Thesis (Ph. D.)--State University of New York at Buffalo, 1995. / "May 1995." Includes bibliographical references (p. 80-89). Also available in print.

Published Article / Limits of artificial intelligent, expert systems are defined by the specific hardware limitation of the specific system. Limits can be overcome, or addressed, by giving an intelligent system web access; therefore giving it access to Google's™ vast hardware, search functions and databases. Reverse image searches can be done directly in Google's™ image search bar since October 2011. This reverse image search function is used by the proposed system to do object recognition. Computational creativity, or the ability of a program or computer to show human-level creativity and interaction, is achieved by means of a voice communication of the object identification result to the user. The proposed system interprets the result by doing a definition web search and communicating this to the user. The results show that with the novel interpretation software, it should be possible to use Google™ as an artificial intelligent, computational creative system. This proposed system thus has the ability to do object classification by accessing Google's™ vast hardware, search functions and databases, thereafter would the proposed system search a suitable definition for the classification. All of this information is communicated to the user using voice. These techniques could be used on an automatic guided vehicle, robots or expert systems

This research is concerned with the retrieval of visual or pictorial information from videodisc databases. Videodisc technology has made automated storage and retrieval of high quality visual information possible. A problem is that traditional keyword or text access to pictorial information may be inappropriate if the type of information sought cannot be readily described in words. An answer may be to encourage visual searching or browsing. The challenge lies in creating flexible retrieval systems which will both maximise search efficiency and accommodate the individual user. An experimental retrieval environment was developed to examine visual information search strategies. This system allowed for three search types: keyword search, specific browsing, and scanning. Over two experiments visual information search and browsing strategies were identified and characterised: seeking, focused exploring, open exploring, and wandering. In addition, five factors which influence visual information search strategies were identified: the nature of the information itself, database structure, the task or information need, the user, and the interface. This research combines elements of information retrieval and human factors to point to ways in which visual information retrieval systems can be developed which will meet the needs of their users. System design must take account of individual search behaviour and utilise knowledge of the factors which influence user interaction with the system in the search and retrieval process.

published_or_final_version / Electrical and Electronic Engineering / Master / Master of Philosophy

No description available.

This dissertation describes the application of maximum entropy image restoration to envelope-detected ultrasonic sector scans. The maximum entropy restoration of the image of a point target (phantom) test object is shown to be superior to results obtained from the more familiar Wiener filter. The subsequent application of maximum entropy to an in-vivo clinical ultrasound image, however, illustrates the pitfalls associated with determining the relative merit of an ultrasonic image restoration technique from test object results alone. Since the resolution of sector scan images is substantially worse in the lateral (azimuthal) scan direction than the axial scan direction, the deconvolution filters described in this thesis were applied in the lateral direction only. The maximum entropy method is shown to have certain inherent advantages over linear frequency-domain techniques for the restoration of ultrasonic sector scan images. The positivity constraint inherent in the maximum entropy method is shown to produce restorations with substantially fewer oscillatory artifacts than those produced by Wiener filtering. In addition, the iterative nature of the maximum entropy algorithm is shown to be compatible with the restoration of the undersampled regions in the far field of sector scan images. The restoration of sector scan images is complicated by the spatially varying degradation associated with such images. A novel approach to the restoration of this class of image degradation is presented in this thesis. The widespread use of maximum entropy image restoration has been inhibited by the technique's demanding computational requirements. This problem can be alleviated by the use of high speed computer hardware, and the final chapters of this thesis describe the design and construction of a microcomputer-based array processor. The advantages inherent in the use of such hardware are demonstrated with reference to the maximum entropy restoration of ultrasonic images.

No description available.

No description available.

No description available.

No description available.