain images was developed to illustrate the concepts introduced in COBRA.

Efficient content-based indexing of large image databases

Large image databases have emerged in various applications in recent years. A prime requisite of these databases is the means by which their contents can be indexed and retrieved. A multilevel signature file called the Two Signature Multi-level Signature File (2SMLSF) is introduced as an efficient access structure for large image databases. The 2SMLSF encodes image information into binary signatures and creates a tree structures can be efficiently searched to satisfy a users query. Two types of signatures are generated. Type I signatures are used at all tree levels except the leaf level and are based only on the domain objects included in the image. Type II signatures, on the other hand, are stored at the leaf level and are based on the included domain objects and their spatial relationships. The 2SMLSF was compared analytically to existing signature file techniques. The 2SMLSF significantly reduces the storage requirements; the index structure can answer more queries; and the 2SMLSF performance significantly improves over current techniques. Both storage reduction and performance improvement increase with the number of objects per image and the number of images in the database. For an example large image database, a storage reduction of 78% may be archieved while the performance improvement may reach 98%.

Document image representation using XML technologies

Electronic documents have gained wide acceptance due to the ease of editing and sharing of information. However, paper documents are still widely used in many environments. Moving into a paperless and distributed office has become a major goal for document image research. A new approach for form document representation is presented. This approach allows for electronic document sharing over the World Wide Web (WWW) using Extensible Markup Language (XML) technologies. Each document is mapped into three different views, an XML view to represent the preprinted and filled-in data, an XSL (Extensible style Sheets) view to represent the structure of the document, and a DTD (Document Type Definition) view to represent the document grammar and field constraints. The XML and XSL views are generated from a document template, either automatically using image processing techniques, or semi-automatically with minimal user interaction. The DTD representation may be fixed for general documents or may be generated semi-automatically by mining a number of filled-in document examples. Document templates need to be entered once to create the proposed representation. Afterwards, documents may be displayed, updated, or shared over the web. The merits of this approach are demonstrated using a number of examples of widely used forms.

Document image matching using a maximal grid approach

A new approach for form document representation using the maximal grid of its frameset is presented. Using image processing techniques, a scanned form is transformed into a frameset composed of a number of cells. The maximal grid is the grid that encompasses all the horizontal and vertical lines in the form and can be easily generated from the cell coordinates. The number of cells from the original frameset, included in each of the cells created by the maximal grid, is then calculated. Those numbers are added for each row and column generating an array representation for the frameset. A novel algorithm for similarity matching of document framesets based on their maximal grid representations is introduced. The algorithm is robust to image noise and to line breaks, which makes it applicable to poor quality scanned documents. The matching algorithm renders the similarity between two forms as a value between 0 and 1. Thus, it may be used to rank the forms in a database according to their similarity to a query form. Several experiments were performed in order to demonstrate the accuracy and the efficiency of the proposed approach.

Model-based bone segmentation from digital X-ray images

A model-based algorithm for long bone segmentation from digital X-Ray images is introduced. The model is based on statistical variations of anatomical data collected after examining diverse bone shapes. This method extends the centroid to boundary distance shape analysis approach. A bone is modeled by two centroid points, one for each of the two epiphysis, and a range of weighted values for the distances between the centroid and the boundary points. To locate the bone in an image, a strong edge belonging to the boundary of the shape should be present within the calculated ranges after edge detection has been performed. The algorithm is scale and rotation invariant. Preliminary results show that the method can identify complete or partial bones, which makes it applicable to detecting common bone fractures.

HIT: a new approach for hiding multimedia information in text

A new technique for hiding multimedia data in text, called the Hiding in Text (HIT) technique, is introduced. The HIT technique can transform any type of media represented by a long binary string into innocuous text that follows correct grammatical rules. This technique divides English words into types where each word can appear in any number of types. For each type, there is a dictionary, which maps words to binary codes. Marker types are special types whose words do not repeat in any other type. Each generated sentence must include at least one word from the marker type. In the hiding phase, a binary string is input to the HIT encoding algorithm, which then selects sentence templates at random. The output is a set of English sentences according to the selected templates and the dictionaries of types. In the retrieving phase, the HIT technique uses the position of the marker word to identify the template used to build each sentence. The proposed technique greatly improves the efficiency and the security features of previous solutions. Examples for hiding text and image information in a cover text are given to illustrate the HIT technique.

Toward automated bone fracture classification

A model is developed for the automated classification of bone fractures via image analysis techniques. The model is based on the widely used fracture classification system developed by the M.E. Mueller Foundation of Bern, Switzerland. The system describes a hierarchy of fractures, six layers deep. It also describes a series of questions to be asked about a given fracture, in which each question answered classifies the fracture into more descriptive subcategories. The model developed considers fracture classification as a tree traversal problem, in which the lower layers of the tree represent more precise categorizations. At each of the trees nodes, algorithms specific to that subcategory determine which of the child nodes will be visited. Digital image processing techniques are most readily applicable to the largest number of nodes. Thus, the initial algorithms in this work are based on image processing techniques. The main contributions of this paper include a model for automated bone fracture classification and the algorithms for classification of a subset of long bone fractures. This work aims to provide a solid model and initial results that will serve as the basis for further research into this challenging and potentially rewarding field.

Shaking snakes using color edge for contour extraction

We propose greedy-algorithm-based shaking snakes for estimating image contours. The proposed snake model shakes a search area over which an energy function is to be minimized. Thus, it can work effectively even though an initial contour is not close enough to a target object. We also use color edges as an image energy term which enables snakes to avoid undesirable local minima when the contour spans a region where gray edges are weak or missing. Experimental results show that the suggested approach is very effective in estimating image contours accurately.

Seeded image segmentation for content-based image retrieval application

Seeded image growing (SRG) algorithm is very attractive for semantic image segmentation but it also suffer from the problems of pixel sorting orders for labeling and automatic seed selection. We design an automatic SRG algorithm, along with a boundary-oriented parallel pixel labeling technique and an automatic seed selection method. In order to support more efficient image access over large-scale database, we suggest a multi-level image database management structure. This framework also supports a concept-oriented image classification via a probabilistic approach. Hierarchical image indexing and summarization are also discussed.

Signature-Based Indexing for Retrieval by Spatial Content in Large 2D-String Image Databases

Image matching and content-based spatial similarity assessment based on the 2D-String image representation has been extensively studied. However, for large image databases, matching a query against every 2D-String has prohibitive cost. Indexing techniques are used to filter irrelevant images so that image matching algorithms can only focus on relevant ones. Current 2D-String indexing techniques are not efficient for handling large image databases. In this paper, the Two Signature Multi-Level Signature File (2SMLSF) is used as an efficient tree structure that encodes image information into two types of binary signatures. The 2SMLSF significantly reduces the storage requirements, responds to more types of queries, and its performance significantly improves over current techniques. For a simulated image databases of 131,072 images, a storage reduction of up to 35% and a querying performance improvement of up to 93% were achieved.