Automatic performance evaluation of printed Chinese character recognition systems

Performance evaluation is crucial for improving the performance of OCR systems. However, this is trivial and sophisticated work to do by hand. Therefore, we have developed an automatic performance evaluation system for a printed Chinese character recognition (PCCR) system. Our system is characterized by using real-world data as test data and automatically obtaining the performance of the PCCR system by comparing the correct text and the recognition result of the document image. In addition, our performance evaluation system also provides some evaluation of performance for the segmentation module, the classification module, and the post-processing module of the PCCR system. For this purpose, a segmentation error-tolerant character-string matching algorithm is proposed to obtain the correspondence between the correct text and the recognition result. The experiments show that our performance evaluation system is an accurate and powerful tool for studying deficiencies in the PCCR system. Although our approach is aimed at the PCCR system, the idea also can be applied to other OCR systems.     

Automatic extraction of roads from aerial images based on scale space and snakes

Abstract. We propose a new approach for automatic road extraction from aerial imagery with a model and a strategy mainly based on the multi-scale detection of roads in combination with geometry-constrained edge extraction using snakes. A main advantage of our approach is, that it allows for the first time a bridging of shadows and partially occluded areas using the heavily disturbed evidence in the image. Additionally, it has only few parameters to be adjusted. The road network is constructed after extracting crossings with varying shape and topology. We show the feasibility of the approach not only by presenting reasonable results but also by evaluating them quantitatively based on ground truth. Received: 22 July 1999 / Accepted: 20 March 2000     

Handwriting recognition or reading? What is the situation at the dawn of the 3rd millenium?

During the last forty years, Human Handwriting Processing (HHP) has most often been investigated under the frameworks of character (OCR) and pattern recognition. In recent years considerable progress has been made, and to date HHP can be viewed much more as an automatic Handwriting Reading (HR) task for the machine. In this paper we propose the use of handwriting invariants, a physical model for a first segmentation, a logical model for segmentation and recognition, a fundamental equation of handwriting, and to integrate several sources of perception and of knowledge in order to design Handwriting Reading Systems (HRS), which would be more universal systems than is currently the case. At the dawn of the 3rd millennium, we guess that HHP will be considered more as a perceptual and interpretation task requiring knowledge gained from studies on human language. This paper gives some guidelines and presents examples to design systems able to perceive and interpret, i.e., read, handwriting automatically. Received October 30, 1998 / Revised January 30, 1999     

The recognition of handwritten numeral strings using a two-stage HMM-based method

In this paper, a two-stage HMM-based recognition method allows us to compensate for the possible loss in terms of recognition performance caused by the necessary trade-off between segmentation and recognition in an implicit segmentation-based strategy. The first stage consists of an implicit segmentation process that takes into account some contextual information to provide multiple segmentation-recognition hypotheses for a given preprocessed string. These hypotheses are verified and re-ranked in a second stage by using an isolated digit classifier. This method enables the use of two sets of features and numeral models: one taking into account both the segmentation and recognition aspects in an implicit segmentation-based strategy, and the other considering just the recognition aspects of isolated digits. These two stages have been shown to be complementary, in the sense that the verification stage compensates for the loss in terms of recognition performance brought about by the necessary tradeoff between segmentation and recognition carried out in the first stage. The experiments on 12,802 handwritten numeral strings of different lengths have shown that the use of a two-stage recognition strategy is a promising idea. The verification stage brought about an average improvement of 9.9% on the string recognition rates. On touching digit pairs, the method achieved a recognition rate of 89.6%. Received June 28, 2002 / Revised July 03, 2002     

Symbol and character recognition: application to engineering drawings

In this paper, we consider the general problem of technical document interpretation, as applied to the documents of the French Telephonic Operator, France Télécom. More precisely, we focus the content of this paper on the computation of a new set of features allowing the classification of multioriented and multiscaled patterns. This set of invariants is based on the Fourier–Mellin Transform. The interests of this computation rely on the excellent classification rate obtained with this method and also on using this Fourier–Mellin transform within a “filtering mode”, with which we can solve the well known difficult problem of connected character recognition.     

Accuracy of a domain decomposition method for the recovering of discontinuous heat sources in metal sheet cutting

This paper describes a method for the retrieval of discontinuous heat sources involved in a metal cutting process. Two smoothing techniques were used in the present study in order to smooth noisy sensor data recorded by temperature sensors. The two smoothing techniques are a least squares polynomial fit and a Lagrangian smoothing. These data are then used to recover the heat source. It is found that the least squares polynomial provides over-smoothed results and the Lagrangian smoothing produces phyically acceptable results of the retrieved heat source. Received: 26 February 1999 / Revised version: 5 July 1999     

Automatic detection of vehicle occupants: the imaging problemand its solution

The automatic detection and counting of vehicle occupants is a challenging research problem that was given little attention until recently. An automated vehicle-occupant-counting system would greatly facilitate the operation of freeway lanes reserved for car pools (high occupancy vehicle lanes or HOV lanes). There are three major aspects of this problem: (a) the imaging aspect (sensor phenomenology), (b) the pattern recognition aspect, and (c) the system architecture aspect. In this paper, we present a solution to the imaging aspect of the problem. We propose a novel system based on fusion of near-infrared imaging signals and we demonstrate its adequacy with theoretical and experimental arguments. We also compare our solution to other possible solutions across the electromagnetic spectrum, particularly in the thermal infrared and visible regions.     

MAGELLAN: Map Acquisition of GEographic Labels by Legend ANalysis

A system named MAGELLAN (denoting Map Acquisition of GEographic Labels by Legend ANalysis) is described that utilizes the symbolic knowledge found in the legend of the map to drive geographic symbol (or label) recognition. MAGELLAN first scans the geographic symbol layer(s) of the map. The legend of the map is located and segmented. The geographic symbols (i.e., labels) are identified, and their semantic meaning is attached. An initial training set library is constructed based on this information. The training set library is subsequently used to classify geographic symbols in input maps using statistical pattern recognition. User interaction is required at first to assist in constructing the training set library to account for variability in the symbols. The training set library is built dynamically by entering only instances that add information to it. MAGELLAN then proceeds to identify the geographic symbols in the input maps automatically. MAGELLAN can be fine-tuned by the user to suit specific needs. Recognition rates of over 93% were achieved in an experimental study on a large amount of data. Received January 5, 1998 / Revised March 18, 1998     

User diversity and design representation: Towards increased effectiveness in Design for All

This paper addresses user modelling for “Design for All” in a model-based approach to Human-Computer Interaction, paying particular attention to placing user models within organisational role- and task-related contexts. After reviewing a variety of user modelling approaches, and deriving requirements for user modelling related to Design for All, the paper proposes a role-driven individualised approach. Such an approach is based on a model-based representation schema and a unifying notation that keeps the user’s models and the contextual information transparent and consistent. Individualisation is achieved by coupling symbolic model specifications with neural networking on synchronisation links between symbolic representation elements. As a result, user modelling for Design for All is achieved not by stereotypical user properties and functional roles, but by accommodating the actual users’ behaviour. Published online: 18 May 2001     

Control of perceived quality of service in multimedia retrieval services: prediction-based mechanism vs. compensation buffers

In multimedia systems end-to-end delay jitter has a great impact on the continuity of information playback. Therefore, it is necessary to introduce appropriate mechanisms to compensate for delay variations, so that the intramedia and intermedia temporal relationships can be preserved. In this paper, two methods for compensation of the network delay jitter in a distributed multimedia retrieval service are compared: the first is based on prediction of the network delay jitter suffered by each information unit and retrieval time modification at the source site; the second is based on a compensation buffer at the destination site. Comparison is made by assuming a master/slave relationship between the monomedia streams composing the multimedia data flow.     

The Effect of Workload and Workshift on Air Traffic Control: A Taxonomy of Communicative Problems

Communication is crucial for air navigation safety: communicative problems are implied in 70% of aviation accidents and incidents. This study investigated the influence of workshift (backward rapid rotation) and workload on air traffic controller (ATCo) communications: a taxonomy of possible communicative errors and incorrectness was designed and a specific grid proposed to analyse the communicative exchanges taking place during the workshifts and under different workloads. The corpus we used to design and test our taxonomy and obtain measures of the communicative performance of ATCos consisted of 10 hours of radio exchanges between tower and approach controllers and pilots in an Italian airport. Results showed that the taxonomy was indeed apt to capture a variety of communicative problems: controllers widely employed a linguistic code strongly deviating from standard phraseology, with a widespread presence of Italian language, of non-standard expressions, ellipses and redundancies. Shiftwork and workload significantly affected the ATCos’ communicative performance: linguistic deviations significantly increased during the nightshift with a low workload, while the most correct exchanges occurred in the morning shift. Correspondence and offprint requests to: Cristina Cacciari, Department of Biomedical Sciences, Via Campi 287, 41100 Modena, Italy. Email: cacciari.cristina@unimo.it     

Composite Device Computing Environment: A Framework for Situated Interaction Using Small Screen Devices

Contemporary small screen devices are used as personal companion or communication devices. However, their physical dimensions constrain the processing, communication and user interface capabilities. Thus, rich content presentation and diverse service access via small screen appliances is limited accordingly. This paper introduces the Composite Device Computing Environment (CDCE) that provides a framework for dynamically detecting and utilising surrounding computing resources to overcome the small screen device limitations. CDCE includes the communication infrastructure in addition to supporting alternative models for interactivity between small screen clients and surrounding computing resources.     

A deformable model of the human iris for measuring small three-dimensional eye movements

This paper describes a deformable model of the human iris which forms part of a system for accurate off-line measurement of binocular three-dimensional eye movements, particularly cyclotorsion (torsion), from video image sequences. At least two existing systems measure torsion from infrared video images by pupil tracking followed by cross correlation using arcs of bandpass-filtered iris texture. Unfortunately, pupil expansion and contraction reduces the accuracy of this method unless drugs are used to constrict the pupil, which causes temporary blurred vision. A five-parameter deformable model of the iris is therefore developed for analysing images obtained without the use of drugs. This model can translate (horizontal and vertical eye motion), rotate (torsion) and scale both uniformly and radially (pupil changes). Torsion measurements obtained with the model are repeatable and accurate to within 0.1°; this performance is illustrated by analysing binocular torsion during fixation on a stationary target. Received: 27 August 1997 / Accepted: 15 January 1998     

RCSP and stop-and-go: a comparison of two non-work-conserving disciplines for supporting multimedia communication

To support emerging real-time applications, high-speed integrated services networks must provide end-to-end performance guarantees on a per-connection basis in a networking environment. Resource management algorithms must accommodate traffic that may get burstier as it traverses the network due to complex interactions among packet streams at each switch. To address this problem, several non-work-conserving packet-service disciplines have been proposed. Non-work-conserving servers may be idle and hold packets under certain conditions, to reconstruct, fully or partially, the traffic pattern of the original source inside the network and prevent the traffic from becoming burstier. We compare two non-work-conserving service disciplines. Stop-and-go uses a multilevel framing strategy to allocate resources in a single switch and to ensure traffic smoothness throughout the network. Rate controlled static priority (RCSP) decouples the server functions with two components: (1) a regulator to control traffic distortion introduced by multiplexing effects and load fluctuations in previous servers, and 2) a static priority scheduler to multiplex the regulated traffic. We compare the two service disciplines in terms of traffic specification, scheduling mechanism, buffer space requirement, end-to-end delay characteristics, connection admission-control algorithms, and achievable network utilization. The comparison is first done analytically, and then empirically by using two 10-min traces of MPEG compressed video.     

Dejittering in the transport of MPEG-2 and MPEG-4 video

When multimedia information is transported over a packet-switched network, the quality of presentation can be degraded due to network delay variation or jitter. This paper presents a dejittering scheme that can be used in the transport of MPEG-4 and MPEG-2 video to absorb any introduced network jitter, thus preserving the presentation quality of transported media streams. The dejittering scheme is based on the statistical approximation of delay variation in the arrival times of video packets carrying encoded clock reference values and a filtering and re-stamping mechanism. In addition, a brief overview of the MPEG-4 system is presented.     

Control and data abstraction: the cornerstones of practical formal verification

In spite of the impressive progress in the development of the two main methods for formal verification of reactive systems – Symbolic Model Checking and Deductive Verification, they are still limited in their ability to handle large systems. It is generally recognized that the only way these methods can ever scale up is by the extensive use of abstraction and modularization, which break the task of verifying a large system into several smaller tasks of verifying simpler systems. In this paper, we review the two main tools of compositionality and abstraction in the framework of linear temporal logic. We illustrate the application of these two methods for the reduction of an infinite-state system into a finite-state system that can then be verified using model checking. The technical contributions contained in this paper are a full formulation of abstraction when applied to a system with both weak and strong fairness requirements and to a general temporal formula, and a presentation of a compositional framework for shared variables and its application for forming network invariants.     

Specifications, Design and Evaluation of an Advanced Human-Adapted Supervisory System

Supervision of highly automated processes is an interdisciplinary research area. Knowledge in the fields of automation, process knowledge, machine engineering, ‘work post’ ergonomics, cognitive ergonomics, working psychology, sociology and so on is necessary to design efficient supervisory systems. This is because supervision is an activity in which man, despite the increasing automation of recent years, is still present. Our research concerns monitoring tasks and diagnosis tasks in continuous processes. In this paper we propose specifications for an advanced human-adapted supervisory system (AHASS) integrating representation characteristics of the production system, such as functional, structural and behavioural aspects based on cognitive engineering models, with the use of advanced algorithms of detection and location. The main idea is to design a supervisory system well balanced between human and technical aspects. Indeed, man–machine system-centred approaches can deal to another extreme like purely technical approaches. These specifications have been used to design an AHASS for a nuclear fuel reprocessing system that has been evaluated through experiments with experienced operators. The results show that the approach is interesting because the boarder between support and assistantship is never crossed.     

Networks of Science and Technology in India: The Elite and the Subaltern Streams

The paper investigates the structure and functioning of the science and technology (S&T) system in India as it has evolved in the post-independence period (1947 onwards). The networks of entities involved in S&T actions, the paper argues, can be categorised, in terms of adopted approaches to agenda and priority setting and accounting for actions, into two streams. The origins and expansion of the two streams are traced. One, the ‘Elite’ stream (high profile and visibility linked to big industry), adopting what the paper has generically termed the ‘Nehruvian’ model of development, is shown to have emerged as a dominant network. The other socially powerful ‘Subaltern’ stream (less visible, closer to ground realities and linked to village and cottage industry), adopting the ‘Gandhian’ model of development, still remains dispersed and outside the consideration of high-level decision-making bodies. The paper stresses the importance of moving the support and attention from the dominant stream to efforts that attempt a synthesis between the dominant and the subaltern.     

On a generalization of the Youla–Kučera parametrization. Part II: the lattice approach to MIMO systems

Within the lattice approach to analysis and synthesis problems recently developed in Quadrat (Signal Syst, to appear), we obtain a general parametrization of all stabilizing controllers for internally stabilizable multi input multi output (MIMO) plants which do not necessarily admit doubly coprime factorizations. This parametrization is a linear fractional transformation of free parameters and the set of arbitrary parameters is characterized. This parametrization generalizes for MIMO plants the parametrization obtained in Quadrat (Syst Control Lett 50:135–148, 2003) for single input single output plants. It is named general Q-parametrization of all stabilizing controllers as we show that some ideas developed in this paper can be traced back to the pioneering work of Zames and Francis (IEEE Trans Automat control 28:585-601, 1983) on H _∞-control. Finally, if the plant admits a doubly coprime factorization, we then prove that the general Q-parametrization becomes the well-known Youla-Kučera parametrization of all stabilizing controllers (Desoer et al. IEEE Trans Automat control 25:399–412, 1980; Vidyasagar, Control system synthesis: a factorization approach MIT Press, Cambridge 1985).