Showing papers on "Facial recognition system published in 1978"

Suspect identification following exposure to sketches and Identi-Kit composites

Abstract: A facial recognition study explored the utility of two common image generation techniques--sketches and Identi-kit composites. Subjects saw an image (sketch or composite) and then attempted to select the target face in a series of photographs. The effect of image quality (goodness-of-fit of the image with the target person) was a second variable. Better images led to better recognition performance. Image type was marginally significant--sketches were better than composites. The results have implications for criminal identification systems. Language: en

Recognition of facial features in immediate memory

Abstract: This study sought to determine which facial features are best retained in a recognition test of immediate memory. Following a 30-sec viewing of an entire face in either a front or profile orientation, subjects were tested for feature recognition of the eyes, nose, or mouth in either the same or different orientation. Results showed (1) performance was significantly above chance in each condition, (2) feature selection was superior when study and test orientations were the same, (3) there were differences among the individual features when the study and test orientations were the same, but no differences when the orientations differed, and (4) when the study and test orientations were the same, the eyes and mouth were recognized better than the nose. These data provide converging evidence on the relative importance of the eyes and mouth for facial recognition.

Memory processes in facial recognition and recall

Abstract: The encoding processes of recognition and recall for line-drawn faces were investigated. Subjects randomly received three-alternative forced-choice tests of recognition and probe recall of 20 male faces. Between each inspection and test, subjects performed an interference task for 10 sec. The interference tasks consisted of either identifying the missing facial feature in line drawings or in photographs, or correctly identifying the misspelled words describing different facial features. The results indicate that recognition performance was higher than probe-recall performance for all groups. The analysis of the recognition data suggests that recognition ability decreased as the similarity of the interference task to the target increased. This finding suggests that faces are encoded using visual rather than verbal imagery.