Toyohide Watanabe

An HMM-based segmentation method for traffic monitoring movies

Shadows of moving objects often obstruct robust visual tracking. We propose an HMM-based segmentation method which classifies in real time each pixel or region into three categories: shadows, foreground, and background objects. In the case of traffic monitoring movies, the effectiveness of the proposed method has been proven through experimental results.

An HMM/MRF-based stochastic framework for robust vehicle tracking

Shadows of moving objects often obstruct robust visual tracking. In this paper, we present a car tracker based on a hidden Markov model/Markov random field (HMM/MRF)-based segmentation method that is capable of classifying each small region of an image into three different categories: vehicles, shadows of vehicles, and background from a traffic-monitoring movie. The temporal continuity of the different categories for one small region location is modeled as a single HMM along the time axis, independently of the neighboring regions. In order to incorporate spatial-dependent information among neighboring regions into the tracking process, at the state-estimation stage, the output from the HMMs is regarded as an MRF and the maximum a posteriori criterion is employed in conjunction with the MRF for optimization. At each time step, the state estimation for the image is equivalent to the optimal configuration of the MRF generated through a stochastic relaxation process. Experimental results show that, using this method, foreground (vehicles) and nonforeground regions including the shadows of moving vehicles can be discriminated with high accuracy.

Optimization of Vehicle Assignment for Car Sharing System

Recent advances in information technology enable realization of new on-demand transportation systems. A car sharing system is one of the new on-demand transportation systems and its concept is that people share vehicles to save maintenance cost. A car sharing system is expected as a solution for traffic jams and lack of parkings. There are two types of car sharing systems: the one-way type and the round-trip type. In this paper, we focus on the one-way type. In the one-way type, users can return vehicles to any stations at any time. Thus, it is hard to keep distribution balance of parked vehicles among stations. We propose a method for optimizing vehicle assignment according to distribution balance of parked vehicles. Finally, we report experimental results of our simulation, and evaluate the effect of our method.

Structure recognition methods for various types of documents

In this paper, we describe experimental methods of recognizing the document structures of various types of documents in the framework of document understanding. Namely, we interpret document structures with individually characterized document knowledge. The document understanding process is divided into three procedures: the first is the recognition of document structures from a two-dimensional point of view; the second is the recognition of item relationships from a one-dimensional point of view; and the third is the recognition of characters from a zero-dimensional point of view. The procedure for recognizing structures plays the most important role in document understanding. This procedure extracts and classifies the logical item blocks from paper-based documents distinctly.We discuss the structure recognition methods for three classes of documents: 1) table-form documents, filled-in forms, cataloging lists, etc. — each item block is surrounded by horizontal and vertical line segments; 2) library cataloging cards, name cards, letters, etc. — each item block is separated by spaces; 3) newspapers, pamphlets, etc. — each item block is constructed hierarchically and by combining under roughly specified layouts. The structure recognition procedure is characterized by individual recognition methods: in class 1 documents, binary trees indicating the connective relationships among neighboring item blocks, which are surrounded by line segments; in class 2 documents, binary trees defining the spatial and geometric relationships among neighboring item blocks, which are separated by spaces; and in class 3 documents, composition rules specifying the constructive relationships among neighboring item blocks, which are represented by adjacent relationship graphs. The methods are effective under the knowledge-based frame-work and are integrated complementarily from the top-down (model-driven) and bottom-up (data-driven) approaches. Of course, the integration means vary according to document classes.

Character extraction from noisy background for an automatic reference system

It is important to provide digitized manuscripts of old literature (in page image form) and their electronic text (in full-text form), with an automatic reference mechanism between the images and the text, on the Internet. As an essential step for creating such an automatic reference system, this paper describes the issue of extracting character areas from page images of old handwritten manuscripts. Page images of old manuscripts are usually terribly dirty and considerable large in size. To overcome the first problem, we propose a new effective method for separating characters from noisy background, since conventional threshold selection techniques are inadequate to cope with the image where the gray levels of the character parts are overlapped by that of the background. To solve the second problem, we propose an approach based on a downscaled image and a recursive labeling method for word extraction. This approach is suitable for large size images because it has the advantage of saving memory and reducing processing time.

Toward a practical document understanding of table-form documents: its framework and knowledge representation

A framework of four-layer recognition processes is proposed for understanding documents, and a knowledge representation method adaptable to the understanding of table-form documents is addressed. Although Y. Nakano et al. (1986) looked upon the recognition of multi-kinds of table-form documents as an important subject from a practical point of view, they could not report any successful approach because their knowledge was based only on the physical coordinate data. In the approach presented, this recognition issue was solved, using both the classification tree based on the physical characteristics and the structure description tree based on the logical characteristics. At least, it is not so difficult to classify various kinds of documents into appropriate document classes since table-form documents are well designed on the basis of vertical and horizontal line segments. However, it is not easy in the case of the other documents because the geometric and spatial characteristics of documents are not well specified. It is necessary to investigate the application techniques for the other documents from the viewpoint of the knowledge representation.<<ETX>>

Visual interface for retrieval of electronic-formed books

The authors address visual interface and virtual manipulation for full text management. Their objective is to investigate the retrieval/reference mechanism of computer-readable full texts as if paper-form books were being manipulated directly in the real world. This mechanism is derived basically from the object-linking facility of hypersystems. Of course, the facility must be applicable to the manipulation of a great deal of electronic-formed books, like the traditional information retrieval systems, through hypersystems are suitable to only private filing applications.<<ETX>>

Automatic acquisition of layout knowledge for understanding business cards

Document knowledge plays a very important role in many document image understanding methods. In these methods, the document knowledge is utilized to classify/extract individual item data interpretatively from paper-based sheets as a kind of document model: these days, this knowledge is specified into the document image understanding system in advance. In this paper, we propose an experimental method to acquire the layout knowledge automatically from sample document images. In particular, we focus on the acquisition of the layout of business cards. Our idea is to generate the layout knowledge of business cards from a predefined logical structure, which is used as a kind of meta-knowledge to interpretatively generate the layout knowledge of given business cards.

Layout-Based Approach for Extracting Constructive Elements of Bar-Charts

The analysis/recognition subject of chart structures aims to distinguish individual composite elements structurally, identify their constructive relationships logically, and extract the interpretative information semantically. Many of constructive elements are often allocated to appropriately predefined positions according to the illustrated structures of individual charts. Thus, we can construct a layout knowledge for chart structures with respect to the connective/neighboring relationships among some composite elements. We represent the layout knowledge of bar-chart structures, using a network structure called the layout network. This network contains all possible chart primitives in bar-charts and is composed by all possible relationships among them. In addition to this network, rules are introduced to make the interpretation of this layout network effectual and resolve the ambiguously duplicated representations stepwisely.

Automatic Paper-to-reviewer Assignment, based on the Matching Degree of the Reviewers☆

Abstract There are a number of issues which are involved with organizing a conference. Among these issues, assigning conference-papers to reviewers is one of the most difficult tasks. Assigning conference-papers to reviewers is automatically the most crucial part. In this paper, we address this issue of paper-to-reviewer assignment, and we propose a method to model the reviewers, based on the matching degree between the reviewers and the papers by combining a preference-based approach and a topic-based approach. We explain the assignment algorithm and show the evaluation results in comparison with the Hungarian algorithm.