The class of contour map patterns, for example, isobar patterns on a weather map and a geographic elevation map, is an important class of pictorial data, the storage and retrieval management of which have serious implications in the context of an image data bank organization. In this context, we propose a structural tree description of contour maps after first introducing a model for a contour map and defining various concepts and ideas. This tree description has a property that its upper levels describe the structure of the global features of the contour map, while its lower levels describe the structure of the local features of contour clusters. From this tree description, we derive a string representation that contains the global features of the corresponding contour map. We then describe the implementation of these ideas in an automatic description and analysis system for weather map data. Finally, we conclude with a discussion of the applications of the above ideas, the realization of the data storage structure and the retrieval procedures for weather maps.

The class of contour map patterns, for example, geographic elevation map and isobar map, is an important class of pictorial data. Its storage and retrieval management have serious implications in the context of a pictorial data bank organization. In this context, we propose the use of the global description of contour map, a string representation called GDCM, for the storage organization of contour maps. We first present a summary of the basic ideas and concepts that leads to the structural description of contour map and then formulate the global description. To take into consideration the frequencies of occurrence of contour clusters (GDCM symbols), we encode the GDCM, which serves as indexes to contour maps, with the Huffman coded GDCM symbols. After organizing the set of encoded GDCM strings into a digital tree for storing the contour maps, we discuss the resulting space and time complexity. We then apply the above ideas to the storage organization of weather maps and evaluate the space and time complexity of the resulting storage structure. The evaluated results indicate that our proposed storage structure for contour map is a viable one.

The amount of memory space required by a branch-and-bound algorithm depends on the search strategy used in the algorithm. From the viewpoint of implementing branch-and-bound algorithms, it is desirable that the amount of memory space can be bounded to some feasible size. In this paper, we propose two new search strategies for branch-and-bound algorithms, by which the amount of required memory space is controllable. These strategies are named pdfs (parallel depth-first search)" and blis (breadth limited search)", respectively. One of the main results of this paper is that (a) the amount of required memory space of any of these strategies is a linear function of the size of the given problem and (b) the amount of required memory space is controllable by adjusting appropriate parameter. That is, these search strategies are adaptable to the available memory space. Another result of this paper is that the computational performance of a branch-and-bound algorithm, using any of these strategies, can be improved by adjusting appropriate parameters.

In this paper we show an effective algorithm for automatically constructing a simple acceptor (a modified finite state automaton) of line-segments. The algorithm was successfully applied to the hand-written English alphabet and to the randomly generated line-segments.