Jaakko Sauvola

Bio: Jaakko Sauvola is an academic researcher from University of Oulu. The author has contributed to research in topics: Mobile computing & Wireless network. The author has an hindex of 17, co-authored 64 publications receiving 3061 citations.

Adaptive document binarization

Abstract: A new method is presented for adaptive document image binarization, where the page is considered as a collection of subcomponents such as text, background and picture. The problems caused by noise, illumination and many source type related degradations are addressed. The algorithm uses document characteristics to determine (surface) attributes, often used in document segmentation. Using characteristic analysis, two new algorithms are applied to determine a local threshold for each pixel. An algorithm based on soft decision control is used for thresholding the background and picture regions. An approach utilizing local mean and variance of gray values is applied to textual regions. Tests were performed with images including different types of document components and degradations. The results show that the method adapts and performs well in each case.

Features in future: 4G visions from a technical perspective

Abstract: Mobile communication is continuing to be one of the hottest areas developing at a booming speed, with advanced techniques emerging in all the fields of mobile and wireless communications. Currently, 3G mobile communication systems are just beginning to be deployed, while research on the next generation of mobile communications, 4G wireless and mobile networks, begin to pave the way for the future. This paper studies the visions of 4G from a technical perspective. After a brief review on the development history and status of mobile communications and related 4G perspectives, we present an overall 4G feature framework based on the kernel concept of integration, in which two key features (diversity and adaptability) of the three targets (terminals, networks and applications) are described in detail. The concepts of both external and internal diversity of each target are defined to illustrate the causes and solutions of the adaptability feature. Then, along the entire 4G domain, each feature in the framework is deeply discussed from a technical standpoint, in which promising techniques and possible research issues for sufficient support of adaptability are also proposed. Finally, a short summary on 4G visions is presented as a continuum of features in the development of the mobile communications world.

Towards connectivity management adaptability: context awareness in policy representation and end-to-end evaluation algorithm

Abstract: An infrastructure based on multiple heterogeneous access networks is one of the leading enablers for the emerging pervasive and ubiquitous computing paradigm, in which the optimal management of diverse networking resources is a challenging problem. This paper presents a context-aware policy mechanism and related end-to-end evaluation algorithm for adaptive connectivity management of multi-access wireless networks. A policy is used to express the criteria for adaptive selection of the best local and remote network interfaces. The best connection can then be used for the establishment of a channel as well as the maintenance of on-going data transmission. Rich context information is considered in the policy representation with respect to user profile and preference, application characteristics, device capability, and network QoS condition. The decision of the best access networks to be used is made on the basis of an end-to-end evaluation process. The decision can be made in both Master-Slave and Peer-to-Peer modes. The paper focuses on the methods for policy representation and connection evaluation algorithm. A case study is presented to show the usability of the proposed policy mechanism and decision-making algorithm in the adaptive management of heterogeneous networking resources.

Plug-and-play application platform: towards mobile peer-to-peer

Abstract: While peer-to-peer (P2P) has emerged as a new hot communication concept among the Internet users, mobile usage of P2P applications is still taking its first steps. This article first elaborates the evolutionary process that P2P architectures are going through. Challenges and requirements for mobile P2P are then identified, followed by a definition of a novel Plug-and-Play Application Platform (PnPAP). This platform enables dynamic selections between diverse P2P and session management protocols while preserving the best available network connectivity through Holistic Connectivity (HCon) management. On-the-fly reconfiguration and run-time parameter optimization can be done with a lightweight interpretable state machine. The concept enables flexible and seamless communications for mobile devices in P2P networks.

Survey over image thresholding techniques and quantitative performance evaluation

Abstract: We conduct an exhaustive survey of image thresholding methods, categorize them, express their formulas under a uniform notation, and finally carry their performance comparison. The thresholding methods are categorized according to the information they are exploiting, such as histogram shape, measurement space clustering, entropy, object attributes, spatial correlation, and local gray-level surface. 40 selected thresholding methods from various categories are compared in the context of nondestructive testing applications as well as for document images. The comparison is based on the combined performance measures. We identify the thresholding algorithms that perform uniformly better over nonde- structive testing and document image applications. © 2004 SPIE and IS&T. (DOI: 10.1117/1.1631316)

반도체 공정 overview

Abstract: With digital equipment becoming increasingly networked, either on wired or wireless networks, for personal and professional use alike, distributed software systems have become a crucial element in information and communications technologies. The study of these systems forms the core of the ARLES' work, which is specifically concerned with defining new system software architectures, based on the use of emerging networking technologies. In this context, we concentrate on the study of distributed systems which bring to life the vision of ubiquitous computing systems, also known as ambient intelligence.

Adaptive Thresholding using the Integral Image

Abstract: Image thresholding is a common task in many computer vision and graphics applications. The goal of thresholding an image is to classify pixels as either "dark" or "light." Adaptive thresholding is a form of thresholding that takes into account spatial variations in illumination. We present a technique for real-time adaptive thresholding using the integral image of the input. Our technique is an extension of a previous method. However, our solution is more robust to illumination changes in the image. Additionally, our method is simple and easy to implement. Our technique is suitable for processing live video streams at a real-time frame-rate, making it a valuable tool for interactive applications such as augmented reality. Source code is available online.