Thomas Whalen

The retrieval of images from image databases: trademarks

Abstract This paper focuses on the problem of information retrieval from databases containing images rather than text. We propose an error-tolerant alternative to menus and keywords—the feature-matching approach—in which users describe what they want to retrieve in response to a set of queries. The system matches the users description with descriptions of images already in the database. Database images are then presented to the user in order of similarity to the users description. The present paper serves four purposes: application of our feature-matching approach to a new image domain (trademarks); systematization of the process for developing these systems (articulation of five stages in the process of system development); specification of criteria for selecting features to maximize system performance; and introduction of concepts of power of discrimination and error tolerance to show how measures of these two factors can be used for evaluating system performance and optimizing system development. Eva...

COMODA: a conversation model for database access

Abstract As electronic database technology becomes less expensive, people will want to access information without undergoing special training. These people could use their native language if databases could be accessed through natural language conversations. The approach of the current research is that in order for the computer to be controlled by natural language, the computer does not have to understand it, only respond correctly. The conversation model for database access (COMODA) describes information retrieval as a dialogue. The dialogue is modelled by a series of states, where each state has an utterance that provides some information. The states are linked by transitions that are followed if a parse template matches the input sentence. Provisions are made for backtracking to earlier states, and for changes in topic. A small database of general information about one division of the Federal Government was implemented on an IBM-PC using these principles. When ten untrained people were allowed to conve...

Field testing a natural-language information system: usage characteristics and users' comments

Abstract A field trial was conducted to test a natural-language technology developed by the authors (COMODA) and to dispense AIDS information to the public. This trial allowed users with computers and modems to dial-in to an AIDS information system and ask questions or browse through the information. The system received nearly 500 calls during a two month period. The calls lasted an average of 10 minutes and involved an average of 27 interactions between the user and the computer. Approximately 45% of the interactions were direct naturallanguage questions, and the COMODA system was quite successful in answering these questions. Also, the comments left by the users were extremely positive, with 96% of the users who rated the system giving it a positive rating. The users commented that the COMODA system was an easy-to-use method of accessing valuable AIDS information, and they would like to see the system expanded to cover more topic areas. The users also made useful suggestions on how the system could be improved. It was concluded that the COMODA system is a viable natural-language access system for presenting information to the public.

Suspect identification by facial features.

Often during criminal investigations, witnesses must examine photographs of known offenders, colloquially called ‘mug shots’. As witnesses view increasing numbers of mug shots that are presented in an arbitrary order, they become more likely to identify the wrong suspect. An alternative is a subjective feature-based mug shot retrieval system in which witnesses first complete a questionnaire about the appearance of the suspect, and then examine photographs in order of decreasing resemblance to their description. In the first experiment, this approach is found to be more efficient and more accurate than searching an album. The next three experiments show that it makes little difference if the witness has seen the suspect in person or only seen a photograph. In the last two experiments, it is shown that the feature-based retrieval system is effective even when the witness has seen the suspect in realistic natural settings. The results show that the main conclusions drawn from previous studies, where witnesses searched for faces seen only in photographs, also apply when witnesses are searching for a face that they saw live in naturalistic settings. Additionally, it is shown that is it better to have two raters than one create the database, but that more than two raters yield rapidly diminishing returns for the extra cost.

The effects of delay on the performance of computerized feature systems for identifying suspects

In suspect identification, witnesses examine photos of known offenders in mugshot albums. The probability of correct identification deteriorates rapidly, however, as more photos are examined. Computerized feature systems, which display mugshots in order of similarity to witness descriptions increase success by reducing the number of mugshots examined. Previous experimental tests failed to examine the effects of delay (in eliciting witness descriptions) on recall memory and system performance, as well as the effects of number of raters per mugshot, and live target suspects (rather than using photos of men as targets). In two studies (one with live and one with photo target suspects), subject witnesses described targets after delays varying from several days up to four weeks. Delay had no effect on the number of photos examined, although in the fourth week the accuracy of witness feature descriptions of suspects began to deteriorate. Two raters per mugshot significantly improved performance. More raters did...

Suspect Identification: Traditional Mugshot Album Versus Computerized Feature System

In suspect identification, witnesses examine photos of known offenders in mugshot albums. Identification success deteriorates rapidly, however, as the number examined increases. Feature approaches, where mugshots are displayed in order of similarity to witness descriptions of suspects, increase identification success by reducing the number examined. In this study, subject witnesses searched for target suspects in a database of 1000 mugshots. Feature system users correctly identified more target suspects (90 %) than did album users (60 %) and misidentified fewer innocent suspects (0% versus 38%). For album users, identification success declined as the number of photos examined by witnesses increased. For feature users, the photo of target suspects was, on average, the 16th of 1000 photos examined.

Synthetic designs: a new form of true experimental design for use in information systems development

Computer scientists and software engineers seldom rely on using experimental methods despite frequent calls to do so. The problem may lie with the shortcomings of traditional experimental methods. We introduce a new form of experimental designs, synthetic designs, which address these shortcomings. Compared with classical experimental designs (between-subjects, within-subjects, and matched-subjects), synthetic designs can offer substantial reductions in sample sizes, cost, time and effort expended, increased statistical power, and fewer threats to validity (internal, external, and statistical conclusion). This new design is a variation of within-subjects design in which each system user serves in only a single treatment condition. System performance scores for all other treatment conditions are derived synthetically without repeated testing of each subject. This design, though not applicable in all situations, can be used in the development and testing of some computer systems provided that user behavior is unaffected by the version of computer system being used. We justify synthetic designs on three grounds: this design has been used successfully in the development of computerized mug shot systems, showing marked advantages over traditional designs; a detailed comparison with traditional designs showing their advantages on 17 of the 18 criteria considered; and an assessment showing these designs satisfy all the requirements of true experiments (albeit in a novel way).

Computerized feature systems for identifying suspects: empirical tests using crime scenarios

When a witness in a criminal investigation is asked to identify a suspect in a conventional, randomly ordered album of photographs, identification success deteriorates rapidly as more photos are examined. An alternative is a feature-based retrieval system in which mug shots of previous offenders are displayed in order of similarity to a witnesss description of a suspects facial features. Previous studies have shown that the use of a feature system increases identification success by reducing the number of photographs witnesses examine. However, those studies failed to test feature systems in naturalistic settings. Two experiments are reported showing that feature systems are, indeed, effective in more naturalistic settings. In one, subject witnesses viewed a 37-second videotape of a crime in progress. In the other, they witnessed a live confrontation between two people. Afterwards, witness descriptions of the facial features of each suspect were compared with those of 1000 official police mug shots on file. The number of photos to be examined to find target suspects was reduced from the 500 expected for the traditional album to an average of less than 25.