|
I first heard of the term “pattern recognition” during my one-year visiting professorship at MIT during 1958. It was from an article by G. P. Dinneen that had appeared in the proceedings of the Western Joint Computer Conference in 1955. While at M.I.T. my attention was called to the problem of describing line drawings on a digital grid. This led to my formulating the chain code, which subsequently gained wide acceptance. After joining the faculty at New York University in 1960, and with the help of various PhD students, I continued to expand application of the chain code and also to explore its usefulness in pattern recognition. One of the first articles dealing with this topic was presented by me at a conference in Namur, Belgium in 1961 and published in their conference proceedings. As a result of that work, I was invited to participate in what was probably the first dedicated pattern recognition conference, the conference held in Puerto Rico in the fall of 1966. This was followed with an invitation to attend a wonderful NATO-sponsored workshop in pattern recognition, organized by Antonio Grasselli of the University of Pisa, Italy, in the summer of 1968. Grasselli invited participants from every corner of the world, and the workshop, together with the proceedings published by Academic Press in 1969, can be said to have laid a solid foundation for the future development of this field. The next great step in pattern recognition took place at a meeting at Airlie House in Virginia in 1972. The purpose of the meeting, arranged by King-Sun Fu and Azriel Rosenfeld, was to organize a regular biennial conference dealing specifically with this field. Such a conference series already was in existence for artificial intelligence (AI) and there were voices that felt pattern recognition was merely a sub-field of AI. However, at Airlie House it was decided that pattern recognition was distinct from AI and that it should have its own biennial conference series, preferably in years alternating with those of the AI community. So as not to delay the process unduly, the “First International Joint Conference on Pattern Recognition” was set for Washington DC in 1973, with subsequent conferences to be held in 1974 and biennially thereafter. Because of my previous experience in working with IFIP (the International Federation for Information Processing) in which I had been active since 1962 and even had become program chairman of the IFIP World Computer Congress held in Stockholm, Sweden, in 1974, I argued strongly that the pattern recognition community should also form an international organization. The concept for such an organization was approved at the 1974 meeting, and Professor C.J.D.M. Verhagen of the Netherlands and I took on the task of formulating a constitution for the organization. I also arranged to have the organization officially incorporated under the laws of New York State and be approved as being eligible for tax-deductible donations under the laws of the United States. Professor King-Sun Fu of Purdue University became the first president of IAPR and I was elected as the first treasurer. In 1978, at the IAPR meeting in Kyoto, Japan, I was elected president for the term 1978-1980. In 1980, Prof. Azriel Rosenfeld was elected president. I was again chosen to be treasurer in 1982, then holding that office for the next three successive terms, till 1988. I continued to be active also in IFIP and became aware of a movement in IFIP to organize a technical committee dealing with the subject of pattern recognition. To avoid competition between IFIP and IAPR on this topic, I convinced IFIP to invite IAPR to be an “affiliate member”, a concept IFIP subsequently expanded to a number of other technical areas. IAPR accepted the IFIP invitation and asked me to be the first IAPR representative to IFIP, a position I gladly accepted and in which I served for many years. The death of Professor King-Sun Fu in 1985 at the age of 55 was great loss to all of us. I was the IAPR treasurer at the time and I got the Governing Board to approve the creation of an endowment, the income of which would fund a prize to be named in his honor and awarded biennially. The K.S. Fu Prize was to be for pattern recognition what the Nobel prize in physics is for physics. The Fu family donated a significant sum, as did some companies as well as a number of others who had known Professor Fu and knew of his many contributions to IAPR and the pattern recognition community. In 1994, at the IAPR International conference in Jerusalem, I had the honor of being awarded the King-Sun Fu prize for my work with the chain code, and had the additional honor of being made a “Fellow” in IAPR. I have had the privilege of attending every IAPR international conference through 2004, including the two “Joint conferences” that were held prior to the formal founding of IAPR, and am probably the only individual who can make such a claim. In 2004, at the conference that year held in Cambridge, England, I realized that I knew fewer and fewer of the attendees—and fewer knew me. Many of my friends and colleagues from the early days of IAPR had either withdrawn or passed away, and it was time for me also to let younger people take over. There is a time for everything and nothing lasts forever. In terms of my own work, it was focused on line drawings. In the early 1960s the emphasis was on the representation of line drawing data, the matching of line patterns (e.g., coast lines), the solution of jigsaw puzzles solely on the basis of the shape of the pieces, and on the automatic recognition of automobile license plate numbers. In the late 1960s and the early 1970s more emphasis was placed on three-dimensional structures—solution of the so-called “hidden-line” problem—and matching of three-dimensional objects by means of their characteristic views. Over the years my attention shifted toward maps (geographic) data. Together with a colleague from Italy I organized a workshop on map data processing in 1979. During that workshop my attention was called to the difficulty of properly placing the names of map features so that there would be no overlap of names and no ambiguity as to the feature with which the name was to be associated. This led to many publications and finally to the forming of a company, MapText, Inc., dedicated to automatic text placement for maps. The company was bought by a large international company in 2005, and I began my retirement. My first task was to write my memoir – my autobiography entitled Cobblestones and published by Xlibris in 2009. During 2009 and 2010 I served as chairman of the IAPR Advisory Committee and updated the IAPR history originally prepared by Professor Verhagen. Now I am busy with writing an occasional article, keeping in contact with former colleagues, and looking back on a most satisfying and privileged life. |
|
Feature |
|
Other articles in the Getting to Know...Series:
From Document Analysis to Anti-Phishing by Wenyin Liu, IAPR Fellow
In Memoriam…Piero Mussio, IAPR Fellow by Paolo Bottoni and Stefano Levialdi
Image Analysis with Discrete Tools by Gabriella Sanniti di Baja
Has the time for telepresence finally come? by Larry O’Gorman
Biometrics: The key to the gates of a secure and modern paradise by Nalini K. Ratha
Recognition of Human Activities: A Grand Challenge by J.K. Aggarwal
|
|
Herbert Freeman received his B.S.E.E. degree from Union College, Schenectady, NY (1946) and his Masters (1948) and Dr.Eng.Sc. degrees from Columbia University (1956). From 1948 through 1960 he was employed by the Sperry Corporation, where he designed the company's first digital computer, the SPEEDAC, which was completed in 1953. In 1960 he joined the faculty of the Electrical Engineering Department at New York University, becoming chairman of the department in 1968. From 1975 through 1985, he was professor and director of the Image Processing Laboratory in the Electrical, Computer and Systems Engineering department at Rensselaer Polytechnic Institute, in Troy, NY. Since 1985 he has been State of New Jersey Professor of Computer Engineering at Rutgers University in Piscataway, NJ, where he also served as the first Director of the Center for Computer Aids for Industrial Productivity, a university-industry-government collaborative research center. Among some of his significant technical contributions are the invention of the chain code for line-drawing representation (commonly known as the "Freeman chain code"), the concept of characteristic views in machine vision, and the development of high-quality automated cartographic text placement technology. In 1994, the International Association for Pattern Recognition awarded him its K.S.Fu prize "for his pioneering contributions to the representation and analysis of line drawing data," and in 1996, the University of Pavia, Italy, honored him with its Medaglia Teresiana award for his contributions to the field of pattern recognition. Dr. Freeman has held visiting positions at various international academic settings in addition to having served as a founding member, Chairman, President, and Fellow of numerous prominent committees and associations. He is the author or editor of seven books and has published more than 120 articles in the technical literature. In 1997 he founded a company, MapText, devoted to the automated labeling of map features. The company was sold in 2005 and he has been in retirement since that time. |
|
Getting to know...Herbert Freeman, IAPR Fellow |
|
By Herbert Freeman, IAPR Fellow (USA) |
|
Dr. Herbert Freeman, IAPR Fellow ICPR 1994, Jerusalem, Israel For outstanding contributions in image analysis and map data processing and leadership in the IAPR |
